Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00031
Chi-yu Chen, Po-Chien Hsu, Tao Chang, Huan Ho, Min-Chun Hu, Chi-Chun Lee, Hui-Ju Chen, M. Ko, Chia-Fan Lee, Pei-Yi Wang
Common screening tasks for developmental-behavioral disabilities require human judgement to decide pass/fail on checklists, which possibly causes subjective biases. On the other hand, professional requirements for an assessment build a barrier for the accessibility to such screening tests. Therefore, we applied a combination of computer vision techniques to automatically perform cognition assessment on toddlers. To tackle insufficient data, multi-person scene, and unexpected movements of toddlers, YOLOv5, Mediapipe, LOFTR, and depth prediction model trained from Mannequin Challenge dataset are utilized to accurately focus our detection model on assigned areas to generate better results. We believe that similar concepts could be further extended to other sub-fields in childhood developmental-behavioral screening and improve clinical practice.
{"title":"Computer Vision Based Cognition Assessment for Developmental-Behavioral Screening","authors":"Chi-yu Chen, Po-Chien Hsu, Tao Chang, Huan Ho, Min-Chun Hu, Chi-Chun Lee, Hui-Ju Chen, M. Ko, Chia-Fan Lee, Pei-Yi Wang","doi":"10.1109/ICDH55609.2022.00031","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00031","url":null,"abstract":"Common screening tasks for developmental-behavioral disabilities require human judgement to decide pass/fail on checklists, which possibly causes subjective biases. On the other hand, professional requirements for an assessment build a barrier for the accessibility to such screening tests. Therefore, we applied a combination of computer vision techniques to automatically perform cognition assessment on toddlers. To tackle insufficient data, multi-person scene, and unexpected movements of toddlers, YOLOv5, Mediapipe, LOFTR, and depth prediction model trained from Mannequin Challenge dataset are utilized to accurately focus our detection model on assigned areas to generate better results. We believe that similar concepts could be further extended to other sub-fields in childhood developmental-behavioral screening and improve clinical practice.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124420604","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00009
J. Epperlein, N. Hardy, Pól Mac Aonghusa, R. Cahill
Intraoperative assessment of tissue can be guided through fluorescence imaging which involves systemic dosing with a fluorophore and subsequent examination of the tissue region of interest with a near-infrared camera. This typically involves administering indocyanine green (ICG) hours or even days before surgery and intraoperative visualization at the time predicted for steady-state signal-to-background status. Here, we describe our efforts to capture and utilize the information contained in the first few minutes after ICG administration from the perspective of both signal processing and surgical practice. We prove a method for characterization of cancerous versus benign rectal lesions now undergoing further development and validation via multicenter clinical phase studies.
{"title":"Extracting, Visualizing, and Learning from Dynamic Data: Perfusion in Surgical Video for Tissue Characterization","authors":"J. Epperlein, N. Hardy, Pól Mac Aonghusa, R. Cahill","doi":"10.1109/ICDH55609.2022.00009","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00009","url":null,"abstract":"Intraoperative assessment of tissue can be guided through fluorescence imaging which involves systemic dosing with a fluorophore and subsequent examination of the tissue region of interest with a near-infrared camera. This typically involves administering indocyanine green (ICG) hours or even days before surgery and intraoperative visualization at the time predicted for steady-state signal-to-background status. Here, we describe our efforts to capture and utilize the information contained in the first few minutes after ICG administration from the perspective of both signal processing and surgical practice. We prove a method for characterization of cancerous versus benign rectal lesions now undergoing further development and validation via multicenter clinical phase studies.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122771891","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00013
Victoire Metuge, Maria Valero, Liang Zhao, Valentina Nino, David Claudio
Emergency department (ED) visits have risen to more than 60% since 1997, with more than 90% of U.S EDs being over-stretched due to overcrowding which has only been compounded by the recent pandemic. Consequences for ED overcrowding range from less severe effects such as patient inconvenience to more severe outcomes such as patient fatality. Research shows poor crowd management at the ED does not only affect patients but takes a toll on ED staff as well. To attempt to address this issue, our study researches how patient vitals collected and transmitted in real time to ED staff can help manage patients in the ED using a triage system that orders vitals in an urgent priority listing. We gathered data from participants using non-invasive wearable devices (CareTaker4 & Oximeter) to collect vital signs information such as heart rate, respiratory rate, blood pressure, and oxygen levels. We aim to use the data to feed a mathematical model that will create a priority algorithm that can sort patients in an ED according to the urgency of their vital signs and transmit the data in real time to health personnel. This way, the patients can be moved automatically in the list as they deteriorate while waiting. We were able to plot the data to show which patients' health are deteriorating quickly and that would require immediate attention. This will be instrumental by helping ED staff attend to pressing cases faster and help control crowds according to medical urgency instead of a first come first serve basis which is not always effective.
{"title":"Preliminary Data Collection for Collaborative Emergency Department Crowd Management using Wearable Devices","authors":"Victoire Metuge, Maria Valero, Liang Zhao, Valentina Nino, David Claudio","doi":"10.1109/ICDH55609.2022.00013","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00013","url":null,"abstract":"Emergency department (ED) visits have risen to more than 60% since 1997, with more than 90% of U.S EDs being over-stretched due to overcrowding which has only been compounded by the recent pandemic. Consequences for ED overcrowding range from less severe effects such as patient inconvenience to more severe outcomes such as patient fatality. Research shows poor crowd management at the ED does not only affect patients but takes a toll on ED staff as well. To attempt to address this issue, our study researches how patient vitals collected and transmitted in real time to ED staff can help manage patients in the ED using a triage system that orders vitals in an urgent priority listing. We gathered data from participants using non-invasive wearable devices (CareTaker4 & Oximeter) to collect vital signs information such as heart rate, respiratory rate, blood pressure, and oxygen levels. We aim to use the data to feed a mathematical model that will create a priority algorithm that can sort patients in an ED according to the urgency of their vital signs and transmit the data in real time to health personnel. This way, the patients can be moved automatically in the list as they deteriorate while waiting. We were able to plot the data to show which patients' health are deteriorating quickly and that would require immediate attention. This will be instrumental by helping ED staff attend to pressing cases faster and help control crowds according to medical urgency instead of a first come first serve basis which is not always effective.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"430 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133983639","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00034
Patrick Fuhlert, Anne Ernst, Esther Dietrich, Fabian Westhaeusser, K. Kloiber, Stefan Bonn
Deep neural networks for survival prediction outperform classical approaches in discrimination, which is the ordering of patients according to their time-of-event. Conversely, classical approaches like the Cox Proportional Hazards model display much better calibration, the correct temporal prediction of events of the underlying distribution. Especially in the medical domain, where it is critical to predict the survival of a single patient, both discrimination and calibration are important performance metrics. Here we present Discrete Calibrated Survival (DCS), a novel deep neural network for discriminated and calibrated survival prediction that outperforms competing survival models in discrimination on three medical datasets, while achieving best calibration among all discrete time models. The enhanced performance of DCS can be attributed to two novel features, the variable temporal output node spacing and the novel loss term that optimizes the use of uncensored and censored patient data. We believe that DCS is an important step towards clinical application of deep-learning-based survival prediction with state-of-the-art discrimination and good calibration.
{"title":"Deep Learning-Based Discrete Calibrated Survival Prediction","authors":"Patrick Fuhlert, Anne Ernst, Esther Dietrich, Fabian Westhaeusser, K. Kloiber, Stefan Bonn","doi":"10.1109/ICDH55609.2022.00034","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00034","url":null,"abstract":"Deep neural networks for survival prediction outperform classical approaches in discrimination, which is the ordering of patients according to their time-of-event. Conversely, classical approaches like the Cox Proportional Hazards model display much better calibration, the correct temporal prediction of events of the underlying distribution. Especially in the medical domain, where it is critical to predict the survival of a single patient, both discrimination and calibration are important performance metrics. Here we present Discrete Calibrated Survival (DCS), a novel deep neural network for discriminated and calibrated survival prediction that outperforms competing survival models in discrimination on three medical datasets, while achieving best calibration among all discrete time models. The enhanced performance of DCS can be attributed to two novel features, the variable temporal output node spacing and the novel loss term that optimizes the use of uncensored and censored patient data. We believe that DCS is an important step towards clinical application of deep-learning-based survival prediction with state-of-the-art discrimination and good calibration.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131412469","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00027
Tarek El Salti, E. Sykes, Javier Nievas, Chen Tong
Over the last two years, COVID-19 pneumonia has killed more than six million people worldwide. To self-triage pneumonia patients, many mobile Health (mHealth) solutions have been developed. Some of these solutions only provide guidelines and trace outbreaks. Others collect inaccurate vitals and/or are considered costly. To address these challenges, a cost-effective and accurate mHealth system was designed in this paper. The system consists of several biosensors (e.g., oxygen saturation) as they are considered significant for the disease assessment. In addition, a new mobile application was developed to collect biometric vitals and transmit them to a HIPPA compliant server. Our real-world experiments demonstrated that the new system was strongly correlated with the gold standard systems in terms of pulse rate and temperature (e.g., 90%). Moreover, the difference in the rate of change between the two systems for the measurements were mostly insignificant (e.g., $p-text{value} approx 0.77$). Lastly, the prototype cost is approximately $20 USD.
{"title":"A New Low-Cost and Accurate Diagnostic mHealth System for Patients with COVID-19 Pneumonia","authors":"Tarek El Salti, E. Sykes, Javier Nievas, Chen Tong","doi":"10.1109/ICDH55609.2022.00027","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00027","url":null,"abstract":"Over the last two years, COVID-19 pneumonia has killed more than six million people worldwide. To self-triage pneumonia patients, many mobile Health (mHealth) solutions have been developed. Some of these solutions only provide guidelines and trace outbreaks. Others collect inaccurate vitals and/or are considered costly. To address these challenges, a cost-effective and accurate mHealth system was designed in this paper. The system consists of several biosensors (e.g., oxygen saturation) as they are considered significant for the disease assessment. In addition, a new mobile application was developed to collect biometric vitals and transmit them to a HIPPA compliant server. Our real-world experiments demonstrated that the new system was strongly correlated with the gold standard systems in terms of pulse rate and temperature (e.g., 90%). Moreover, the difference in the rate of change between the two systems for the measurements were mostly insignificant (e.g., $p-text{value} approx 0.77$). Lastly, the prototype cost is approximately $20 USD.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115848315","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00020
Alexander Turner, David Scott, S. Hayes
In this work we investigate the effectiveness of a wireless in-shoe pressure sensing system used in combination with a type of machine learning referred to as long term short term memory networks (LSTMs) to classify multiple interacting gait perturbations. Artificially induced gait perturbations consisted of restricted knee extension and altered under foot centre of pressure (COP). The primary aim was to assess the capacity to diagnose gait abnormalities without the need to attend a gait laboratory or visit a clinical healthcare professional, through the use of technology. Ultimately, such a system could be used to autonomously generate therapeutic guidance and provide healthcare professionals with accurate up to date information about a patients gait. The results show that LSTMs are capable of classifying complex interacting gait perturbations using in-shoe pressure data. When testing, 11 of 12 perturbation conditions were correctly classified overall and 58.8% of all data instances were correctly classified (8.3% is random classification). This work illustrates that an automated low cost, non-invasive gait diagnosis system with minimal sensors can be used to identify interacting gait abnormalities in individuals and has further potential to be used in a healthcare setting.
{"title":"The Classification of Multiple Interacting Gait Abnormalities Using Insole Sensors and Machine Learning","authors":"Alexander Turner, David Scott, S. Hayes","doi":"10.1109/ICDH55609.2022.00020","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00020","url":null,"abstract":"In this work we investigate the effectiveness of a wireless in-shoe pressure sensing system used in combination with a type of machine learning referred to as long term short term memory networks (LSTMs) to classify multiple interacting gait perturbations. Artificially induced gait perturbations consisted of restricted knee extension and altered under foot centre of pressure (COP). The primary aim was to assess the capacity to diagnose gait abnormalities without the need to attend a gait laboratory or visit a clinical healthcare professional, through the use of technology. Ultimately, such a system could be used to autonomously generate therapeutic guidance and provide healthcare professionals with accurate up to date information about a patients gait. The results show that LSTMs are capable of classifying complex interacting gait perturbations using in-shoe pressure data. When testing, 11 of 12 perturbation conditions were correctly classified overall and 58.8% of all data instances were correctly classified (8.3% is random classification). This work illustrates that an automated low cost, non-invasive gait diagnosis system with minimal sensors can be used to identify interacting gait abnormalities in individuals and has further potential to be used in a healthcare setting.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"2006 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125840526","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}
Pub Date : 2022-07-01DOI: 10.1109/icdh55609.2022.00052
{"title":"Digital Health Security & Privacy Symposium","authors":"","doi":"10.1109/icdh55609.2022.00052","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00052","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126236867","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}
Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00017
Oritsetimevin Arueyinzho, Korede Sanyaolu
Health promotion involves intentional activities geared towards enabling and empowering persons to have better control over their health. The management of health has evolved from being drug centered to patient centered, andwithin the auspices of patient-centeredness it is becoming the focus of a lot of health promotion programs. Self-care encourages disease management or lifestyle modifications outside formal clinical settings, in different contexts of the everyday life of an average person. Recently, innovative digitalhealth tools have been used to encourage action on the determinants of health, self-care, and overall health promotion. The fitness industry is not left behind in this trend of self-care as key players are investing in the creation of digital health tools for this purpose. This review aims to summarize digital health technologies being used by fitness enthusiasts in Africa, and health promotion strategies (if there are any) for encouraging the use of these tools by fitness enthusiasts
{"title":"Digital Health Promotion For Fitness Enthusiasts In Africa","authors":"Oritsetimevin Arueyinzho, Korede Sanyaolu","doi":"10.1109/ICDH55609.2022.00017","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00017","url":null,"abstract":"Health promotion involves intentional activities geared towards enabling and empowering persons to have better control over their health. The management of health has evolved from being drug centered to patient centered, andwithin the auspices of patient-centeredness it is becoming the focus of a lot of health promotion programs. Self-care encourages disease management or lifestyle modifications outside formal clinical settings, in different contexts of the everyday life of an average person. Recently, innovative digitalhealth tools have been used to encourage action on the determinants of health, self-care, and overall health promotion. The fitness industry is not left behind in this trend of self-care as key players are investing in the creation of digital health tools for this purpose. This review aims to summarize digital health technologies being used by fitness enthusiasts in Africa, and health promotion strategies (if there are any) for encouraging the use of these tools by fitness enthusiasts","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114786650","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}
Pub Date : 2022-07-01DOI: 10.1109/icdh55609.2022.00051
{"title":"Message from the Organizing Committee 2022 IEEE International Conference on Digital Health","authors":"","doi":"10.1109/icdh55609.2022.00051","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00051","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124503471","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}
Pub Date : 2022-07-01DOI: 10.1109/icdh55609.2022.00049
{"title":"Welcome Message from the General Co-Chair of the IEEE Services 2022","authors":"","doi":"10.1109/icdh55609.2022.00049","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00049","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122916998","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：