Healthcare and Medical Devices

AHFE International

Accelerating Open Access Science in Human Factors Engineering and Human-Centered Computing

Healthcare and Medical Devices

book-cover

Editors: Jay Kalra

Topics: Healthcare and Medical Devices

Publication Date: 2025

ISBN: 978-1-964867-47-2

DOI: 10.54941/ahfe1005982

Articles

The Accuracy of the Eye Tracking in a Virtual Reality Headset for Possible Research and Clinical Applications

Virtual Reality (VR) headsets are widely used in various clinical and research settings. The reliability and quality of this technology heavily rely on the accuracy of data collected by the VR headsets. The specifications of the VR headsets' accuracy are normally published by the manufacturers. However, the performance claimed by the manufacturers is rarely validated by third-party organizations. Despite its importance, limited research has been focused on the data accuracy of VR headsets, even less so in eye-tracking applications. The main purpose of this project is to invest in the accuracy of eye rotation measurements recorded by the eye-tracking system built into a VR headset. A VR headset with eye-tracking capabilities (HTC Vive™ Pro Eye) was used in this study. For testing purposes, we also developed an eye model that can simulate human eye motion on a controlled pattern with a 30-degree range. The model was used to test the eye-tracking system data collection at frequencies ranging from 10 Hz to 500 Hz, with a step size of 10 Hz. A Unity program was developed to read and export the data, from which the headset’s eye tracking accuracy was assessed at each of the tested frequencies. Our experimental results suggested that the VR headset showed great potential for precise eye rotation measurement. Overall, the correlation between the VR headset measurement and the truth reference was between 0.97 and 0.99 from 10 Hz to 500 Hz. The root mean square error (RMSE) values were from 4.39 to 4.74 for the left eye and 3.63 to 3.67 for the right eye, both in degrees. We suspect that the increased RMSE values in the right eye may be due to the relative position between the VR headset and the eye system during testing. Nevertheless, the high correlation between the measurement and truth reference indicates precision in the estimation.

Ryan Hall, Rui Wu, Matthew Joyner, Zhen Zhu, Brian Sylcottt, Chia-Cheng Lin

Conference Proceedings

Human Factors in an Agile Environment: Capturing Value in Healthcare

Increasingly, healthcare systems seem to be turning to management practices and tools used in manufacturing and software industries, including lean, to structure process improvement. They focus on identifying waste and delay to reduce bottlenecks and improve flow. There are, however, challenges to deploying such tools and methods in a healthcare environment. Expanding the ways we consider attributes such as value and waste and utilizing human factors methods to better understand how people are functioning in the system can assist with the translation of these manufacturing ideas into healthcare domains. By describing different types of value, including value associated with patient-centered care and resilient behavior, we were able to better capture important functionality of the healthcare system. We illustrate the importance of explicitly considering different types of value people may add to a system by examining the activities around delivering gastrointestinal (GI) specialty care to patients via referrals from primary care providers (PCPs). These expanded ways of looking at value and methods for understanding the activities of people within systems can contribute to better comprehension of systems and support more effective process improvement methods.

Helen Fuller, Tamara Winden, Brandon Harpold, Somer Hand, Jacob Huffman, Timothy Arnold

Conference Proceedings

Enhanced Fall Prevention in Nursing Facilities: Assisting Caregivers through Data-Driven Selective Monitoring and Notification

Falls in nursing homes predominantly occur when elderly residents are unwatched, a situation exacerbated by critical workforce shortages in Japan where 69.3% of facilities report caregiver deficits. Our research develops a selective monitoring system that strategically targets high-risk residents through three phases: targeting (identifying risk using body temperature data), monitoring (detecting risky activities in fall-prone locations), and intervening (providing multi-channel feedback). We took an approach to predict the potential occurrence of fall accidents, as well as caregivers' intuitive "sense of risk", achieving practical results despite the former proving challenging due to data imbalance. We believe the prediction of ‘sense of risk’ could serve as a valuable proxy that translates caregivers' tacit knowledge into actionable monitoring protocols in resource-constrained environments. The system delivers notifications through alarm lamps, audio instructions, and smartphone alerts to facilitate timely intervention. Future work will focus on enriching understanding of caregivers' risk assessment, implementing near-miss reporting, and expanded usability testing. This selective approach demonstrates technology's potential to augment human caregiving by focusing on resources where most needed in aging societies.

Taihe Huang, Takuma Kano, Nao Takizawa, Takumi Ohashi, Miki Saijo

Conference Proceedings

Examining the Efficacy of an Improved CanSim for Quantifying Hemodialysis Cannulation Skills

Cannulation of a patient’s vascular access is a daily requisite procedure for initiating hemodialysis for those with End-Stage-Kidney Disease. Skills training and assessment for hemodialysis cannulation needs attention; currently, trainees lack effective teaching tools and practice on patients—leading to stress for the cannulator and potentially multiple attempts with pain and infiltration (extravasation of blood into soft tissue) for the patient. We created a cannulation simulator (CanSim) with the goal of measuring cannulation skill and tested the hypothesis that the simulator’s process metrics are able to predict cannulation outcomes on the simulator. Data collected on CanSim from a recent study with improved simulation technology was compared with a previous dataset collected on an earlier prototype. Multiple sensors were used to measure different aspects of cannulation behavior and outcome on the simulator. The infiltration rate on the improved system was less than half that of the previous prototype (20% v 53%). Additionally, only one trial included an extra attempt (1.4%) in the new group, with 15% requiring more than one attempt on the older simulator. Analysis of performance metrics revealed key predictors of successful cannulation, specifically shallower insertion angles. These results could inform design of objective, reproducible cannulation training for providers in a safe, simulated environment.

Lydia Petersen, Joe Bible, Abhijit Kshirsagar, Lee Sierad, Ravikiran Singapogu

Conference Proceedings

Human Factors Engineering and User- centered Design Principles in the Design and Development of Device Combination Products for Special Patients Populations

The US Food and Drug Administration (US FDA) is a global leader in the regulation of device combination products and founded the Office of Combination Products (OCP) in December 2002, Combination products range from physical or chemical combinations to products packaged together and separately packaged products that need to be used together. The OCP has developed many policies and guidance, in particular, the US FDA Human Factor Guidance, the regulatory lens for this paper (1, 2). In the Combination Product Human Factors component, the US FDA, similar to other leading agencies, in Europe, China, Japan, and WHO, stresses the importance of usability studies in medical device combination product design to promote patient ease of use and error reduction. This guidance further emphasizes the physical safety features of the device when used by the end-user. Device design flaws can cause injury to the end user and prescription compliance to the patient. End-users refer to healthcare practitioners: pharmacists, nurses, doctors administering the drug to the patient, or the patient administering it to oneself (4, 5). The 2024 US FDA draft and China’s National Medical Products Administration (Final, Oct. 2024) guidance are closely aligned in requiring manufacturers to use user-focused design principles in the design and development of new drug delivery devices and recommend specifications based on rigorous usability research rather than technical properties of device components (6, 7). New pharmaceutical products are generally developed for most of the population and largely exclude the special segments of the population which include pediatrics, geriatrics, and people with debilitating diseases or specific physical impairments. (1) Geriatric Population: Impaired vision, cognitive decline, motor sensory challenges.(2) Pediatric Population: Pediatric drug delivery systems repurposed from adult formulations and devices are difficult to administer, leading to compliance issues. Off-label use, physician- directed and Adult devices are difficult to use in pediatrics, i.e. Nasal, meter-dose, and dry powder inhalers. (3) Patient disabilities such as hand dexterity, and color blindness.(4) Patients with specific illness or disability: Rheumatoid Arthritis - Did you test your device or container closure with an arthritic glove; Schizophrenia - Very sensitive to any change in drug product appearance or design. There is a case for including Human Factor Engineering-led user-centric design principles and usability research in designing and developing device combination products targeting these special patient populations (8, 9, 10, 11).References1. Lauritsen, K. J., & Nguyen, T. (2009). Combination products regulation at the FDA. Clinical Pharmacology & Therapeutics, 85(5), 468-470.2. Tian, J., Song, X., Wang, Y., Cheng, M., Lu, S., Xu, W. & Zhang, X. (2022). Regulatory perspectives of combination products. Bioactive Materials, 10, 492-503.3. Schillinger., D. C. (2004). The office of combination products: its roots, its creation, and its role. 4. Jackson, J. (2022, July 11). FDA “hit list” of highest priority medical device for human factor guidance, Blogarithmic Thinking, Starfish Medical.5. World Health Organization. (2022, July). WHO global model regulatory framework for medical devices including in vitro diagnostic medical devices6. Food and Drug Administration. 2024. , Guidance for Industry and FDA Staff. Purpose and Content of Use: Related Risk Analyses for Drugs, Biological Products, and Combination Products. Rockville: Food and Drug Administration.7. ClariMed. (2024, Aug). New NMPA Human Factors Guidelines for Medical Devices in China: What Manufacturers Need to Know.8. Espinoza, J., Shah, P., Nagendra, G., Bar-Cohen, Y., & Richmond, F. (2022). Pediatric medical device development and regulation: current state, barriers, and opportunities. Pediatrics, 149(5).9. Djukic et al., 2020). Training improves the handling of inhaler devices and reduces the severity of symptoms in geriatric patients suffering from chronic obstructive pulmonary disease.10. Schneider, A., Richard, P., Mueller, P., Jordi, C., Yovanoff, M., & Lange, J. (2021). User-Centric Approach to Specifying Technical Attributes of Drug Delivery Devices: Empirical Study of Autoinjector- Cap Removal Forces. Patient preference and adherence, 159-168.11. Randal McCarthy, R & Li, Z (2024, Feb.). The Role of Human Factors in the Design of Drug Delivery Systems to Optimize Patient and Heath Care Provider Use and Compliance, US Annual Medical Device Human Factors and Usability Engineering Conference, Boston.

Randal Mccarthy

Conference Proceedings

Patients over Process: Stratifying Risk in the Design, Development, and Deployment of Artificial Intelligence in Healthcare

The global focus on artificial intelligence (AI) in healthcare and medicine is on the rise. Despite remarkable progress in integrating AI into clinical workflows, gaps in regulation remain a prevalent issue within healthcare systems. Effective regulation of artificial intelligence in clinical practice is essential for managing medico-legal risk and ensuring patient safety. Numerous studies highlight the significant potential for medico-legal risk and the need for clear guidelines on the ethical and safe use of AI in clinical practice. Although there are various concerns that these guidelines must address, our work focused on researching best practices regarding patient-centered factors like patient autonomy, trust and transparency, privacy and security, equity and fairness, and ensuring human oversight. While challenges in AI workflow integration arise from many factors, including human interactions and system inadequacies, the focus on individuals rather than the system has fostered an unsuitable culture for enhancing patient-centered care. Key focus areas include risk stratification strategies and increasing transparency within this inherently complex system, as they play a crucial role in guiding clinical decisions in patient management. Proper integration of AI regulatory frameworks into clinical practice is essential for addressing gaps in the design, development, deployment, and long-term monitoring of AI solutions. Globally, the regulation of AI in clinical practice is continually evolving as governments and legal systems adapt to the rapid advances in AI as a medical device (AIaMD). In Canada, a strategic path forward prioritizes federal and provincial regulations; however, at this stage, they remain fragmented. We advocate for the establishment of uniform guidelines that address the risks, benefits, opportunities, and best practices as AI technologies are integrated into the clinical workflow. Achieving a national standard with clear guidance on the ethical and safe use of AI in clinical practice is recommended to move forward.

Bryan Johnston, Jay Kalra

Conference Proceedings

Using Design Thinking to Improve Student Feedback in Healthcare Simulation

Patient safety remains a critical global challenge, with medical errors contributing to an estimated 400,000 deaths annually worldwide. Simulation-based training, particularly using Standardized Patients (SPs), has emerged as a promising approach to reducing such errors by providing medical students with realistic, hands-on learning experiences in a safe environment. SPs play a multifaceted role in simulation training, including designing case scenarios, delivering feedback, and ensuring the consistency of simulation outcomes. However, despite their importance, SPs face significant challenges in providing effective feedback, often due to limited resources, support, and the complexity of balancing multiple responsibilities. This paper explores the challenges SPs encounter in the feedback process and investigates strategies to better support them in their roles. It also examines the potential of design thinking—a user-centered, innovative problem-solving approach—to enhance SP training and improve the quality of feedback delivery. By engaging stakeholders such as medical educators, SP trainers, and students, this study aims to contribute to the development of more effective and supportive simulation training practices, ultimately enhancing patient safety and the quality of healthcare education

Swetha Anand

Conference Proceedings

Elicitation of risk perception strategies in emergency rooms based on KYT technique and eye tracking stimulated retrospections

In the present paper, we aim at eliciting risk perception strategies from medical doctors and nurses in emergency rooms (ERs). In the research processes, a series of cognitive task analyses including an effective debriefing procedure aided by eye movement recordings as well as eye movement data interpretation scheme are developed to identify individual risk perception strategy and its characteristics. To uncover the cognitive processes performed to find risks/hazards in an ER, we adopt KYT (KIKEN YOCHI Training, hazard prediction training in English) technique. In this technique, examples of various photos found in an ER (e.g., photos in which doctors are caring a patient moved by an ambulance) are shown to a medical staff. By seeing the photos, he/she is asked to explain what are risks, hazards, and potential issues. We record his/her eye movements to analyze his/her risk perception processes. In addition, we use the data as cues to verbalize his/her cognitive processes to obtain elaborated information regarding hidden cognitive processes.A series of KYT-styled experiments in which 15 medical doctors majoring in emergency and critical care medicine and 14 nurses participated were carried out. Six photos were shown to each participant. The photos were taken at ER/ICU in Tokyo Medical and Dental University Hospital. The participant was asked to see the photo based on the assumption that he/she see it in his/her daily working conditions, and what he/she would do in the given situations. Additionally, we asked him/her whether he/she found something relating to hazards/risk. During seeing photos, the participant’s eye movements were recorded. Immediately afterwards, an interview where eye tracking recordings were used as cues to verbalize the participant’s implicit cognitive/perceptional processes during seeing was conducted.Based on the verbal protocols obtained in the interview session, each participant’s cognitive/perceptual processes were carefully traced. In addition, the areas/objects to which most of attention (i.e., more than 80% of time spent) were paid in photos were clearly identified for each participant. From these results, we could find that the exist clear difference between doctors and nurses in risk perception strategies. Medical doctors tended to focus their attention mainly on information sources related to a patient’s vital signs. Nurses, on the other hand, seemed to pay their attention not only to vital signs, but also to information sources related to patient’s mental situation (e.g., a patient’s face to know his/her hidden needs) and other medical staffs to know the status of workloads. Based on all results as well as implications obtained, we discuss insights relating to effective medical care teams composed by doctors, nurses, and other co-medical staffs.

Hirotaka Aoki, Koji Morishita, Takanori Urano, Tomohiro Adachi, Mai Kinoshita, Atsushi Kudo

Conference Proceedings

Advancing Scoliosis Treatment: Development and Evaluation of Anisotropic Textile Brace (ATB) for Enhanced Patient Compliance

Adolescent Idiopathic Scoliosis (AIS) presents significant challenges in treatment adherence, particularly with traditional full-time hard braces, which are often uncomfortable and psychologically burdensome for patients. This study focuses on the development and evaluation of a new generation of Anisotropic Textile Brace (ATB) designed to enhance patient compliance by improving comfort and flexibility while maintaining the efficacy of traditional braces in reducing spinal curvature.Our research addresses the limitations of existing rigid braces. The ATB incorporates intelligent padding and an exoskeleton with hinged vertebrae. These innovations aim to provide corrective forces and optimize treatment outcomes.The study involves a systematic clinical wear trial with 30 subjects aged 10 to 16, diagnosed with AIS. Throughout the trial, we assessed the effectiveness of the ATB using full-spine coronal and sagittal X-ray imaging with an EOS system, measuring parameters such as Cobb angle, pelvic tilt, sacral slope, and lumbar lordosis.Preliminary results suggest that the ATB maintains or reduces spinal curvature without increasing patient discomfort. Continuous feedback from participants regarding wear comfort and flexibility informed iterative design improvements. This study demonstrates the potential of the ATB to revolutionize scoliosis treatment by balancing functionality with enhanced patient compliance, ultimately improving long-term outcomes for AIS patients.

Jingyi Ma, Ka Po Lee, Kenneth Man Chee Cheung, Kai-yu Tong, Joanne Yip

Conference Proceedings

Biological evaluation of antimicrobial treated textiles

Textiles provide a suitable environment for the growth of microorganisms, including fungi and bacteria. Their presence can have detrimental effects on both the fabric and the user. These effects may include unpleasant odors, fabric discoloration, a higher risk of contamination, and a decline in the material's mechanical strength. The transmission of infections through textiles can be mitigated by using antimicrobial fabrics, which either eliminate pathogens on contact or inhibit their reproduction before they spread to another surface or individual. Antimicrobial textiles are created by applying antimicrobial agents to textile substrates or by utilizing fibers that naturally possess antimicrobial properties. This paper is mainly focused on the biological evaluation of antimicrobial treated textiles with doxycycline and collagen hydrolysate. The textile structures were obtained from different fibers such as polyester (PES), cotton/elastane (CO/EL) and cotton/polyester (CO/PES). The antibacterial treatment was carried out by applying the obtained solution on the textile structures using the padding method. The characterization of the treated textiles includes the release profile of active compound, the evaluation of antibacterial activity on two bacterial strains Escherichia coli (E. coli) and Staphylococcus aureus (S. aureus), as well as the assessment of cell viability by MTS and LDH assays. The release kinetics of doxycycline from the textile structures showed a burst release in the first 30 minutes followed by a slow and sustained release until the end of the experiment. The samples presented good results in terms of antimicrobial activity on both bacterial strains, the effect being classified as satisfactory. The viability of HUVEC cells is places between 90.89-95.99%, while the necrosis has low values between 4.01-9.11% suggesting that the antibacterial treated textiles can be considered non-cytotoxic. The obtained results confirm that the textile structures treated with doxycyline and collagen hydrolysate can be used as functional antibacterial textiles in direct contact with human skin.

Alina Vladu, Emilia Visileanu, Alexandra Gabriela Ene, Madalina Georgiana Albu Kaya, Viviana Roman, Carmen Gaidau

Conference Proceedings

Ergonomic investigation on Interventional Radiology in the era of robotic surgery

Interventional Radiology(IVR) is a minimally invasive　treatment by using the small-caliber catheter and X-ray fluoroscopy. As the IVR technique can perform the dilation, occlusion and selective cannulation of the vessel and digestive canal without open-surgery, so demand and clinical cases have increased rapidly. However ergonomic problems of IVR had not been considered. Ergonomic problems during the IVR procedures of arterial catheterization are analyzed and investigated in this study. There are ergonomic problems such as neuro-muscular fatigue and asthenopia due to remote operation under X-ray fluoroscopy, small caliber catheters and inadequate working postures. Development of robotic catheter manipulator for IVR partially solved these problems. However, developments of robotic catheter manipulator are still limited such as coronary and carotid artery diseases, and manual operation by the physician still remains. Ergonomic and technological problems of IVR treatments should be further resolved through further workflow analysis of medical devices and medical staffs.

Kazuhiko Shinohara

Conference Proceedings

Self-monitoring of blood glucose: The perception of physicians who care for older adults in a health service in Mexico

This paper presents the perception of the process of glucose self-monitoring by older adults diagnosed with type 2 diabetes mellitus. The study was conducted in a health service in Mexico using semi-structured interviews to physicians and it was based on the behavioural model. Diabetes mellitus type 2 (DM2) is one of the 3 main causes of death in Mexico. The self-monitoring of blood glucose (SMBG) behaviour is one of the most valuable tools in controlling of diabetes. In health care, it is common for interventions to be developed, implemented or evaluated to promote healthier lifestyle behaviours for patients; however, these interventions are often designed without an analysis or diagnosis to determine what needs to be changed to change the behaviour. This work focuses on the perception of people working in Mexican health services that provide medical care to the older adult population diagnosed with T2DM. The objectives of this research were: (1) Identify the organizational aspects that influence or affect the use of the blood glucose meter (BGM) in elderly patients with T2DM; (2) define the barriers and enablers for older adults to use the BGM detected by clinician in patients with T2DM and whether these characteristics differ with the rest of the population diagnosed with T2DM and; (3) understand the importance of the BGM for the treatment of T2DM in an elderly patient. Six semi-structured interviews with clinicians with specialization in Family Medicine (FM) of the first level of the Mexican Social Security Institute (IMSS) were undertaken. The interviews were divided into five aspects: (a) Clinicians’ background, (b) context and support by IMSS, (c) glucose meter in home and use, (d) information that patients receive, and (e) barriers and enablers to use the BGM. A thematic analysis of the qualitative data collected in the interviews with the clinicians was carried out to identify, analyze and report the patterns. The coding of the themes was based on the theory of the COM-B model. As a result of the interviews, it was identified that SMBG is composed of three different behaviours and that each behaviour requires different capabilities, motivations and opportunities. In order to perform the SMBG behaviour, clinicians considered 12 physical capacities necessary, 22 psychological capabilities, seven physical opportunities, three social opportunities, five reflective motivations and two automatic motivations. Physicians consider that older people have barriers to achieving the behaviour. The study further demonstrated that the target behaviour of SMBG use is not only the interaction with a single medical device; rather the older adult is required to interact with four medical devices to achieve SMBG.

Stephanie Daphne Prado-jimenez, Rosa Rosales-cinco, Carlos Aceves-gonzalez, Alexandra Lang

Conference Proceedings

Socio-Technical Risk Analysis for the Digitalized Transfusion Process: the e-TRAST Tool

The digital transformation of the healthcare sector, while innovative for diagnoses and treatments, presents new challenges related to patient safety and the need to maintain a patient-centered approach. Among complex healthcare contexts, the transfusion sector, inherently both safety-critical and mission-critical, is increasingly characterized by the integration of digital solutions. These technologies, which play a crucial role in managing clinical data and supporting medical decision-making, are essential for ensuring the safety and efficiency of the transfusion process. However, the adoption of such tools has highlighted the need to consider Human and Organizational Factors (HOFs) to ensure the effective and safe integration of technology in high-risk healthcare settings. Although studies and hemovigilance reports have pointed out significant errors—including interoperability issues and inadequate management of IT alerts—that increase process complexity and risks, the literature has shown a lack of models to address these challenges. This master's thesis aims to fill this gap by exploring the impact of digitalization on the transfusion process through a qualitative and quantitative analysis of the risks associated with the interaction among technology, operators, and organizational structure.Methodology: The research process was developed in three main phases. First, a literature review was conducted to identify and classify relevant HOFs in the context of digital healthcare. Then, these findings were integrated into a risk analysis applied to e-health solutions in the transfusion process, resulting in the development of a theoretical model and the creation of a practical tool implemented in an Excel file. This tool was subsequently validated in collaboration with two hospitals and the developer of the software under analysis. Finally, the methodology was tested in a transfusion department of a hospital in Lombardy to calibrate the tool's parameters and verify its effectiveness.Results: The e-TRAST (digitalized Transfusion Risk Analysis from a Socio-Technical perspective) framework was developed by integrating Failure Modes, Effects, and Criticality Analysis (FMECA) with the Cognitive Reliability and Error Analysis Method (CREAM). This combination enables an in-depth analysis of failure modes within the digitalized transfusion process and their root causes. The tool’s underlying logic supports both safety and risk assessments that incorporate human, organizational, and technological factors, providing a holistic perspective on risk and facilitating the contextualization of e-health solutions within their operational environments.The Excel tool revealed that over 25% of failure modes present a higher likelihood of occurrence than previously estimated when human and organizational factors are considered. This tool proved to be effective in pinpointing areas for improvement—both for healthcare institutions, through enhanced training programs and stress management strategies, and for technology developers, by addressing system usability and reliability. In conclusion, the e-TRAST framework facilitates the safer and more efficient adoption of digital technologies within high-risk healthcare environments, ensuring patient safety and operational effectiveness.

Chiara Fasanotto, Annalisa Corradi, Rossella Onofrio, Paolo Trucco

Conference Proceedings

Wearable sit-to-stand-up (STS) Guiding Device Using Asymmetric Vibration Speaker

The lack of physical therapist (PT) resources has become a global problem [1]. The sit-to-stand-up (STS) training is one of the most important PT programs to improve the elderly’s mobility and prevent falling. In this research, a wearable (STS) motion navigation system utilizing asymmetric vibration techniques has been developed. Aiming to help the elderly do PT programs at their own house instead of paying the high cost and difficulty of making an appointment for PT.The asymmetric vibration method in this research uses a vibration speaker to play the asymmetric amplitude signal that drives the speaker to generate a vibration that could have a practical feeling, like pushing or pulling [2]. This kind of poke feeling is similar to the guiding training that the PT doctor is poking the shoulder to direct the motion. Based on this method, our lab has developed an upper-limb rehabilitation training system [3] and a walking training system [4][5]. For this research, the STS motion has been picked up from the PT program. The guiding system mainly has two functions. (a) the first is according to the user’s current STS motion by using an IMU sensor. The system could generate an asymmetric vibration from the vibration model which is attached to the front side of the chest or the back side of the neck to guide the user to lean the body. This will match the key index of the PT training of the recommended STS motion. This will decrease the required torque on the body joint due to this kind of motion [6]. User under the guidance could stand up easily. (b)The Second function is for the sitting down motion, the system will calculate the COG position according to the age, height, and gender information that is input to the system. It will calculate the balanced COG moving tunnel and according to the detected angular data and acceleration for judge the current situation needs what kind of revise. Guide the user through the asymmetric vibration to sit down in a balanced way, preventing falling down.To achieve these two functions, the following points have been researched. 1) The definition of the recommended STS motion was calculated from the simplified 3-D human model by the condition of COG position and the muscle simulation 2) The suitable asymmetric vibration setting was researched in the wave shape frequency and the power. We invite volunteers to vote for the poke feeling and choose the sensitive position around the upper body, 3) The guiding quality was evaluated by the volunteer experiment in the repeated test and the STS motion timing judgment. 4) the guided learning angular data from the volunteer was recorded by motion capture system and compared to the recommended database for evaluating the quality of this system. From the motion comparison results, our proposed device's effectiveness could be evaluated.Reference：[1] N. Hori S., et al., “Trends in outpatient rehabilitation practices in Japan: analysis using the National Database of Health Insurance Claims Open Data,” J. Rural, pp. 125–130, 2022. [2] T. Tanabe, H. Yano, and H. Iwata, “Properties of proprioceptive sensation with a vibration speaker type non-grounded haptic interface,” IEEE Haptics Symposium, pp. 21–26, 2016. [3] H.Y. Duan, T. Q. Wang, H. Lee, E. Tanaka, A Wearable Haptic System for Rehabilitation Based on the Asymmetric Vibration, SII2021, pp. 815-816, (2021).[4] E. Tanaka, H. Y. Duan, K. Osawa, K. Nakagawa, H. Lee, L. Yuge, Development of a Walking Promoter Using Vibration Speaker, LIFE2022, pp. 20-23.(in Japanese)[5] E. Tanaka, K. Osawa, J.-R. Zhuang, X. Wu, Y. Hua, K. Nakagawa, H.-H. Lee, and L. Yuge, “Development of walking assistance devices considering the users’ psychological and physical status,” The 16th IFToMM World Congress (WC2023), pp. 152–162, 2023. [6] E. Tanaka, K. Osawa, J.-R. Zhuang, X. Wu, Y. Hua, K. Nakagawa, H.-H. Lee, and L. Yuge, “Mechanical design of a standing-up assistance apparatus of leaning forward the upper body which can be transformed into a flat-lying posture,” JSME, pp. 712–727, 2011.

Shenghao Yin, Jun Zhou, Keisuke Osawa, Kei Nakagawa, Eiichiro Tanaka

Conference Proceedings

Enhancing Motor Performance in Pediatric Cerebral Palsy: A Preliminary Study on Soft Knee Robotic

Crouch gait is a common pathology in individuals with cerebral palsy (CP), significantly affecting their daily activities. The soleus and gastrocnemius muscles in their shank are often too weak to generate sufficient force against body weight. Soft wearable robotics are compliant, lightweight, and portable. In this study, we aimed to address the gap in soft knee robotic systems for children with CP. This paper introduces the design of a textile-based knee actuator and a control system. It investigates the feasibility of this soft knee robotic system through a preliminary study involving two children with CP. The study includes 20 walking sessions to assess the system's performance.Methods: The actuator of the soft knee robot uses a PVC Nylon composite textile material. The actuator is worn on the back of the subject’s knee joint with a skin-friendly textile brace. The unilateral weight of the soft knee brace is only 0.2 kg. Two ground reaction sensors are placed on the forefoot and heel of the subject to detect gait events during the walking cycle. When the heel strikes the ground, the actuator inflates to assist knee joint extension until toe-off. The subjects participated in training twice a week, totaling 20 sessions over 10 weeks. Each session included 30 minutes of walking training with the soft knee robot.Results: Preliminary training results demonstrated the feasibility of the soft knee robot in improving crouch gait. The knee flexion angles of both subjects were reduced (Subject 1 from 20.56° to 1.9 ° and Subject 2 from 24.21°to 12.1°) during the mid-stance phase after 20 training sessions. The Modified Ashworth Scale (MAS) score of the paretic side knee joint reduced from 1+ to 0 and from 1+ to 1 respectively, indicating an improvement in muscle tone of the spastic knee joint. The subjects' gross motor function scale showed improvement.Conclusion: This work demonstrates the validation of the soft knee robot protocol for extension support in crouch gait with pneumatic and comfortable assistive torque. The pilot testing results indicate that the soft knee robotic system improves knee control and locomotor function during walking.

Dezhi Liang, Shuk Fan Tong, Alistair Mcewan, Darryl Chiu, Joanne Yip, Kai-yu Tong

Conference Proceedings

Evaluating Clinical Efficacy of Optical Motion Tracking with Real-Time Animation for Rehabilitation Monitoring

Rehabilitation is a cornerstone for recovering motor function following conditions such as stroke, Parkinson’s disease, aging, or surgery. These conditions often result in musculoskeletal, neurological, or sensory dysfunctions that impair Activities of Daily Living (ADL), delaying recovery. Clinical studies have shown that repeated rehabilitation programs significantly enhance recovery outcomes. Motion capture systems (mocap) provide a robust method to monitor rehabilitation progress, diagnose biomechanical disorders, and adjust treatment plans. This study evaluates the clinical effectiveness of optical motion tracking systems by conducting quantitative kinematic analyses and integrating real-time animation streaming. The study utilized the OptiTrack motion capture system equipped with seven Flex 13 optical cameras and Motive Tracker software to record movement data. Five healthy participants (aged 19–29 years, M=23, SD=3.67; height 170–195 cm, M=181.6, SD=9.63) were recruited to perform three biomechanical tasks: gait, single-leg squat jump, and straight-leg sidewalk. Movements were analysed under normal and braced conditions to investigate key kinematic variables: knee flexion, dorsiflexion/plantar flexion, and hip abduction. Motion capture data was processed in MATLAB for 3D transformation matrix calculations, and the results were streamed into Unity3D to create real-time animations for visualization.Statistical parametric mapping (SPM) paired t-tests (α=0.05) revealed significant differences between normal and braced conditions. During gait, knee flexion range of motion (ROM) was reduced by 32.06° under braced conditions, indicating a limping motion with limited vertical swing-phase movement. In the single-leg jump test, braced conditions resulted in a 7.2° increase in plantar flexion and reduced jump height, while normal conditions demonstrated greater dorsiflexion and knee flexion, indicating compensation. For the sidewalk test, braced conditions showed reduced hip abduction and increased lumbar engagement, with lumbar flexion increasing from 16.82° to 30.89°, suggesting alternate muscle activation patterns. Real-time animation in Unity3D successfully visualized participant biomechanics, offering potential as a recreational and engaging tool for rehabilitation. While the system provided statistically significant data and detailed motion analyses, there are some limitations in the current approach. The rigid-body tracking method required extensive filtering to mitigate inaccuracies caused by marker occlusion and auto-solve algorithms. This approach differs from dynamic skeletal models, which typically integrate lower-body kinetic plugins, and therefore required additional post-processing to accurately calculate joint angles. In real-world applications, factors such as environmental conditions (e.g., lighting and reflective materials), patient behaviour, and movement variability must be considered. Expanding the study to include a diverse range of injury types and larger, more varied sample sizes will be important for understanding how motion capture can be seamlessly integrated into rehabilitation programs. Machine learning could automate the processing of motion data, enabling faster diagnosis and real-time tracking of movement disorders, such as gait abnormalities or Parkinson's symptoms. Furthermore, the integration of virtual reality (VR) with real-time animation could create more immersive rehabilitation experiences, enhancing patient engagement and motivation during therapy. Real-time applications could also enable home-based monitoring, allowing patients to continue their rehabilitation remotely, while clinicians track progress and provide personalized feedback from a distance. Augmented reality (AR) apps could further enrich this experience, guiding patients through exercises with interactive visuals and real-time feedback.This study highlights the growing potential of motion capture systems, combined with advanced computational tools, to transform rehabilitation. By optimizing motion tracking, enabling more personalized treatment, and improving patient engagement, these technologies have the capacity to enhance recovery outcomes and improve the accessibility of rehabilitation programs.

Kartikeya Walia, Kaivalya Raval

Conference Proceedings

Usability Testing of Healthcare Portals for Individuals with Mental and Physical Disabilities: Assessing Accessibility and User Experience (UX)

As healthcare continues to become more digital, patient portals have become essential tools for patients in their healthcare experience, including but not limited to accessing electronic healthcare records (EHR), scheduling appointments, and messaging healthcare providers. Despite widespread use of these tools, challenges with accessibility continue to exist, disproportionately impacting individuals with cognitive and physical disabilities. This study investigates the usability of healthcare portals for this population with usability mixed-methods tests with individuals experiencing cognitive or physical disabilities to assess how well their needs are met with online patient portals. Ten participants completed nine tasks representative of routine healthcare interactions. Quantitative results indicated that participants with physical impairments took three times longer to complete tasks such as scheduling appointments and locating lab results. Qualitative data revealed shared frustrations across all participants, with many expressing confusion over inconsistent terminology. Emotional hesitation was common, driven by fear of making an irreversible mistake. The findings suggest that task-specific improvements such as simplified navigation and real-time feedback cues are beneficial to ensuring equitable digital health access for users.

Janelle Wilson, Duha Ali

Conference Proceedings

Directional Kinetic Characteristics of Drop Landing for Patients with Functional Ankle Instability

This study aimed to investigate the kinetic characteristics, potential injury risk factors, and energy dissipation strategies of bilateral lower limbs during multidirectional drop landings in patients with unilateral functional ankle instability (FAI). Methods: Fifteen male patients with unilateral FAI participated in this study. Kinetic data were synchronously collected using a Vicon infrared motion capture system and a Kistler 3D force platform during single-leg drop landings performed in three directions (forward/oblique/side, FL/OL/SL) for both the unstable and stable limbs. A repeated-measures analysis of variance was conducted to compare the kinetic performance across directions and between sides. Results: Peak vertical ground reaction force (PvGRF), the time to PGRF in the vertical and lateral directions, the loading rate, and hip joint torques were affected by direction (p < 0.05). Hip torques at initial contact were significantly influenced by limb side (p < 0.05), and an interaction effect between direction and side was observed for ankle plantarflexion torques (p < 0.05). Specifically, the unstable limb ankle plantarflexion torques in FL and OL were lower than those in SL, while on the stable limb, plantarflexion torques in FL were lower than in OL and SL. Furthermore, plantarflexion torques were greater in the stable limb than in the unstable limb during FL and OL (p < 0.05). Conclusions: OL exerted higher medial ankle impact forces, while SL, which combines forward and lateral loading components, placed higher adaptive demands on the unstable ankle. FAI patients relied on compensatory strategies, with increased dependence on the stable limb for energy dissipation during drop landing movements.

Marilyn Meng, Yubo Wang, Qiuxia Zhang

Conference Proceedings

Integrating Explainable Machine Learning Techniques for Predicting Diabetes: A Transparent Approach to AI-Driven Healthcare

Diabetes mellitus is a global health concern affecting millions worldwide, with profound medical and socioeconomic implications. The increasing adoption of machine learning (ML) in healthcare has revolutionized clinical decision-making by enabling predictive diagnostics, personalized treatment plans, and efficient resource allocation. Despite their potential, many ML models are often regarded as "black boxes" due to their lack of transparency, which raises significant challenges in critical fields like healthcare, where explainability is crucial for ethical and accountable decision-making (Hassija et al., 2024).Explainable Artificial Intelligence (XAI) has emerged as a solution to address these challenges by making ML models more interpretable and fostering trust among healthcare practitioners and patients. This paper explores the integration of XAI techniques with ML models for diabetes prediction, emphasizing their potential to enhance transparency, trust, and clinical utility. We present a comparative analysis of popular XAI methods, such as SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and attention mechanisms, within the context of healthcare decision support. These techniques are evaluated based on interpretability, computational efficiency, and clinical applicability, highlighting the trade-offs between accuracy and transparency.The study underscores the critical role of interpretability in advancing trust and adoption of AI-driven solutions in healthcare, while addressing challenges such as balancing model performance with explainability. Finally, future directions for deploying explainable ML in healthcare are outlined, aiming to ensure ethical, transparent, and effective AI implementation.

Amos Njeru, Ruth Wario, Lucy Gitonga, Rosa Njagi, Casam Nyaga

Conference Proceedings

Analyzing Diabetes-Related Hospitalizations: Trends and Insights from NIS 2016–2019 for Health Informatics Applications

Potentially preventable hospitalizations are a major area of concern as they represent a huge financial burden across the healthcare ecosystem. To alleviate this issue, this research investigates characteristics, risk factors, and outcomes related to hospital inpatient stays in the context of diabetic patients. Diabetes is a major public health issue that is approaching epidemic proportions globally. Compared to the early 2000s, the prevalence of diabetes in individuals within the age group of 20 - 79 years has increased by 53.3% in the US. In addition to clinical factors, prior studies emphasized the role of socio-economic factors, health conditions, demographics, and quality of care in influencing hospitalization rates. In this retrospective cohort study, Healthcare Cost and Utilization Project (HCUP) National Inpatient Sample (NIS) dataset (2016-2019) was analyzed. This study identified trends in length of stay (LOS) by highlighting disparities related to demographics, income and payer type with an overall goal to guide administrators and policy makers involved in the design and development of systems and health policy services to implement new action plans and quality initiatives.From 2016 to 2019, it was observed that diabetes-related hospitalizations increased by 6.8%. Females accounted for 51–52% of cases, and most patients were between 18–68 years. White patients comprised the largest proportion (52–53%), while individuals in the lowest income quartile accounted for 38.9–40.8% of diabetes-related hospitalizations. The mean LOS for diabetes-related stays increased slightly from 3.17 to 3.25 days over the four years, with older adults and males experiencing longer stays. Most patients were treated in private, non-profit hospitals, with urban teaching hospitals accounting for most admissions. A multivariate linear regression model was used to analyze the impact of variables such as age, gender, payer type, income, hospital characteristics, and severity of illness on LOS. The results indicate that among diabetic patients, risk factors such as age, demographics, income, and insurance policies associated with in-patient stays are critical and warrant further investigation. Findings of this study suggest that awareness, timely screening, and lifestyle changes from a young age can reduce diabetes-related complications and eventually lower preventable hospitalizations, thus improving the effectiveness of healthcare delivery.

Ruchi Kukde, Jaymeen Shah, Aindrila Chakraborty

Conference Proceedings

Smart Glasses and Augmented Reality to Support Healthcare

Augmented Reality (AR) holds considerable promise in transforming clinical practice by enabling hands-free, real-time access to critical information. This paper examines the current state, challenges, and prospects of integrating AR smart glasses in healthcare environments through a human-centred design framework. Despite technological advances and promising pilot studies, the widespread clinical adoption of AR remains limited due to issues in comfort, spatial accuracy, usability, and insufficient clinical validation. Smart glasses and head-mounted displays (HMDs) such as Microsoft HoloLens have demonstrated their utility in surgical settings, medical training, and remote collaboration. These systems enhance situational awareness and procedural efficiency by overlaying digital information within the clinician’s field of view. However, significant barriers such as ergonomic discomfort, inadequate integration with electronic health records (EHR), cognitive overload, and limited interoperability with hospital systems hinder broader acceptance. The EU-funded POPULAR project addresses these limitations by proposing a human-centred AR Eyewear (ARE) platform tailored for clinical settings. This platform emphasises ergonomic design, ophthalmic customisation, and context-sensitive data presentation, aligning with healthcare workflows and professional needs. A user-centric methodology underpins the development process, involving qualitative and quantitative research with healthcare professionals and educators. Through interviews, focus groups, and usability benchmarking, “training in medical procedures” emerged as the primary application area. Additional functionalities such as vital sign projection, procedural alerts, and medical history access were also prioritised. Early-stage prototypes with side-mounted and top-mounted projection systems underwent testing at the Medical University of Lodz (MUL). Field trials under simulated emergency scenarios revealed user preferences for side-mounted configurations due to superior comfort and visibility. Continuous participant feedback informed iterative design refinements, improving usability and acceptance. The study found that visual clarity, optimal fit, and seamless information integration into clinical tasks are critical to long-term adoption. Despite these advances, challenges remain. Data security and patient privacy concerns are paramount, especially when AR systems incorporate real-time audio-visual capture and EHR access. Additional barriers include device weight, thermal discomfort, and steep learning curves. The successful deployment of smart glasses in healthcare requires addressing these multifaceted issues through robust encryption, ergonomic engineering, intuitive interfaces, and structured user training. Looking ahead, further clinical validation and large-scale deployment are necessary to confirm the effectiveness and safety of AR smart glasses in real-world healthcare scenarios. By embedding user feedback throughout the development cycle, smart glasses can evolve into reliable tools that enhance care quality, clinical efficiency, and professional satisfaction across diverse medical contexts.

Adrian Morales Casas, Clara Solves Camallonga, José Manuel Rojas, Vanessa Jimenez, Fabien Divo, Aneta Andrzejczyk

Conference Proceedings

Artificial Intelligence Revolution in Healthcare: Enhancing Clinical Practice with a New Member of the Team

Artificial intelligence (AI) is a relatively new medical resource with the potential to revolutionize current practices in the prevention and treatment of disease. AI has been defined as computer programs accomplishing tasks traditionally associated with human intelligence such as learning and solving problems. As the ethical benefits of increased efficiency and productivity of AI systems are being realized, the consequences of implementing such transformative technologies has raised ethical and regulatory questions across the globe. AI represents a tool to address longstanding issues in healthcare delivery and can achieve a caliber of healthcare quality that was previously beyond our grasp. However, AI systems may incorporate and often amplify existing patterns of practice, including societal biases and inequitable healthcare practices. Surmounting these ethical and regulatory challenges represents the next frontier in the successful implementation of AI to promote human development and wellbeing. In this study, we examined the current literature and analyzed the scope of practice around the ethical and regulatory issues surrounding AI in medicine and its application to healthcare. Knowledge integration was performed across disciplines relevant to the potential role for AI in facilitating progress, innovation, and quality assurance in healthcare. Thematic analysis was conducted on qualitative data pertaining to both ethical and regulatory challenges concerning the implementation of AI into healthcare practices. The project provided exposure to the innovative field of AI and various strategies related to ethical issues, regulatory laws, quality improvement, and healthcare management. We explored both the reliability and current limitations of AI in order to create best practices guidelines designed to facilitate the successful incorporation of AI into healthcare fields. Ethical challenges of AI such as risk management, data security, and a lack of transparency span all sectors working to implement these new technologies. All medical disciplines working to leverage the potential applications of AI struggle with the ethical challenges of informed consent, autonomy, accountability, biases, and equitable healthcare delivery. The field of laboratory medicine and pathology was a pioneer in the implementation of AI technology. Laboratory medicine and pathology face additional hurdles when ensuring accurate interpretation of results such as unequal contexts, opportunity costs, and low levels of acceptable risk and uncertainty. Rather than an all-or-nothing approach, we suggest a stepwise, transparent, and patient-centered approach with clear boundaries to the incorporation of new tools. The AI-assisted era of medical care will be transformative but will never be void of all risk or ethical challenges. This work represents the first of many steps in using AI technology to optimize healthcare delivery in a way that protects and strengthens the ethical values of medical care.

Jay Kalra, Bryan Johnston

Conference Proceedings

Stethoscope to Algorithm: Equipping Tomorrow’s Doctors for Artificial Intelligence Driven Healthcare

Artificial Intelligence (AI) is transforming the delivery of patient-centred healthcare in Canada and around the globe. As the next generation of healthcare providers completes their medical education, it is critical to equip them with both digital literacy and the skills to effectively integrate AI into patient-centered care. In Canada, medical education is guided by the CanMEDS framework, which has recently transitioned to a competency-based medical education (CBME) model. CBME emphasizes outcomes-based learning, focusing on patient-centered care through direct observation and assessment of Entrustable Professional Activities (EPAs). These EPAs are specific, observable, and measurable units of professional practice, underpinned by milestones that track progression and facilitate continuous feedback to learners. The CBME framework is divided into four stages—transition to discipline, foundation, core, and transition to practice—and is structured around seven CanMEDS roles: Medical Expert, Communicator, Collaborator, Leader, Health Advocate, Scholar, and Professional. Despite the growing influence of AI in healthcare, there is a notable absence of AI-specific competencies for critically evaluating AI tools, interpreting AI-generated outputs, and safely and ethically integrating AI into clinical decision-making. To address these gaps, we propose the integration of AI-specific competencies into the CanMEDS framework. This integration should adopt a constructivist approach, leveraging active learning, case-based scenarios, simulations, and real-world experiences to prepare learners for the complexities of AI in clinical practice. These AI-specific competencies can be adapted for undergraduate medical education and tailored to align with the Royal College’s subspecialty groups, including imaging-based, internal medicine, surgery, pediatrics, critical care, obstetrics and gynecology, psychiatry, and other specialized areas. Central to this approach is the incorporation of feedback loops from both learners and instructors to ensure a sustained focus on patient-centered care. While concerns about cognitive load exist with the introduction of AI-specific competencies, AI’s generative capabilities can be harnessed for self-assessment and reflective practice, potentially mitigating this challenge. Through an exploration of global efforts to integrate AI into medical education, we identified gaps within the current CanMEDS framework and evaluated existing EPAs for Royal College subspecialties using Generative AI. Our findings highlight opportunities to embed AI competencies across training stages and milestones. Preliminary results suggest that the optimal strategy for integrating AI into the CanMEDS framework focuses on the core stage of resident training and the role of the Medical Expert. Rather than creating a new role centered on digital literacy and AI, we recommend augmenting the existing CanMEDS framework to incorporate these competencies. By leveraging the flexibility of the CanMEDS framework, we aim to establish AI-specific competencies that are measurable, progressive, and conducive to longitudinal learning and continuous feedback. This integration will prepare the next generation of healthcare providers to use AI safely and effectively in their practice while maintaining a patient-centered focus.

Jay Kalra, Bryan Johnston, Zoher Rafid-Hamed, Patrick Seitzinger

Conference Proceedings

AI-Assisted Creativity Support for Persona Creation Tools

Creativity is both a crucial and complex experiential process, valued not only for its outcomes but also for the ideation journey (O'Toole, 2024). With the increasing adoption of generative AI technologies, such as AI image generators, studies have shown that these tools can lead to fixation on initial examples, limiting idea diversity and originality (Wadinambiarachchi et al., 2024). To address this, designers must learn to identify and reflect on such fixation to enhance creative collaboration with AI. This study investigates how AI-assisted tools, through interface design and interactive features, can better support the creativity of design students in persona creation. The research employs an experimental design involving task tests with two types of AI-assisted persona creation tools. Evaluations using the Creativity Support Index (Cherry et al., 2014) and post-task interviews provide insights into user experience and creativity performance. Preliminary results indicate that both tools effectively support exploratory creativity, with participants viewing AI as a collaborative assistant rather than a dominant force. Additionally, the findings highlight distinct AI support needs across different stages of the creative process, such as inspiration generation in early ideation and refinement support in later stages. This study emphasizes the importance of designing AI tools that address diverse user needs and align with the phased nature of the creative process. The results contribute to design education by offering new perspectives on AI’s role in creativity and provide practical implications for developing AI-assisted tools that foster innovative workflows.

Shih Ju Wang, Chien-Hsiung Chen

Conference Proceedings

Art and Emotion in the Age of AI: Understanding Human Engagement with AI-Generated and Traditional Art

AI-generated art has become a part of our daily lives, from website illustrations to art exhibitions; generative AI is increasingly influencing traditional art and human-made design. However, there is limited research exploring the impact of AI-generated art on human emotions and aesthetics. This study aims to analyze how people of different age groups perceive and engage with AI-generated art compared to traditional art, exploring the emotional connections they establish with each type of artwork and how these connections vary based on their backgrounds and experiences. In this study, the primary emotions defined by the Geneva Emotional Wheel are employed to analyze the emotional responses of respondents toward both AI-generated art and traditional art. The results indicate that most respondents favor traditional art and feel wider emotional resonance towards it compared to AI-generated art. However, when respondents are presented with a choice between traditional art and AI-generated art without being informed of their origins, AI-generated artworks emerge as the top choice. These results suggests that further exploration into the emotional and aesthetic dimensions of AI-generated art is essential for understanding its potential future acceptance.

Anastasiia Fomina, Yan Luo

Conference Proceedings

Artificial Intelligence in Self-Service: Ushering a New Era of Customer Interaction

In an increasingly digital world, the integration of Artificial Intelligence (AI) in self-service solutions is becoming a critical success factor for organizations especially companies offering services. This paper explores both the challenges and opportunities associated with using AI in self-service systems supporting customer service employees. By automating routine inquiries, companies would increase efficiency as well as increase customer satisfaction through personalized and prompt responses. However, issues of data security and privacy needs to be addressed. This paper studies the impact of AI-powered self-services on the customer satisfaction and employee productivity in the service industry. The paper will provide practical insights into successful implementation strategies of self-services and AI. The paper demonstrates how companies can benefit from the synergy between human expertise and AI technology. The case studies reveal that a successful implementation of AI Self-Services requires a prerequisite digitalization level, employee skills, and agile development mindset. The focus is on analyzing case studies that illustrate the transformative power of AI in customer service. Finally, future trends and developments that could shape the service industry will be discussed. The study concludes that AI-powered self-service solutions can significantly enhance customer service operations when implemented strategically.

Jürgen Müller, Abdulrahman Abdulrazek

Conference Proceedings

Cloud Computing Innovations in the Financial Services Industry: Benefits, Challenges, And Opportunities.

Cloud computing has become a catalyst for change in the financial services industry. To be competitive, organizations are realizing that cloud computing is becoming an essential tool in a constantly evolving digital environment. For companies in the financial sector looking to stay flexible and competitive in the face of global upheaval, cloud computing has become significant in this digital age (Carr, Pujazon, & Vazquez, 2018). With customers seeking more digital solutions, meeting these demands efficiently and effectively can require significant amounts of resources and time. Cloud computing can help organizations develop innovative solutions within their resource constraints, and do so in a more timely fashion. To understand cloud computing’s impact on financial services so it can be leveraged effectively, it will be important to identify the benefits, challenges, and future opportunities.This study seeks to achieve the following. First, we strive to assess the impact of cloud computing on innovative processes within financial services organizations and highlight the benefits. Second, we intend to examine the challenges and obstacles that financial institutions encounter in implementing and using cloud solutions. After achieving the aforementioned objectives, the study aims to offer a thorough grasp of how cloud computing is revolutionizing the financial services industry and identify future opportunities.To accomplish these objectives, we will conduct a literature review and thematic analysis (Braun & Clarke, 2006). The results will identify the benefits, challenges, and future opportunities of cloud computing in the financial services industry. We will discuss cloud technologies’ ability to improve essential aspects such as consumer engagement, organizational agility, providing new services, cutting costs, and operational efficiencies. Other benefits to be addressed include cloud-based platforms assisting in innovation by enabling financial product development cycles to be completed more quickly, successfully meeting new consumer demands. We will examine the challenges as well such as issues associated with storing sensitive data on the cloud raising the danger of data leaks and cyberattacks. Other challenges to be addressed include software identity management, perceived low-security levels, incompatible infrastructure, and compliance issues.Future opportunities to be addressed will include effective technology management and rigorous security assessments to address the previously noted problems. Other opportunities to be highlighted will include implementing emerging technologies such as artificial intelligence for fraud detection. This paper intends to contributerecommendations for practitioners to capitalize on the benefits, address the challenges, and seize opportunities that exist or are coming into existence. We intend to summarize our findings into a framework that practitioners and researchers can utilize in their endeavors. Research topics will also be proposed, such as focusing on methods of removing the identified obstacles and investigating new strategic approaches.REFERENCESBraun, V. & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology (3:2), pp. 77-101.Carr, B. P. D. V. J., Pujazon, D., & Vazquez, J. (2018). Cloud computing in the financial sector part 1: an essential enabler. Institute of International Finance.

Elizabeth Baidoo, Brenda Eschenbrenner

Conference Proceedings

Artificial Intelligence and Media Literacy - Navigating Information in a Digital World

Artificial intelligence (AI) is playing an increasingly important role in the media ecosystem, transforming both the creation and distribution of content. At the same time, the growing influence of AI raises questions about media literacy as a key aspect of critical thinking in the digital age. This article explores the relationship between AI and media literacy by analyzing how automated technologies shape information perception, fake news detection, and critical content evaluation skills. The article combines theoretical review and empirical research to identify the main challenges and opportunities in the field. The focus is on the interaction between AI tools, such as content recommendation algorithms and generative models, and the ability of users to analyze, interpret, and create information. It analyzes the possibilities of using AI as a means of improving media literacy through interactive learning platforms, capabilities for identifying prejudice and hate speech, and as a support tool in journalistic work for effective and rapid data analysis and fact-checking.

Lora Metanova, Neli Velinova

Conference Proceedings

Preliminary Survey on Trust Levels in AI-Clinical Decision Support Systems Among Medical Professionals

Artificial Intelligence-based Clinical Decision Support Systems (AI-CDSS) have the potential to enhance clinical decision-making. However, trust remains a critical challenge influencing their adoption, and the specific direction of trust among medical professionals remains unclear. This study aims to provide empirical evidence on current trust levels in AI-CDSS among medical professionals. A revised version of questionnaire measuring trust in automation was utilized, employing a five-point Likert scale. A total of 29 Thai medical professionals, including both junior and senior practitioners, participated in this study. The findings reveal a spectrum of trust levels, with an average trust score of 3.05 (SD = 0.44). The majority of participants exhibited moderate trust; however, there were tendencies of undertrust and overtrust toward AI-CDSS in 10.34% and 27.59% of participants, respectively. Concerns regarding the capability, reliability, and transparency of AI-CDSS were identified as key barriers to trust. These findings provide valuable insights into trust perceptions, contributing to the development of more trustworthy AI-CDSS solutions and informing strategies for their effective integration into clinical practice.

Yada Sriviboon, Arisara Jiamsanguanwong, Ornthicha Suphattanaporn

Conference Proceedings

A Tool to Complement Human Intelligence: the Math Behind Human Indispensibility

Much ink has been spilled recently on the existential risks and potential of Artificial Intelligence. Between breathy utopian think-pieces and apocalyptic proclamations of the end of meaning in human life, an entire spectrum of outlooks muddies the waters on insight-driven and human-focused paths forward. While philosophical musings and abstract plans are prevalent, relatively little attention has been paid to underwriting integrative deployment as a problem which yields to analysis. The question 'when should an autonomous system step in' is typically framed as demanding a comprehensive world-model of the human subject- oppositional defiance and counter-picking make this approach undesirable, turning the human and AI against one another. Instead, by combining operationalization from psychology, Pareto optimality from economics, norm-based stability from robust controls, and shortest-path algorithms from graph theory, we are able to present mathematically robust conditions under which heterogenous systems provide superior performance to unitary agents, guaranteeing a lower bound on efficacy of joint human/AI teams endorsed by relative advantage. We also derive implicit conditions under which such relationships hold, finding them to be of geometrically increasing scope as task complexity increases. Finally, we demonstrate these relations are not merely theoretical, using sample tasks with adversarial complexity to challenge the assignment paradigm, and find the results to remain within an order-of-magnitude of the predicted robustness condition.

Christopher Robinson, Joshua Lancaster

Conference Proceedings

Ethical Dilemmass and Regulations of Artificial Intelligence Under the Perspective of Nietzsche’s Superman Philosophy Based on the Alien: Romulus

The paper analyzes the ethical dilemmas and regulations of AI from five perspectives, grounded in Nietzsche's Übermensch philosophy. The aim is to provide theoretical support and multiple case studies for the establishment of an ethical order in AI. Firstly, it addresses kinship ethics dilemmas and regulations concerning AI within the context of dual ethics. This section examines the ethical challenges posed by AI through both human-centric and alien-centric lenses. It raises critical questions regarding whether kinship ethics should be predicated on a clear distinction between humans and animals. Secondly, it explores social ethics dilemmas and regulations related to AI against the backdrop of artificial ethics and professional standards. Ethical judgments alongside legal boundaries give rise to significant social ethical challenges associated with AI. The technology exacerbates social inequalities while undermining principles of equal opportunity. This segment poses essential inquiries about whether social ethics necessitate that AI assumes certain social responsibilities, as well as what specific forms these responsibilities should take. Should we redefine social ethics based on fairness when individual circumstances are similar, or justice when they differ? Thirdly, it delves into political ethics dilemmas and regulations pertaining to AI within contexts shaped by imagery suggestions and ethical reinforcements. Using Alien: Romulus as a case study, this section discusses how one might explore the moral imagination surrounding AI driven by its moral autonomy through visual representations. It raises pertinent questions about whether loyalty and integrity constitute political or ethical obligations that must be addressed by AI systems. Fourthly, national ethics dilemmas concerning regulation of AI are examined in light of digital transformation processes and advancements in technological security development. This part prompts reflection on whether a great power’s responsibilities represent a matter of national ethics for AI. Finally, the ethical dilemmas surrounding Earth and the regulation of AI within the framework of bioethics and ethical care are examined. This paper poses the question of whether concepts such as co-assistance, co-integration, co-sharing, and co-prosperity represent essential issues of Earth ethics that AI must address.

Yazhou Chen

Conference Proceedings

Perceptions and Usage of AI-based Technology among Preschool Children in Bulgaria

This study investigates the attitudes of parents and teachers of preschool children (aged 3–6 years) toward the emergence and use of AI-based technologies, with a focus on Bulgaria. Utilizing an online survey format, data were collected during October 2024 from parents and teachers (N=150), primarily residing in urban areas. The findings reveal that while AI-driven technologies such as smartphones, tablets, and smart TVs are integrated into children’s daily life, newer AI tools like virtual assistants and creative AI applications remain underutilized, especially in kindergartens. Teachers primarily use AI-related tools for educational purposes, such as e-blackboards and multimedia, but report limited training and information about emerging AI technologies. Parents were found to be more open to integrating AI-based tools at home, though primarily for practical applications relevant to daily activities. Both groups expressed dissatisfaction with the existing regulatory frameworkin the country, citing inadequacies in policies addressing the challenges of AI usage for vulnerable age groups. The study highlights the importance of a more inclusive approach to understanding AI exposure among children, as well as the need for targeted policy reforms and training programs. The findings contribute to ongoing discussions about integrating AI into early childhood education and provide actionable insights for educators, parents, and policymakers.

Lyubomir Kolarov

Conference Proceedings

AI vs. Authentic: Decoding Architectural Imagery

As AI becomes increasingly integrated into design processes, accurately distinguishing AI-generated architectural images from real photographs is crucial for effective communication and decision-making in the field. Aim: This study explored how experienced designers perceive and identify AI-generated images, focusing on the challenges they encounter and the visual cues they rely on to assess authenticity. Method: Employing a mixed methods approach, five designers (1–20 years of experience) from a single firm participated in an hour-long focus group session on the Miro platform. They examined 16 images—8 AI-generated and 8 real—and were asked to identify AI-generated visuals. Annotations and discussions were thematically analyzed to capture participants’ decision-making processes and patterns of observation. Result: Overall, participants correctly classified 65% of exterior images and 70% of interior images. Analysis revealed five recurrent themes: subtle distortions in spatial elements, distorted or “demon-like” human features, warped backgrounds and inconsistent perspectives, over-perfection that lacked real-world imperfections, and reliance on professional domain knowledge. Night shots and images containing people presented consistent difficulties, while architectural expertise bolstered participants’ confidence in detecting anomalies. Limitation: Time constraints, limited zoom functionality on the Miro platform, and occasional confusion with voting mechanics potentially reduced thoroughness and accuracy. Environmental factors, including early-finishers discussing progress, introduced additional distractions that may have biased responses. Conclusion: These findings highlight how architectural expertise, image content, and technological constraints shape the process of identifying AI-generated images. As part of a broader ongoing study also including participants without an architectural background, this research underscores the importance of examining how diverse user groups approach AI-generated visual content.

Hamid Estejab, Sara Bayramzadeh

Conference Proceedings