AHFE Open AccessHealth Informatics and Biomedical Engineering Applications
Editors: Jay Kalra
Topics: Healthcare and Medical Devices
Publication Date: 2023
ISBN: 978-1-958651-54-4
DOI: 10.54941/ahfe1003448
Articles
Digital Informed Consent for Older Adults in Emergency Department Research
The objective of the informed consent (IC) process is to inform potential participants about the purpose, procedures, risks, and benefits associated with clinical research and medical procedures. Traditional paper consent processes are generally long and confusing, especially in busy settings for research such as the emergency department (ED). We describe how we used a tablet-based digital IC process to recruit (N=1,002) older adults for an elder mistreatment study in the ED. Methods: The Virtual Multimedia Interactive Informed Consent (VIC) consent tool was previously developed and tested in an AHRQ-funded R21 study and was found to be usable, acceptable, and it enhanced participants’ comprehension and satisfaction when compared to a traditional paper-based IC process (Abujarad et al., 2021a). VIC was developed using a user-centered design (UCD) approach, incorporating digital coaching, multimedia features such as animated videos to explain research procedures, automated text-to-speech audio, and automated teach-back to emphasize key concepts. The VIC digital consent tool was used to recruit patients for an NIA-funded R01 study evaluating the feasibility of the VOICES Elder Mistreatment Intervention, a self-administered digital health intervention to increase identification of elder mistreatment in ED settings. Due to the complexities of elder mistreatment identification, we recognized the need for an IC process that ensures participant privacy, autonomy, and comprehension, with particular focus on the risks and benefits of recognizing and disclosing mistreatment. A total of 1,002 participants ages 60 and older were consented and enrolled during their visit in the ED. Results: A total of 1,204 of eligible participants agreed to participate in the study and started the consent, of whom 1,012 (84%) participants completed the consent process and enrolled in the VOICES study. Of the 192 (16%) participants who were not enrolled in the study: 158 (13%) did not complete the IC process for varying reasons, the most common reason being due to pain, and 34 (3%) completed the IC fully and chose not to participate in VOICES study. Of the consented participants, 99% fully completed the VOICES study and filled all surveys. Consented participants included older adults from 60 to 102 years old with a mean age of 73.5. Most participants were female, white, and high school educated or higher.Discussion: We believe that the use of digital IC process benefitted the participants who were able to complete the IC process on their own and with minimal help from the study coordinators. We received a high study completion rate among consented participants, and we believe that emphasizing key concepts and using multimedia to explain the more complicated research topics helped better educate potential participants to make a true informed decision about their participation in the VOICES study. It is likely that research participants who have a better understanding of the nature of the study are more likely to finish study procedures, increasing study retention. For the patients who did not complete the IC, they associated that to their chief complaint and medical reasons related to the nature of their visit to the ED. More research is needed to compare traditional and digital consent processes to better evaluate the effectiveness of digital consent.
Chelsea Edwards, Fuad Abujarad
Open Access
Article
Conference Proceedings
Combination of tall-man lettering and symbol prefixing to improve drug identification by pharmacists
Similar drug names can confuse pharmacists and lead to dispensing errors. A well-accepted solution to the problem is tall-man lettering, a typographic alteration to drug names. However, studies of its effectiveness have yielded mixed results. Furthermore, the potential of orthographic alterations to drug names has not been explored. Therefore, this study aims to examine the usefulness of the combination of tall-man lettering and a simple but new orthographic alteration, symbol prefixing. Twenty-six outpatient pharmacists were recruited to participate in an experiment on drug identification. The results showed that first, the accuracy of drug identification increased with tall-man lettering. Next, the response time and the number of eye fixations for the identification decreased with tall-man lettering and symbol prefixing. Finally, the number of eye fixations decreased with symbol prefixing when there was no tall-man lettering. The findings support that tall-man lettering and symbol prefixing are effective techniques for helping pharmacists identify drugs. Further research could assess the impacts of different types of typographic and orthographic alterations for alleviating the problem of drug name confusion and ultimately minimizing medication errors and ensuring patient safety.
Sheau Farn Max Liang, Kai Xuan Luo, Ren Ming Zhang, Tu Sheng Lee
Open Access
Article
Conference Proceedings
BIOFEE: Biomedical Framework for Enhanced Experimentation
Biomedical Framework for Enhanced Experimentation, based on Firebase Real-Time Database, helps in designing and testing various multimodal solutions for patients suffering from progressive diseases. It allows interacting with objects and robots to test various multimodal solutions, such as touch, voice, gesture... to perform tasks according to the patient's pathology. We tested BIOFEE with Unity3D and Webots virtual worlds to compare different ways to interact for particular tasks (switch lamps, pick and place...).
José Rouillard, Jean-Marc Vannobel, Marie-Helene Bekaert
Open Access
Article
Conference Proceedings
Understanding the Dietary Need of a Local Food Bank’s Population Using Visual Analytics
Food banks are at the forefront of the battle against food insecurity which is a condition where households do not have adequate access to food. Traditionally speaking, food banks focus on distributing food to meet the needs. Recently, more food banks are shifting to supply adequate healthy food based on the populations they serve. However, the question remains whether a local food bank can find racial communities in need with dietary considerations. This study's purpose is to use data collected by a local food bank and create visualizations to aid strategic decision-making for the food bank to recognize racial communities with those who have dietary considerations. Results revealed nine out of sixteen counties in the service area of the local food bank have the highest number of African Americans allergic to shellfish compared to a few counties having the highest number of Whites, American Indians, and Hispanic/Latinos. Additionally, 53.7% of African Americans, 11.2% of Hispanics and Latinos, and 34.3% of Whites face lactose intolerance. Data shows that African Americans have the highest number of dietary considerations in most categories that are in several counties. The significance of this study supports a local food bank in finding dietary considerations within the areas they serve. Finding racial communities that face dietary considerations will aid the local food bank in making better strategic decisions on what types of food they should serve and where. Ultimately, the importance of this study is to combat food insecurity and hunger, so that members of the local food bank community can have dignity in knowing the food that will be given is valuable and not wasted.
Mikaya Hamilton, Steven Jiang, Lauren Davis
Open Access
Article
Conference Proceedings
Home Healthcare System Application Design for COVID-19 Preventive Management
COVID-19 is an infectious disease now known as a "global pandemic" and is reported to be transmitted directly, aerosolized and by contact, and is highly contagious when in contact with patients. Fever, dry cough, and malaise are the most common symptoms of COVID-19. And at this stage, there is still no comprehensive solution for the containment of COVID-19 from a microbiological and curative point of view. Therefore, we need a more independent environment and a smarter medical system for detection and transient isolation before and after social events. And IoT is a popular and proven management technology that can support a variety of human behavior management programs.In this paper, we used interview method, follow-up method, questionnaire method, and literature search method for research verification, process profiling of multiple usage scenarios, and proposed an APP（Application） program design of home medical system for different users' behavioral habits, with functions including risk assessment of planned activity locations and self detection after social activities (via close objects such as masks), etc. The application consists of four main modules: detection, planning, recording, and communication, tracking and warning of epidemic risk sites via wearable devices to reduce the risk of infection for users, and integration of software functions with smart home systems via IoT technology to improve the effectiveness of preventive management for users.
Yukun Xia, Yan Gan, Zijie Ding, Shanyu Ge, Yongkang Wu
Open Access
Article
Conference Proceedings
PBC-ML: Predicting Breast Cancer in Humans using Machine Learning Approach
Cancer is a disease in which cells grow uncontrollably, potentially causing harm tosurrounding healthy tissue and organs. Breast cancer is a specific type of cancer that affectsthe breast and is the second most common cancer among women worldwide. Symptoms ofbreast cancer include a lump or tumour, swelling, nipple discharge, and swollen lymphnodes. Breast cancer is staged, with stage 0 being the earliest stage with minimal symptomsand stage 4 indicating the cancer has spread to other parts of the body. The future burdenof breast cancer is predicted to increase, with over 3 million new cases and 1 million deathsin 2040. Early detection is crucial for successful treatment and recovery, and machinelearning can be used to predict the likelihood of breast cancer based on symptoms. So wepropose in our research to use machine learning algorithms such as CART, SVM, NB, andKNN to analyse and build models for breast cancer detection. These findings offer asummary of relevant machine learning methods for breast cancer detection as it will help tocurb it and we got an accuracy of 98.2% compared to the state of art methods which hasaccuracy of 99%. It proves to be a valuable tool in the early detection of breast cancer andcan improve the accuracy of existing diagnostic methods.
Damilola Oni, Satyam Mishra, Le Trung Thanh, Vu Minh Phuc, Linh Nguyen
Open Access
Article
Conference Proceedings
A pilot study of the effect of bathing time on thermal sensation to get a good night's sleep
In Japan, cold sensitivity is an indefinite complaint that affects many women. However, since it is not a life-threatening serious condition, it is difficult to treat or research the target. However, women who are aware of sensitivity to cold feel the cold most when they go to bed, and there are many people who suffer from the coldness that it is difficult to fall asleep even in a heated environment in winter. In this study, we investigated the effects of bathing, which is likely to raise body temperature, core temperature, skin temperature, and thermal sensation, and prevented coldness. The method of getting a good night's sleep was proposed without a cold sensation.The subject was a 21-year-old healthy woman who has heavy sensitivity to coldness. Experiment I: Room temperature and core temperature (oral temperature) were measured every 60 minutes from 7:00 to 23:00. Experiment II: After taking bath at 20:00, the room temperature, her core temperature, skin temperature of instep/toe, and the thermal sensation of the feet were measured every 20 minutes from 21:00 to 23:00. Experiment III: Two bath times were set from 20:00 or 22:00. The skin temperature of the instep/toe, core temperature, and thermal sensation were measured before and after bath time. Experiment IV: When she felt a cold sensation, core temperature, skin temperature of the instep/toe, and thermal sensation were measured before and after taking the 10 minutes foot bath at 23:00.<Results and Discussion> Result I: From the correlation coefficient between body temperature and room temperature, which had a significant positive correlation, indicating that the higher the room temperature, the higher the body temperature. Room temperature increased significantly from morning to noon and decreased significantly in the evening. However, body temperature increased temporarily from evening to night and decreased significantly in the middle of the night. Result II: The oral temperature was significantly higher than before bathing until 21:20, and then significantly decreased from 22:00. Skin temperature of the instep was significantly higher until 22:00 and one of the toes was significantly higher until 21:40 than before bathing. The thermal sensation was significantly higher until 21:40 compared to before bathing and was evaluated as ``warm''. We calculated the relationship between the skin temperature of the instep/toe and the coldness sensation. The skin temperature (X1: instep, X2: toe) was explained by the equations: Y1 = 0.20X1-5.92 (R2 = 0.518) and Y2 = 0.14X2-3.67 (R2 = 0.667). The skin temperature of the instep/toe (X1/X2) was comfortable thermal sensations, Y1 = 0 (instep) and Y2 = 0 (toe), these skin temperatures were 29.6°C/26.2°C. Result III: Both oral and skin temperatures and their thermal sensations were increased significantly after bathing at 20:00 or 22:00. Although the increasing rate of core temperature at 20:00 bath time was significantly higher than at 22:00, however, there was no difference in the skin temperature of the insteps/toes and the thermal sensation. Result IV: Oral temperature increased after 22:00 bathing (Experiment III), but not after foot bathing. However, both thermal sensations of taking bath or footbath increased. The rate of skin temperature of toes in the footbath was increased significantly higher than taking bath and was maintained until bedtime. Therefore, taking a footbath at 23:00 would make it possible to sleep comfortably.
Tamaki Mitsuno, Sayaka Moriya
Open Access
Article
Conference Proceedings
Methods of computer simulation in the development of technology for the functional assessment of the state of the liver in patients
Most of the diseases associated with carbohydrate and fat metabolism disorders (type 2 diabetes mellitus, obesity, metabolic syndrome) lead to changes in the structure and function of liver cells, and the formed liver dysfunction negatively affects the further progression of the disease. The process of liver damage develops with varying intensity and does not immediately lead to irreversible consequences; therefore, dysfunction should be detected as early as possible, and the data obtained should be used to assess the current state and predict their reversibility.Study purpose. To create a quantitative assessment method that allows to assess the current functional state of the liver and to determine the reversibility of existing functional disorders and the severity of structural changes, to assess the prognosis of the course of the disease and the effectiveness of restorative measures.Instruments and Data Collection Procedure. Examination of patients, in addition to conventional methods, included an assessment of the absorptive-excretory function of the liver and biliary tract patency using a scintillation gamma camera (Siemens Symbia T16) with subsequent processing on the SUPER-SEGAMS computer system (Hungary). Freshly prepared Bromesida, 99mТс was administered intravenously at the rate of 1.1 MBq per kg of the patient's body weight, with a normal content of bilirubin in blood. Series of scintigrams allow to assess the passage of the drug visually through the blood-liver-ducts-intestine system, to characterize the anatomical features and organic changes in the biliary system. Quantitative analysis of the "activity-time" curves obtained from the areas of interest (the right lobe of the liver - 2 zones, the left lobe of the liver, the common bile duct, the intestinal area, the heart area) makes it possible to study the absorptive-excretory function of the liver.Results. By the method of mathematical modeling, a formula was obtained - the index of the functional activity of hepatocytes:IFAH= (-1,1564 + 0,0653 × BMI - 0,0144 × Tmax) × 100,where:IFAH - index of functional activity of hepatocytes (liver cells);BMI - body mass index (kg/m2)Tmax - indicator of the absorption function of the liver (min) - the time to reach the maximum accumulation of the radiopharmaceutical in the liver. It is an indicator of the function of polygonal liver cells (normal = 8-12 min).Functional activity of hepatocytes: from 0 to 9.9 - normal functional activity of hepatocytes; from 10 to 19.9 - the risk of developing functional disorders; from 20 to 29.9 - reversible dysfunction of hepatocytes (steatosis); more than 30 - irreversible (organic) liver dysfunction (steatohepatitis). With negative IFAH values - the influence of extrahepatic factors, such as diseases that accelerate metabolism at the cellular level (thyrotoxicosis), taking drugs in violation of the prescriptions before these studies.The originality and novelty of the technique are confirmed by the patent – “A method for diagnosing fatty hepatosis” (patent RU 2 578 080 C2 dated February 19, 2016).The method was tested in clinical practice and the data obtained confirmed the high diagnostic accuracy (95%) of the proposed method for calculating the index of IFAH.Conclusion: the discussed method allows doctors to evaluate not only the current functional state of the liver, but also to determine the reversibility of existing functional disorders and the severity of structural changes; also could be used to evaluate the prognosis of the course of the disease and the effectiveness of restorative measures. It is characterized by relative ease of implementation. Only one parameter — Tmax is required, after which the study can be completed.
Irina Kurnikova, Shirin Gulova, Guzal Akhmadullina, Natalia Danilina, Ikram Mokhammed
Open Access
Article
Conference Proceedings
Is it possible to use Kinect sensor for lying position rehabilitation exercise? Kinect V2 versus Azure Kinect
The availability of low-cost portable depth sensor camera brings opportunity to be applied in home-based rehabilitation exercise for stroke and other chronic disease patients. Kinect V2 seemed not feasible to easily track motion in a lying position, while the latest Microsoft Azure Kinect has improved the sensor. This paper experimentally explores the feasibility of Azure Kinect and Kinect V2 for lying position rehabilitation exercises and evaluate the tracking performance by changing the camera viewing angles. Two healthy subjects performed upper and lower limb rehabilitation exercise trial on the bed according to supine position and lateral position. The Kinect sensor was tested at 6 viewing angles in human body coronal plane and sagittal plane. Subject motion data and video were recorded and evaluated by two Kinect camera systems. The results showed that the hardware improvement such as resolution enhancement and the neural network motion tracking algorithm of the Azure Kinect depth camera led to higher performance in lying body motion recognition than Kinect v2 for most of the viewing angles. In conclusion, Azure Kinect could improve the lying position body tracking accuracy and it has great potential in the field of rehabilitation with lying position exercises.
Yehua Shi, Xiaoyi Wang, Cathy Lau, Kai-Yu Tong
Open Access
Article
Conference Proceedings
Sitting posture recognition for smart chair
In recent years, the relationship between sitting posture and health has been paid attention to by researchers, since a person spends about 90% of a day sitting except for sleeping time, and the prolonged sitting is one of the important causes of musculoskeletal diseases. Basically, the different sitting postures caused by sitting for a long time will cause different pressure problems on the spine. Thus, this study intends to accurately predict sitting posture to reduce the damage caused by sitting posture using random forest. A smart chair with eight pressure sensors provided by a case company in Taiwan is applied to collect pressure data of various sitting postures in order to develop a prediction model to predict the sitting posture. Since random forest also owns the capability of feature extraction, it is also employed to find unnecessary sensors to reduce the cost of smart chair and further achieve higher prediction accuracy. The results showed that random forest can yield better results for the current problem compared with other methods. In addition, after the feature extraction via random forest, it can be known that there is indeed a sensor that can be eliminated. The accuracy can be enhanced from 90.70% to 91.36%.
Ren-Jieh Kuo, Chih-Wen Shih, Chong-Hao Wang
Open Access
Article
Conference Proceedings
VIS-NLP: Vaccination Inventory System for justified user using Natural Language Processing
In the healthcare industry, especially the Covid-19 pandemic in 2020, produced huge problems with isolate patient and patient heath. Thus, created large amount of data that has been generated every day for the patient heath, in this case is to justify the vaccination of users from social network Twitter. Processing such large volume of the data involves high computation overhead. Good health and well-being; to ensure healthy lives and promote well-being for all at all ages is United Nations 3rd Sustainable Development Goal and we want to align our study with it as well. It is crucial to create an application that is beneficial for humanity health. When we get large datasets from pandemics like Covid-19, for large scale datasets, we presented a solution to verify the user if they are vaccinated or not vaccinated by using Natural Language Processing methods to build an accuracy result, we tried to reduce the computation overhead by storing the data in distributed environment. After processing data, training the data, used pad_sequences, Keras, NLP to build the model. Through multiple epochs we have got an accuracy towards 90 to 91% (which is closer to state-of-the-art methods i.e., 95%). And since our accuracy is higher, we can further utilize it to increase for higher number of epochs. We hope scientists can further develop it and use it in real world applications so that more precious human being lives can be saved. By implementation of its successful results, it also aligns with one of the United Nations Sustainable Development Goals i.e., 3rd: Good Health and Well-Being.
Minh Phuc Vu, Satyam Mishra, Le Trung Thanh, Damilola Oni
Open Access
Article
Conference Proceedings
Detecting Stroke in Human Beings using Machine Learning
In developing and underdeveloped nations, stroke is a leading cause of mortality and disability. Stroke is a life-threatening condition that develops when there is a lack of blood flow to the brain from the carotid arteries and vertebral arteries. Because the brain suffers damage and can quickly expire without oxygen, stroke frequently results in death and can occasionally affect nearby body parts if the patient is not given prompt medical attention. Spasticity, contractures, paralysis, and death are among the effects. According to the World Health Organization, stroke accounts for over 137,000 fatalities per year in the United States alone and over 451,000 deaths per year in Africa. Today, stroke is a medical illness that affects people in practically every region of the world, including industrialized, developing, and undeveloped nations. In general, 1 in 4 adults over 25 will experience a stroke at some point in their lives. This year, 12.2 million people are predicted to experience their first stroke, and 6.5 million of them will pass away as a result. The number of stroke victims worldwide exceeds 110 million. What if this global endemic could be stopped? The world will be safer and life expectancy will rise if accurate stroke prediction technology is developed. We have proposed our research study to develop a solution to predict strokes in people using machine learning. We have employed four models/classifiers to check the accuracy on each of them with same dataset of people and we have achieved great results. The two models gave 98% and 98.29% successful accuracy results which is very close to state-of-the-art methods (99%).
Damilola Oni, Satyam Mishra, Le Trung Thanh, Vu Minh Phuc, Yen Pham
Open Access
Article
Conference Proceedings
Mathematical analysis of daily ECG in assessing the effectiveness of obesity treatment in young patients
Mathematical analysis of the ECG in medicine has been used for a long time, since in 1932 Fleisch and Beckmann first applied the mathematical assessment of the heart rate using the standard deviation of the R-R intervals to assess fluctuations. Mathematical analysis technologies are constantly developing and improving and are the method of choice in the analysis of heart rate variability (HRV). HRV analysis is based on the measurement of time intervals between adjacent ECG R-waves with the construction of a dynamic series - a cardiorhythmogram (CRG). Evaluation of HRV allows to obtain data not only on the functioning of the patient's cardiovascular system, but also on the tension (or exhaustion) of regulatory mechanisms (the state of autonomic regulation), and hence on the preservation of adaptation reserves and rehabilitation capabilities of the body. And this opens opportunities for predicting and monitoring the effectiveness of therapy. At present, the leading direction of research is the development of practical aspects of applying the results of daily HRV analysis.Purpose. To evaluate the possibilities of HRV analysis in monitoring the effectiveness of treatment in young patients with obesity.Materials and methods. Patients with exogenous constitutional obesity underwent 24-hour monitoring of heart rate (Holter monitoring - HM) with software computer analysis of the wave spectrum of the obtained data and selection of frequencies - 0.004–0.08 Hz (very low frequencies - VLF); 0.09-0.16 Hz (low frequencies - LF); 0.17-0.5 Hz (high frequencies - HF); more than 0.5 Hz (Ultra Low Frequency Waves - ULF). Two coefficients were calculated - LF/HF (coefficient of vagosympathetic balance) - the ratio of the power of low frequency waves (LF) to the power of high frequency waves (HF) and the index of centralization (CI) - the ratio of the activity of the central circuit of regulation to the autonomous one (LF+VLF/HF).Results. In total, 14 young patients (from 17 to 26 years old) who were admitted to the medical center with a diagnosis of exogenous constitutional obesity were examined. The survey complex included an analysis of HRV. The initial indicator of autonomic balance was determined by the coefficient LF/HF and the degree of tension of regulatory systems by the index of centralization (CI). In young people, parasympathetic activity prevailed in the wave spectrum - % of high frequency waves (HF) characterizing parasympathetic activity exceeded % of low frequency waves (LF) characterizing sympathetic activity. The follow-up period ranged from 8 months to 1.5 years.In the examined patients, at the beginning of the observation, the predominance of parasympathetics was noted in all, and the value of the coefficient below 0.7 was found in 14 people. (85.7%), which confirmed the predominance of parasympathetics with a significant violation of the autonomic balance (in healthy individuals, the ratio of sympathetic/parasympathetic in terms of LF/HF is from 0.7 to 1.5.). Since the treatment of obesity is a long process, to assess the adequacy of the therapy, after 1 month all patients underwent a second HRV study and the correlation with the effectiveness of the therapy was evaluated. Treatment of obesity was effective in those patients who had their LF/HF increased to a level above 0.7, and the index of centralization increased by more than 50% of the initial level after 1 month. For these patients (11 people - 78.6%), the appropriate treatment tactics were chosen, and the treatment should be continued without additional correction. In patients who did not reach the level of eutonia, the effect of therapy on weight loss was unsatisfactory and relapse of the disease was noted in all cases.Conclusion. Mathematical analysis of HRV in young patients with exogenous constitutional obesity makes it possible to control the state of vegetative balance and, on this basis, to predict the effectiveness of the complex of therapy in a particular patient. If after a month we observe that the predominance of parasympathetics persists (especially during daytime), as well as the high tension of regulatory systems, the complex of therapeutic measures requires immediate correction
Irina Kurnikova, Shirin Gulova, Natalia Danilina, Ikram Mokhammed, Artyom Yurovsky
Open Access
Article
Conference Proceedings
Development of a Home-based Augmented Reality Rehabilitation System for the Elderly with Disabilities
Ageing is accelerating rapidly worldwide. Rehabilitation services are important to maintain the quality of life of the elderly. Clinical therapists share heavy workloads to deliver professional rehabilitation services to the elderly people. Home-based rehabilitation systems are proposed to provide professional training with more flexibility at a convenient time slot and venue. However, most existing home-based rehabilitation systems only provide game for fun or a video-conference platform to have one-to-one training with a therapist. In this study, we designed a home-based augmented reality (AR) rehabilitation system which integrates more than 45 professional rehabilitation training exercises designed by physical therapists and occupational therapists, combined with real-time AR guidance to provide feedback to users’ motions. The new platform does not require the therapist to be online during the time of training and it provides real-time guidance based on users’ 3D body segment motion. A pilot trial was conducted by recruiting 10 elderly subjects with disability to receive a 20 sessions of rehabilitation training using the AR rehabilitation training system. The AR rehabilitation training system can provide an objective and comprehensive performance report for users after each exercise session, which include the score of the corresponding exercise, the curves and the measurement of the significant biomechanics data. The results showed that the system could effectively improve the joint movement and body balance. A questionnaire survey was conducted among all the subjects after they finished the training, the results showed that they were very satisfied with the AR rehabilitation system. This study demonstrates that a home-based AR rehabilitation system has the potential to be applied in clinical application to support the elderly people to improve their physical dysfunction and maintain their quality of life.
Xiaoyi Wang, Yehua Shi, Cathy Lau, Kai-Yu Tong
Open Access
Article
Conference Proceedings
Detecting and monitoring wandering in AD patients with an integrated device based on Humanitude
Alzheimer is a neurodegenerative type of dementia, that has progressive impairment of cognitive and behavioral functions, most commonly presented above 65 years old and it is divided in three stages. Wandering is the most frightening symptom for familiars and caregivers in the mild stage (second stage of the disease) because it can cause from a minor damage to death. Detecting and monitoring wandering is a complex task and has become a strong research line for several research projects. This paper focuses in proposing, developing and testing a support system for monitoring trajectories to identify direction changes alterations and positioning. The proposed system is called Motion acquisition system + Global positioning system(SAM + GPS). The system integrates an accelerometer, magnetometer, gyroscope and a GPS module. To address this challenge, after the development of the device, a pilot test was conducted with 9 young adult healthy subjects instrumented with the SAM + GPS. Each subject needed to route 2 specific trajectories to prove that the integrated device was able to measure different direction changes and map an accurate trajectory for future wandering detection. It was found that the SAM + GPS had an acceptable error of 12.29% measuring the direction changes in the first trajectory and a 27.44% critical error in the second trajectory. In addition, the device was able to map most of the trajectories with high similarities to an ideal pattern traced with the expected horizontal accuracy of 2.5m of the GPS Neo 6m module. It is worth mentioning that the device had a better performance in outdoor environments than in indoor environments, so in future work, more tests are considered with a larger population sample with the integration of an indoor positioning system and Humanitude methodologyprinciples.
Gabriela Cervantes Alarcón, Sergio Navarro Tuch, Ariel Lopez Aguilar, Lili Marlene Camacho Bustamante, Rogelio Bustamante-Bello
Open Access
Article
Conference Proceedings
Humanitude: first step towards the creation of a voice-bot companion for persons with dementia
During the last decade, the life span of the world has been incremented year by year, which comes with a higher probability of suffering from an illness related to aging. An example of this is dementia or Alzheimer’s disease, which causes a progressive decline in various cognitive functions. The costs of living with these types of diseases can destroy a family’s economy if there is no early treatment and detection. This article will aim to develop a protocol to obtain data from interviewing people with cognitive-related questions. This data will form a training corpus to help the development of a neural network that can give a dementia pre-diagnosis. Subsequently, the neural network can be used to program an adaptative companion voice-bot for people with dementia. This will focus on the conversation pillar of Humanitude, a care methodology that can be applied to persons with dementia. The development of this protocol would lead to the creation of one of the few Spanish-based training corpus available for detecting dementia. It is an important step toward developing new tools that can make an early pre-diagnosis or serve as an alternative caregiving solution for people with this condition. Furthermore, this project can lead to the creation of different research whose solutions use Spanish as its main language.
Daniel Isaac Ruiz Cruz, Sergio Navarro Tuch, Ariel Lopez Aguilar, Rogelio Bustamante-Bello, Lili Marlene Camacho Bustamante
Open Access
Article
Conference Proceedings
Dynamic control assignment and automated risk assessment for external control interfaces in the operating room based on ISO IEEE 11073 SDC
Surgical procedures require a variety of medical devices, each bearing an ever-increasing number of settings and functions. Most devices are placed in the unsterile area of the operating room. Therefore, the surgeon and other sterile staff members are not able to interact with the device interfaces. Surgeons often rely on so-called ‘yell-and-click communication’ to have a setting changed, which is error-prone, slow and moreover leads to process interruptions for the involved OR personnel. Suitable control devices, like a foot switch or a sterile user interface, can allow sterile staff members direct access to certain device functions. In a networked operating room, such control devices could exist for any controllable value or operation. Due to spatial limitations in the OR, it is desired to use as few physical control devices as possible. To control a large variety of parameters, these control devices' associated functionality could be re-assigned during a surgical procedure. The manufacturer-independent communication standard ISO IEEE 11073 SDC is tailored for medical device control in the operating room and makes such a re-assignable control interface technically feasible.However, each control association must be assessed with regard to its usability and risk management. For example, a critical control target must never be controlled by an element which is too coarse for the intended task. Therefore, it is a key requirement to develop a software model for control devices and a mechanism to allow or deny a proposed mapping desired by the user based on safety and usability criteria.In the present work, we outline a system to describe and categorize input devices (control elements such as buttons, knobs and foot switches) and controllable counterparts (Targets) typically found in the surgical context. Great attention is given to the means necessary to safely control critical parameters. We assess the current descriptive capabilities of SDC and propose necessary additions to create more comprehensible software models of the control devices. Finally, we present a new convention for medical device modeling which could be used to propose or prohibit unsafe or unintended mappings in a user interface for configuring control devices in the operating room.
Noah Wickel, Okan Yilmaz, Klaus Radermacher, Armin Janß
Open Access
Article
Conference Proceedings