Anup K. Mishra, M. Skubic, Brad W. Willis, T. Guess, Swithin S. Razu, C. Abbott, Aaron D. Gray
Static body sway is a clinically relevant activity parameter, used to assess postural balance, across a wide spectrum of patient populations. We have examined static body sway using two different segmental total body center of mass (TBCM) estimation methods, the Generator of Body Data III (GEBOD) and Winter's method, using Microsoft Kinect skeletal data. Twenty subjects were recruited through an IRB study and asked to perform three trials of single leg stance with their eyes closed, with positioning based on the Balance Error Scoring System. A force plate system was used to estimate the ground truth data for comparison. Results show that both GEBOD and Winter's method performed similar in estimating anterior-posterior (AP) and medio-lateral (ML) body sway. The results also show highly correlated measurements by the two TBCM estimation methods when compared with the force plate system (mean RMSE value of 10.18 mm square in AP and 8.00 mm square in ML direction). Ordinary Least Square (OLS) linear regressions were performed to improve body sway results obtained from the two methods. Improved sway range values obtained from the simple regression method was able to reduce the estimation errors by 50% (~ 10 mm in both AP and ML body sway). The two static body sway estimation methods were found reliable for obtaining body sway. Thus, the inexpensive, portable Kinect V2.0 can be used for clinical measurements.
{"title":"Examining methods to estimate static body sway from the Kinect V2.0 skeletal data: implications for clinical rehabilitation","authors":"Anup K. Mishra, M. Skubic, Brad W. Willis, T. Guess, Swithin S. Razu, C. Abbott, Aaron D. Gray","doi":"10.1145/3154862.3154874","DOIUrl":"https://doi.org/10.1145/3154862.3154874","url":null,"abstract":"Static body sway is a clinically relevant activity parameter, used to assess postural balance, across a wide spectrum of patient populations. We have examined static body sway using two different segmental total body center of mass (TBCM) estimation methods, the Generator of Body Data III (GEBOD) and Winter's method, using Microsoft Kinect skeletal data. Twenty subjects were recruited through an IRB study and asked to perform three trials of single leg stance with their eyes closed, with positioning based on the Balance Error Scoring System. A force plate system was used to estimate the ground truth data for comparison. Results show that both GEBOD and Winter's method performed similar in estimating anterior-posterior (AP) and medio-lateral (ML) body sway. The results also show highly correlated measurements by the two TBCM estimation methods when compared with the force plate system (mean RMSE value of 10.18 mm square in AP and 8.00 mm square in ML direction). Ordinary Least Square (OLS) linear regressions were performed to improve body sway results obtained from the two methods. Improved sway range values obtained from the simple regression method was able to reduce the estimation errors by 50% (~ 10 mm in both AP and ML body sway). The two static body sway estimation methods were found reliable for obtaining body sway. Thus, the inexpensive, portable Kinect V2.0 can be used for clinical measurements.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121468817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
TagTrainer is an end-user adaptable technology for physical rehabilitation. Patients can perform training exercises that require the manipulation of physical objects on three interactive surfaces. Therapists can adapt, extend and create exercises to fit the needs of individual patients. The system addresses a range of important issues in physical rehabilitation, such as treatment personalization, increasing treatment efficiency, and increasing patient motivation.
{"title":"Tagtrainer: end-user adaptable technology for physical rehabilitation","authors":"D. Tetteroo","doi":"10.1145/3154862.3154901","DOIUrl":"https://doi.org/10.1145/3154862.3154901","url":null,"abstract":"TagTrainer is an end-user adaptable technology for physical rehabilitation. Patients can perform training exercises that require the manipulation of physical objects on three interactive surfaces. Therapists can adapt, extend and create exercises to fit the needs of individual patients. The system addresses a range of important issues in physical rehabilitation, such as treatment personalization, increasing treatment efficiency, and increasing patient motivation.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122424502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In health technology projects, user-driven requirements and ideas for functionalities often pose a challenge for research and development teams. Some of these are typical for the context of research projects while others are related to implementation in healthcare settings. In research projects, such challenging issues are sometimes disregarded so that one can focus on the project scope, which, from a user point-of-view, may cause sub-optimal project results. Additionally, disregarding requirements and ideas that are important for end-users in early project stages, hinders the development of in-depth understanding of such issues, which may become a serious barrier for health technology adoption in general. To prevent these risks, we present user requirements that were especially challenging in a research project on disease management for people with congestive heart failure (CHF). By sharing examples like these, we aim to contribute to building intermediate knowledge related to health technology design in general.
{"title":"Mapping the health technology needs of congestive heart failure patients: user needs vs. feasibility","authors":"K. Slegers, M. Mechelen, Jeroen Vanattenhoven","doi":"10.1145/3154862.3154916","DOIUrl":"https://doi.org/10.1145/3154862.3154916","url":null,"abstract":"In health technology projects, user-driven requirements and ideas for functionalities often pose a challenge for research and development teams. Some of these are typical for the context of research projects while others are related to implementation in healthcare settings. In research projects, such challenging issues are sometimes disregarded so that one can focus on the project scope, which, from a user point-of-view, may cause sub-optimal project results. Additionally, disregarding requirements and ideas that are important for end-users in early project stages, hinders the development of in-depth understanding of such issues, which may become a serious barrier for health technology adoption in general. To prevent these risks, we present user requirements that were especially challenging in a research project on disease management for people with congestive heart failure (CHF). By sharing examples like these, we aim to contribute to building intermediate knowledge related to health technology design in general.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"361 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131423764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fereshteh Amini, Khalad Hasan, Andrea Bunt, Pourang Irani
Wearable devices that collect and generate masses of health related data, such as number of steps taken in a day and heart-rate have seen widespread adoption among general consumers. The wearers of such devices need to interpret the data being generated to ensure they meet their physical activity goals. Little is currently known about how users of such devices explore such data and the corresponding visual representations, in-situ, i.e. during the course of their physical activity. Through a series of interview sessions with users of health and fitness data, i.e., quantified-selfers, we gained an understanding of how they benefit from in-situ data exploration. Our findings reveal the wide number of in-situ tasks, data types, and requirements for designing data representations that support immediate reflection on data being collected. We further solicited the aid of professional designers to sketch visual representations for carrying out the necessary in-situ tasks identified by our users. From these exploratory studies, we derive broader implications for the design of data representations supporting in-situ exploration.
{"title":"Data representations for in-situ exploration of health and fitness data","authors":"Fereshteh Amini, Khalad Hasan, Andrea Bunt, Pourang Irani","doi":"10.1145/3154862.3154879","DOIUrl":"https://doi.org/10.1145/3154862.3154879","url":null,"abstract":"Wearable devices that collect and generate masses of health related data, such as number of steps taken in a day and heart-rate have seen widespread adoption among general consumers. The wearers of such devices need to interpret the data being generated to ensure they meet their physical activity goals. Little is currently known about how users of such devices explore such data and the corresponding visual representations, in-situ, i.e. during the course of their physical activity. Through a series of interview sessions with users of health and fitness data, i.e., quantified-selfers, we gained an understanding of how they benefit from in-situ data exploration. Our findings reveal the wide number of in-situ tasks, data types, and requirements for designing data representations that support immediate reflection on data being collected. We further solicited the aid of professional designers to sketch visual representations for carrying out the necessary in-situ tasks identified by our users. From these exploratory studies, we derive broader implications for the design of data representations supporting in-situ exploration.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131466678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. D. de Vries, Cristina Zaga, F. Bayer, C. Drossaert, K. Truong, V. Evers
We present a comparative analysis of motivational messages designed with a theory-driven approach. A previous study [4] involved crowdsourcing to design and evaluate motivational text messages for physical activity, and showed that these peer-designed text messages aligned to behavior change strategies from theory. However, the messages were predominantly rated as motivating in the later stages of behavior change, not in the earlier stages, including those strategies intended for the earlier stages. We speculated that the peers that designed the messages aligned to the strategies did not have sufficient expertise to motivate people in earlier stages. Therefore, we replicated the study with experts. We found that for two of the strategies expert-designed messages were found more motivating in the earliest stage, while for several of the strategies peer-designed messages were rated more motivating for later stages. We conclude that when using these strategies in behavior change technology, expert-designed messages could be more motivating in the earliest stage, while peer-designed messages could be more motivating in the later stages.
{"title":"Experts get me started, peers keep me going: comparing crowd- versus expert-designed motivational text messages for exercise behavior change","authors":"R. D. de Vries, Cristina Zaga, F. Bayer, C. Drossaert, K. Truong, V. Evers","doi":"10.1145/3154862.3154875","DOIUrl":"https://doi.org/10.1145/3154862.3154875","url":null,"abstract":"We present a comparative analysis of motivational messages designed with a theory-driven approach. A previous study [4] involved crowdsourcing to design and evaluate motivational text messages for physical activity, and showed that these peer-designed text messages aligned to behavior change strategies from theory. However, the messages were predominantly rated as motivating in the later stages of behavior change, not in the earlier stages, including those strategies intended for the earlier stages. We speculated that the peers that designed the messages aligned to the strategies did not have sufficient expertise to motivate people in earlier stages. Therefore, we replicated the study with experts. We found that for two of the strategies expert-designed messages were found more motivating in the earliest stage, while for several of the strategies peer-designed messages were rated more motivating for later stages. We conclude that when using these strategies in behavior change technology, expert-designed messages could be more motivating in the earliest stage, while peer-designed messages could be more motivating in the later stages.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126978670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The human body is designed for regular movement. Many humans, however, spend the bulk of their day sitting still instead. On average, for instance an adult spends approximately 10 hours each day sitting-in Asia, Europe as well as US. While a brief period of sitting here and there is natural, long periods of sitting day-in and day-out can seriously impact health and are associated with a significantly higher risk of heart disease, diabetes, obesity, cancer, and depression, as well as muscle and joint problems. Even working out vigorously may not compensate for long sitting sessions. The key is to build frequent movement variety into the day and to change the sitting position from time to time. About every 20--30 minutes the body needs a posture break by moving for a couple of minutes or, at least, by changing the sitting position. Most humans, even knowing about bad behavior and willing to change it, are not able to do so for many different reasons. In order to support behavior changes we have developed a system which is able to track sitting behavior and reflect this by anthropomorphic objects. By doing so we can provide a constant feedback of the sitting posture and give a reminder to sit right, to change the sitting posture from time to time or to stand up. A user study confirms that such a system is accepted and believed to lead to better posture awareness and sitting behavior by most users.
{"title":"Acceptance of dynamic feedback to poor sitting habits by anthropomorphic objects","authors":"Matthias Wölfel","doi":"10.1145/3154862.3154928","DOIUrl":"https://doi.org/10.1145/3154862.3154928","url":null,"abstract":"The human body is designed for regular movement. Many humans, however, spend the bulk of their day sitting still instead. On average, for instance an adult spends approximately 10 hours each day sitting-in Asia, Europe as well as US. While a brief period of sitting here and there is natural, long periods of sitting day-in and day-out can seriously impact health and are associated with a significantly higher risk of heart disease, diabetes, obesity, cancer, and depression, as well as muscle and joint problems. Even working out vigorously may not compensate for long sitting sessions. The key is to build frequent movement variety into the day and to change the sitting position from time to time. About every 20--30 minutes the body needs a posture break by moving for a couple of minutes or, at least, by changing the sitting position. Most humans, even knowing about bad behavior and willing to change it, are not able to do so for many different reasons. In order to support behavior changes we have developed a system which is able to track sitting behavior and reflect this by anthropomorphic objects. By doing so we can provide a constant feedback of the sitting posture and give a reminder to sit right, to change the sitting posture from time to time or to stand up. A user study confirms that such a system is accepted and believed to lead to better posture awareness and sitting behavior by most users.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125226562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Nazemi, M. Mobini, D. Gromala, H. Ko, J. Carlson
Traditionally, healthcare facilities have been designed from a practical standpoint providing efficient spaces for laboratories and increased numbers of rooms to accommodate beds for patients. Such an approach has often led to facilities that "function effectively" but can indirectly create an atmosphere that is stressful, undermining the psychological needs of patients. This research uses an interdisciplinary approach combining immersive environmental sounds constructed as auditory journeys and biofeedback to help manage anxiety and stress in clinical settings. A study was designed exposing 55 patients experiencing anxiety and stress to the auditory journeys. Physiological measurements of skin conductance level (SCL) was used to index parasympathetic activation. Heart rate (HR), and heart rate variability (HF HRV and LF HRV) were used to index sympathetic activation. Although HR, HF HRV, and LF HRV showed no significant effects, the results from SCL were highly significant, suggesting that auditory journeys may assist patients with anxiety management.
{"title":"Sonic therapy for anxiety management in clinical settings","authors":"M. Nazemi, M. Mobini, D. Gromala, H. Ko, J. Carlson","doi":"10.1145/3154862.3154892","DOIUrl":"https://doi.org/10.1145/3154862.3154892","url":null,"abstract":"Traditionally, healthcare facilities have been designed from a practical standpoint providing efficient spaces for laboratories and increased numbers of rooms to accommodate beds for patients. Such an approach has often led to facilities that \"function effectively\" but can indirectly create an atmosphere that is stressful, undermining the psychological needs of patients. This research uses an interdisciplinary approach combining immersive environmental sounds constructed as auditory journeys and biofeedback to help manage anxiety and stress in clinical settings. A study was designed exposing 55 patients experiencing anxiety and stress to the auditory journeys. Physiological measurements of skin conductance level (SCL) was used to index parasympathetic activation. Heart rate (HR), and heart rate variability (HF HRV and LF HRV) were used to index sympathetic activation. Although HR, HF HRV, and LF HRV showed no significant effects, the results from SCL were highly significant, suggesting that auditory journeys may assist patients with anxiety management.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130338606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Hellmers, Sebastian J. F. Fudickar, Eugen Lange, Christian Lins, A. Hein
Gait analysis is often supported by technology. Due to limitations in optical systems, such as limited measurement volumes and the requirement of a laboratory environment, low-cost inertial measurement unit (IMU) based motion capture systems might be better suited for gait analysis since they involve no spatial limitations and are flexibly applicable. In this paper, we investigate if low-cost IMU-based motion capture suits are an adequate alternative for clinical gait analysis in terms of accuracy of the determination of joint flexions and gait parameters. For this reason, we developed a gait analysis system and a gait analysis algorithm, which detects joint positions based on the Joint Coordinate System and determines knee, hip, and ankle flexions, as well as spatiotemporal parameters such as the number of steps, cadence, step duration and step length, and the specific gait phases. We evaluated and validated the IMU-based system in comparison to camera-based measurements (as gold standard) with three different healthy adult subjects. The evaluation indicates that the full-body motion capture system achieves a high degree of precision (0.86) and recall (0.98) in the recognition of gait cycles. The harmonic mean F0.15 of the two factors precision and recall is on average 0.96 and the mentioned temporal gait parameters can be determined with an error below 10 ms. The mean deviation in the determination of joint angles amounts 1.35° ± 2°. Consequently, the article at hand indicates that low-cost IMU-based motion capture suits are an accurate alternative for gait analysis.
{"title":"Validation of a motion capture suit for clinical gait analysis","authors":"S. Hellmers, Sebastian J. F. Fudickar, Eugen Lange, Christian Lins, A. Hein","doi":"10.1145/3154862.3154884","DOIUrl":"https://doi.org/10.1145/3154862.3154884","url":null,"abstract":"Gait analysis is often supported by technology. Due to limitations in optical systems, such as limited measurement volumes and the requirement of a laboratory environment, low-cost inertial measurement unit (IMU) based motion capture systems might be better suited for gait analysis since they involve no spatial limitations and are flexibly applicable. In this paper, we investigate if low-cost IMU-based motion capture suits are an adequate alternative for clinical gait analysis in terms of accuracy of the determination of joint flexions and gait parameters. For this reason, we developed a gait analysis system and a gait analysis algorithm, which detects joint positions based on the Joint Coordinate System and determines knee, hip, and ankle flexions, as well as spatiotemporal parameters such as the number of steps, cadence, step duration and step length, and the specific gait phases. We evaluated and validated the IMU-based system in comparison to camera-based measurements (as gold standard) with three different healthy adult subjects. The evaluation indicates that the full-body motion capture system achieves a high degree of precision (0.86) and recall (0.98) in the recognition of gait cycles. The harmonic mean F0.15 of the two factors precision and recall is on average 0.96 and the mentioned temporal gait parameters can be determined with an error below 10 ms. The mean deviation in the determination of joint angles amounts 1.35° ± 2°. Consequently, the article at hand indicates that low-cost IMU-based motion capture suits are an accurate alternative for gait analysis.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"127 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124307472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Coronary Artery Disease (CAD) kills millions of people every year across the world. In this paper, we present a novel idea of a low cost, non-invasive screening system for early detection of CAD patients by fusion of phonocardiogram (PCG) and photoplethysmogram (PPG) signals. Two sets of time and frequency features are extracted from both the signals. Support Vector Machine (SVM) is used to classify each subject separately based on both the feature sets. Finally, the outcomes of the two classifiers are fused at the decision level, depending upon the maximum absolute distance of the test data-points form their respective SVM hyperplane. We created a corpus of 25 subjects, containing 10 CAD and 15 non CAD subjects using low cost non-medical grade devices. Results show that either of PCG or PPG based classifiers yields sensitivity and specificity scores close to 0.6 and 0.8 respectively in identifying CAD. Whereas, a significant improvement in both sensitivity (0.8) as well as specificity (0.93) can be simultaneously achieved by incorporating the proposed fusion approach.
{"title":"A fusion approach for non-invasive detection of coronary artery disease","authors":"A. Choudhury, Rohan Banerjee, A. Pal, K. Mandana","doi":"10.1145/3154862.3154871","DOIUrl":"https://doi.org/10.1145/3154862.3154871","url":null,"abstract":"Coronary Artery Disease (CAD) kills millions of people every year across the world. In this paper, we present a novel idea of a low cost, non-invasive screening system for early detection of CAD patients by fusion of phonocardiogram (PCG) and photoplethysmogram (PPG) signals. Two sets of time and frequency features are extracted from both the signals. Support Vector Machine (SVM) is used to classify each subject separately based on both the feature sets. Finally, the outcomes of the two classifiers are fused at the decision level, depending upon the maximum absolute distance of the test data-points form their respective SVM hyperplane. We created a corpus of 25 subjects, containing 10 CAD and 15 non CAD subjects using low cost non-medical grade devices. Results show that either of PCG or PPG based classifiers yields sensitivity and specificity scores close to 0.6 and 0.8 respectively in identifying CAD. Whereas, a significant improvement in both sensitivity (0.8) as well as specificity (0.93) can be simultaneously achieved by incorporating the proposed fusion approach.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133963563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Akshay Jain, M. Popescu, J. Keller, Jeffery L. Belden, R. Koopman, Sonal J. Patil, Shannon M. Canfield, L. Steege, Victoria A. Shaffer, P. Wegier, K. Valentine, A. Hathaway
Wearable and non-wearable sensors are pervasive. However, the health implications of the data they provide is not always clear for the user. In this paper we present a Decision Support System (DSS) that assists a user of a Home Blood Pressure (HBP) monitor to decide timely consultation with a doctor. While HBP is more reliable than office readings, it is more variable due to factors such as food, exercise or error in recording measurements. Our DSS is based on fuzzy rules composed of linguistic summaries of the data. The rules are designed from the current US clinical guidelines and are tuned using an evolutionary algorithm. On a dataset of 40 patients monitored over 3 months, we obtained an interrater agreement of 0.97 between the physicians and DSS trained with their data, while the average agreement between these same physicians was 0.95.
{"title":"A decision support system for home BP measurements","authors":"Akshay Jain, M. Popescu, J. Keller, Jeffery L. Belden, R. Koopman, Sonal J. Patil, Shannon M. Canfield, L. Steege, Victoria A. Shaffer, P. Wegier, K. Valentine, A. Hathaway","doi":"10.1145/3154862.3154891","DOIUrl":"https://doi.org/10.1145/3154862.3154891","url":null,"abstract":"Wearable and non-wearable sensors are pervasive. However, the health implications of the data they provide is not always clear for the user. In this paper we present a Decision Support System (DSS) that assists a user of a Home Blood Pressure (HBP) monitor to decide timely consultation with a doctor. While HBP is more reliable than office readings, it is more variable due to factors such as food, exercise or error in recording measurements. Our DSS is based on fuzzy rules composed of linguistic summaries of the data. The rules are designed from the current US clinical guidelines and are tuned using an evolutionary algorithm. On a dataset of 40 patients monitored over 3 months, we obtained an interrater agreement of 0.97 between the physicians and DSS trained with their data, while the average agreement between these same physicians was 0.95.","PeriodicalId":200810,"journal":{"name":"Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123993297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：