Pub Date : 2022-07-01DOI: 10.1109/ICDH55609.2022.00038
M. R. Rahman, J. Bejder, T. Bonne, A. Andersen, J. R. Huertas, R. Aikin, N. Nordsborg, Wolfgang Maass
Sports officials around the world are facing challenges due to the unfair nature of doping practices used by unscrupulous athletes to improve their performance. This prac-tice includes blood transfusion, intake of anabolic steroids or even hormone-based drugs like erythropoietin to increase their strength, endurance, and ultimately their performance. While direct detection and identification of erythropoietin in blood samples of athletes have proven an effective means to uncover doping, not all the cases are easily detectable, and some analyses are too costly to be carried out on every sample. This leads to a need to develop an indirect method for detecting erythropoietin in blood samples based on different blood biomarkers. In this paper, we presented a comparison of different machine learning algorithms combined with statistical analysis approaches to identify the presence of erythropoietin drug in blood samples collected at both sea level and moderate altitude. The results presented indicate that ensemble methods like random forest and X Gboost algorithms may provide an effective tool to aid anti-doping organisations in most effectively distributing scarce resources. Implementation of these methods on the samples from elite athletes may both enhance the deterrence effect of anti-doping as well as increases the likelihood of catching doped athletes.
{"title":"Detection of Erythropoietin in Blood to Uncover Doping in Sports using Machine Learning","authors":"M. R. Rahman, J. Bejder, T. Bonne, A. Andersen, J. R. Huertas, R. Aikin, N. Nordsborg, Wolfgang Maass","doi":"10.1109/ICDH55609.2022.00038","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00038","url":null,"abstract":"Sports officials around the world are facing challenges due to the unfair nature of doping practices used by unscrupulous athletes to improve their performance. This prac-tice includes blood transfusion, intake of anabolic steroids or even hormone-based drugs like erythropoietin to increase their strength, endurance, and ultimately their performance. While direct detection and identification of erythropoietin in blood samples of athletes have proven an effective means to uncover doping, not all the cases are easily detectable, and some analyses are too costly to be carried out on every sample. This leads to a need to develop an indirect method for detecting erythropoietin in blood samples based on different blood biomarkers. In this paper, we presented a comparison of different machine learning algorithms combined with statistical analysis approaches to identify the presence of erythropoietin drug in blood samples collected at both sea level and moderate altitude. The results presented indicate that ensemble methods like random forest and X Gboost algorithms may provide an effective tool to aid anti-doping organisations in most effectively distributing scarce resources. Implementation of these methods on the samples from elite athletes may both enhance the deterrence effect of anti-doping as well as increases the likelihood of catching doped athletes.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"44 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":"116004176","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/ICDH55609.2022.00015
B. Wen, V. Siu, Italo Buleje, Kuan Yu Hsieh, Takashi Itoh, L. Zimmerli, Nigel Hinds, Elif K. Eyigöz, Bing Dang, Stefan von Cavallar, Jeffrey L. Rogers
This paper highlights the design philosophy and architecture of the Health Guardian, a platform developed by the IBM Digital Health team to accelerate discoveries of new digital biomarkers and development of digital health technologies. The Health Guardian allows for rapid translation of artificial intelligence (AI) research into cloud-based microservices that can be tested with data from clinical cohorts to understand disease and enable early prevention. The platform can be connected to mobile applications, wearables, or Internet of things (IoT) devices to collect health-related data into a secure database. When the analytics are created, the researchers can containerize and deploy their code on the cloud using pre-defined templates, and validate the models using the data collected from one or more sensing devices. The Health Guardian platform currently supports time-series, text, audio, and video inputs with 70+ analytic capabilities and is used for non-commercial scientific research. We provide an example of the Alzheimer's disease (AD) assessment microservice which uses AI methods to extract linguistic features from audio recordings to evaluate an individual's mini-mental state, the likelihood of having AD, and to predict the onset of AD before turning the age of 85. Today, IBM research teams across the globe use the Health Guardian internally as a test bed for early-stage research ideas, and externally with collaborators to support and enhance AI model development and clinical study efforts.
{"title":"Health Guardian Platform: A technology stack to accelerate discovery in Digital Health research","authors":"B. Wen, V. Siu, Italo Buleje, Kuan Yu Hsieh, Takashi Itoh, L. Zimmerli, Nigel Hinds, Elif K. Eyigöz, Bing Dang, Stefan von Cavallar, Jeffrey L. Rogers","doi":"10.1109/ICDH55609.2022.00015","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00015","url":null,"abstract":"This paper highlights the design philosophy and architecture of the Health Guardian, a platform developed by the IBM Digital Health team to accelerate discoveries of new digital biomarkers and development of digital health technologies. The Health Guardian allows for rapid translation of artificial intelligence (AI) research into cloud-based microservices that can be tested with data from clinical cohorts to understand disease and enable early prevention. The platform can be connected to mobile applications, wearables, or Internet of things (IoT) devices to collect health-related data into a secure database. When the analytics are created, the researchers can containerize and deploy their code on the cloud using pre-defined templates, and validate the models using the data collected from one or more sensing devices. The Health Guardian platform currently supports time-series, text, audio, and video inputs with 70+ analytic capabilities and is used for non-commercial scientific research. We provide an example of the Alzheimer's disease (AD) assessment microservice which uses AI methods to extract linguistic features from audio recordings to evaluate an individual's mini-mental state, the likelihood of having AD, and to predict the onset of AD before turning the age of 85. Today, IBM research teams across the globe use the Health Guardian internally as a test bed for early-stage research ideas, and externally with collaborators to support and enhance AI model development and clinical study efforts.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"126 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":"123180532","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/icdh55609.2022.00007
{"title":"ICDH 2022 Reviewers","authors":"","doi":"10.1109/icdh55609.2022.00007","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00007","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"52 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":"127468715","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/ICDH55609.2022.00043
Ragib Hasan
In modern healthcare, smart medical devices are used to ensure better and informed patient care. Such devices have the capability to connect to and communicate with the hospital's network or a mobile application over wi-fi or Bluetooth, allowing doctors to remotely configure them, exchange data, or update the firmware. For example, Cardiovascular Implantable Electronic Devices (CIED), more commonly known as Pacemakers, are increasingly becoming smarter, connected to the cloud or healthcare information systems, and capable of being programmed remotely. Healthcare providers can upload new configurations to such devices to change the treatment. Such configurations are often exchanged, reused, and/or modified to match the patient's specific health scenario. Such capabilities, unfortunately, come at a price. Malicious entities can provide a faulty configuration to such devices, leading to the patient's death. Any update to the state or configuration of such devices must be thoroughly vetted before applying them to the device. In case of any adverse events, we must also be able to trace the lineage and propagation of the faulty configuration to determine the cause and liability issues. In a highly distributed environment such as today's hospitals, ensuring the integrity of configurations and security policies is difficult and often requires a complex setup. As configurations propagate, traditional access control and authentication of the healthcare provider applying the configuration is not enough to prevent installation of malicious configurations. In this paper, we argue that a provenance-based approach can provide an effective solution towards hardening the security of such medical devices. In this approach, devices would maintain a verifiable provenance chain that would allow assessing not just the current state, but also the past history of the configuration of the device. Also, any configuration update would be accompanied by its own secure provenance chain, allowing verification of the origin and lineage of the configuration. The ability to protect and verify the provenance of devices and configurations would lead to better patient care, prevent malfunction of the device due to malicious configurations, and allow after-the-fact investigation of device configuration issues. In this paper, we advocate the benefits of such an approach and sketch the requirements, implementation challenges, and deployment strategies for such a provenance-based system.
{"title":"Towards Strengthening the Security of Healthcare Devices using Secure Configuration Provenance","authors":"Ragib Hasan","doi":"10.1109/ICDH55609.2022.00043","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00043","url":null,"abstract":"In modern healthcare, smart medical devices are used to ensure better and informed patient care. Such devices have the capability to connect to and communicate with the hospital's network or a mobile application over wi-fi or Bluetooth, allowing doctors to remotely configure them, exchange data, or update the firmware. For example, Cardiovascular Implantable Electronic Devices (CIED), more commonly known as Pacemakers, are increasingly becoming smarter, connected to the cloud or healthcare information systems, and capable of being programmed remotely. Healthcare providers can upload new configurations to such devices to change the treatment. Such configurations are often exchanged, reused, and/or modified to match the patient's specific health scenario. Such capabilities, unfortunately, come at a price. Malicious entities can provide a faulty configuration to such devices, leading to the patient's death. Any update to the state or configuration of such devices must be thoroughly vetted before applying them to the device. In case of any adverse events, we must also be able to trace the lineage and propagation of the faulty configuration to determine the cause and liability issues. In a highly distributed environment such as today's hospitals, ensuring the integrity of configurations and security policies is difficult and often requires a complex setup. As configurations propagate, traditional access control and authentication of the healthcare provider applying the configuration is not enough to prevent installation of malicious configurations. In this paper, we argue that a provenance-based approach can provide an effective solution towards hardening the security of such medical devices. In this approach, devices would maintain a verifiable provenance chain that would allow assessing not just the current state, but also the past history of the configuration of the device. Also, any configuration update would be accompanied by its own secure provenance chain, allowing verification of the origin and lineage of the configuration. The ability to protect and verify the provenance of devices and configurations would lead to better patient care, prevent malfunction of the device due to malicious configurations, and allow after-the-fact investigation of device configuration issues. In this paper, we advocate the benefits of such an approach and sketch the requirements, implementation challenges, and deployment strategies for such a provenance-based system.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"14 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":"128141586","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/ICDH55609.2022.00042
Nur Imtiazul Haque, Mohammad Rahman, S. Ahamed
Contemporary smart healthcare systems (SHSs) frequently use wireless body sensor devices (WBSDs) for vital sign monitoring and the internet of medical things (IoMT) network for rapid communication with a cloud-based controller. The SHS controllers generate required control decisions based on the patient status to enable real-time patient medication/treatment. Hence, the correct medical delivery primarily depends on accurately identifying the patient's status. Accordingly, SHSs mostly leverage deep neural network (DNN)-based machine learning (ML) models for patient status classification due to their prediction accuracy and complex relation capturing capability. Nevertheless, the open IoMT network is prone to several cyberattacks, including adversarial ML-based attacks, which can exploit DNN models and create a life-threatening event in a safety-critical SHS. Existing solutions usually propose outlier detection or transfer learning-based ML models on top of the patient status classification model to deal with SHS security issues. However, incorporating a separate anomaly detection model increases the model complexity and raises feasibility issues for real-time deployment. This work presents a novel framework, DeepCAD, that considers training a stand-alone DNN model integrated with anomaly detection rules for classification and anomaly detection in SHS. The proposed framework is verified on the Pima Indians Diabetes and Parkinson datasets.
{"title":"DeepCAD: A Stand-alone Deep Neural Network-based Framework for Classification and Anomaly Detection in Smart Healthcare Systems","authors":"Nur Imtiazul Haque, Mohammad Rahman, S. Ahamed","doi":"10.1109/ICDH55609.2022.00042","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00042","url":null,"abstract":"Contemporary smart healthcare systems (SHSs) frequently use wireless body sensor devices (WBSDs) for vital sign monitoring and the internet of medical things (IoMT) network for rapid communication with a cloud-based controller. The SHS controllers generate required control decisions based on the patient status to enable real-time patient medication/treatment. Hence, the correct medical delivery primarily depends on accurately identifying the patient's status. Accordingly, SHSs mostly leverage deep neural network (DNN)-based machine learning (ML) models for patient status classification due to their prediction accuracy and complex relation capturing capability. Nevertheless, the open IoMT network is prone to several cyberattacks, including adversarial ML-based attacks, which can exploit DNN models and create a life-threatening event in a safety-critical SHS. Existing solutions usually propose outlier detection or transfer learning-based ML models on top of the patient status classification model to deal with SHS security issues. However, incorporating a separate anomaly detection model increases the model complexity and raises feasibility issues for real-time deployment. This work presents a novel framework, DeepCAD, that considers training a stand-alone DNN model integrated with anomaly detection rules for classification and anomaly detection in SHS. The proposed framework is verified on the Pima Indians Diabetes and Parkinson datasets.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"14 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":"132883312","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/ICDH55609.2022.00040
Nur Imtiazul Haque, M. Rahman
With the advent of the connected healthcare systems, the contemporary healthcare system is going through a swift transformation to handle the ever-growing healthcare needs. The internet of medical things (IoMT) network and implantable medical devices (IMDs) are progressively being adopted in healthcare facilities for increasing efficiency and reducing treatment latency, thus giving rise to a smart healthcare system (SHS). Moreover, the acquisition of the personalized healthcare concept with SHS is boosting precise medication in real-time. However, the open network communication of IoMT sensor measurements collected from body sensor devices (BSDs) is vulnerable to measurement manipulation attacks since they are primarily encrypted or enciphered with lightweight cryptographic algorithms due to computational constraints. Hence, it is crucial to analyze the robustness of the SHS and real-time sensor measurements' vulnerability analysis to prevent mistreatment. This paper presents PHASE, a novel real-time security analysis framework for personalized rule-based SHS. Our framework can synthesize optimal attack vectors for measurement alteration attacks, each representing minimal required alterations to misinform the SHS controller with wrong patients' health status. The identified attack vectors can assess the vulnerability of the measurements in real-time with variable attacker's capability. We verify the effectiveness of the proposed framework using Pima Indians Diabetes, AIM-94, and Harvard Dataverse datasets.
{"title":"PHASE: Security Analyzer for Next-Generation Smart Personalized Smart Healthcare System","authors":"Nur Imtiazul Haque, M. Rahman","doi":"10.1109/ICDH55609.2022.00040","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00040","url":null,"abstract":"With the advent of the connected healthcare systems, the contemporary healthcare system is going through a swift transformation to handle the ever-growing healthcare needs. The internet of medical things (IoMT) network and implantable medical devices (IMDs) are progressively being adopted in healthcare facilities for increasing efficiency and reducing treatment latency, thus giving rise to a smart healthcare system (SHS). Moreover, the acquisition of the personalized healthcare concept with SHS is boosting precise medication in real-time. However, the open network communication of IoMT sensor measurements collected from body sensor devices (BSDs) is vulnerable to measurement manipulation attacks since they are primarily encrypted or enciphered with lightweight cryptographic algorithms due to computational constraints. Hence, it is crucial to analyze the robustness of the SHS and real-time sensor measurements' vulnerability analysis to prevent mistreatment. This paper presents PHASE, a novel real-time security analysis framework for personalized rule-based SHS. Our framework can synthesize optimal attack vectors for measurement alteration attacks, each representing minimal required alterations to misinform the SHS controller with wrong patients' health status. The identified attack vectors can assess the vulnerability of the measurements in real-time with variable attacker's capability. We verify the effectiveness of the proposed framework using Pima Indians Diabetes, AIM-94, and Harvard Dataverse datasets.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"144 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":"134208194","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/icdh55609.2022.00006
{"title":"Message from the 2022 Steering Committee Chair","authors":"","doi":"10.1109/icdh55609.2022.00006","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00006","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"53 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":"124967369","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/ICDH55609.2022.00044
V. Bellandi, P. Ceravolo, M. Conti, Maryam Ehsanpour
Technological advancements are strongly integrated into our daily lives and an increasing trend prompts the usage of smart healthcare devices for health management. Health providers are beginning to use wearable devices as equipment that can support remote care services. As a result, an accurate, robust, lightweight, and convenient authentication system for smart healthcare devices is urgently required. Considering RFID technology, we present a contactless authentication mechanism that secures a smartwatch at the hardware level. When the authorized person uses the smartwatch, then power is “ON” otherwise “OFF”. Thanks to our method the answer to the question “Am I authorized to use the wearable medical sensor?” and “Am I really the person who is proceeding?” is directly enforced by the system. This study significantly improved the usability and security of the authentication process.
{"title":"Contactless Authentication for Wearable Devices Using RFID","authors":"V. Bellandi, P. Ceravolo, M. Conti, Maryam Ehsanpour","doi":"10.1109/ICDH55609.2022.00044","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00044","url":null,"abstract":"Technological advancements are strongly integrated into our daily lives and an increasing trend prompts the usage of smart healthcare devices for health management. Health providers are beginning to use wearable devices as equipment that can support remote care services. As a result, an accurate, robust, lightweight, and convenient authentication system for smart healthcare devices is urgently required. Considering RFID technology, we present a contactless authentication mechanism that secures a smartwatch at the hardware level. When the authorized person uses the smartwatch, then power is “ON” otherwise “OFF”. Thanks to our method the answer to the question “Am I authorized to use the wearable medical sensor?” and “Am I really the person who is proceeding?” is directly enforced by the system. This study significantly improved the usability and security of the authentication process.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"37 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":"127117480","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/ICDH55609.2022.00011
Laura Wiebelitz, Peter Schmid, T. Maier, Malte Volkwein
Medical artificial intelligence (AI) applications will become increasingly relevant in the future and change the medical technology market. Areas of application are located in the professional as well as in private use. The human-machine interface (HMI) is crucial for a successful use of these AI technologies and for a high user added value. The factors of user experience, usability and joy of use significantly determine the quality of an HMI, but are still insufficiently researched for medical AI applications. This work addresses this gap and provides generally applicable design guidelines to AI-based mobile medical applications. For this purpose, a user-centered requirements analysis was conducted to evaluate possible HMI concepts for a fictitious medical AI application. Based on these findings, specific design guidelines for the HMI of the fictitious application were established. Finally, a universal design catalog for medical AI applications was developed.
{"title":"Designing User-friendly Medical AI Applications - Methodical Development of User-centered Design Guidelines","authors":"Laura Wiebelitz, Peter Schmid, T. Maier, Malte Volkwein","doi":"10.1109/ICDH55609.2022.00011","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00011","url":null,"abstract":"Medical artificial intelligence (AI) applications will become increasingly relevant in the future and change the medical technology market. Areas of application are located in the professional as well as in private use. The human-machine interface (HMI) is crucial for a successful use of these AI technologies and for a high user added value. The factors of user experience, usability and joy of use significantly determine the quality of an HMI, but are still insufficiently researched for medical AI applications. This work addresses this gap and provides generally applicable design guidelines to AI-based mobile medical applications. For this purpose, a user-centered requirements analysis was conducted to evaluate possible HMI concepts for a fictitious medical AI application. Based on these findings, specific design guidelines for the HMI of the fictitious application were established. Finally, a universal design catalog for medical AI applications was developed.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"11 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":"114627933","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/ICDH55609.2022.00029
G. Amprimo, Claudia Ferraris, Giulia Masi, G. Pettiti, L. Priano
Impairment in the execution of simple motor tasks involving hands and fingers could hint at a general worsening of health conditions, particularly in the elderly and in people affected by neurological diseases. The deterioration of hand motor function strongly impacts autonomy in daily activities and, consequently, the perceived quality of life. The early detection of alterations in hand motor skills would allow, for example, to promptly activate treatments and mitigate this discomfort. This preliminary study examines an innovative pipeline based on a single RGB-Depth camera and Google MediaPipe Hands, that is suitable for the remote assessment of hand motor skills through simple tasks commonly used in clinical practice. The study includes several phases. First, the quality of hand tracking is evaluated by comparing reconstructed and real hand 3D trajectories. The proposed solution is then tested on a cohort of healthy volunteers to estimate specific kinematic features for each task. Finally, these features are used to train supervised classifiers and distinguish between “normal” and “altered” performance by simulating typical motor behaviour of real impaired subjects. The preliminary results show the ability of the proposed solution to automatically highlight alterations in hand performance, providing an easy-to-use and non-invasive tool suitable for remote monitoring of hand motor skills.
{"title":"GMH-D: Combining Google MediaPipe and RGB-Depth Cameras for Hand Motor Skills Remote Assessment","authors":"G. Amprimo, Claudia Ferraris, Giulia Masi, G. Pettiti, L. Priano","doi":"10.1109/ICDH55609.2022.00029","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00029","url":null,"abstract":"Impairment in the execution of simple motor tasks involving hands and fingers could hint at a general worsening of health conditions, particularly in the elderly and in people affected by neurological diseases. The deterioration of hand motor function strongly impacts autonomy in daily activities and, consequently, the perceived quality of life. The early detection of alterations in hand motor skills would allow, for example, to promptly activate treatments and mitigate this discomfort. This preliminary study examines an innovative pipeline based on a single RGB-Depth camera and Google MediaPipe Hands, that is suitable for the remote assessment of hand motor skills through simple tasks commonly used in clinical practice. The study includes several phases. First, the quality of hand tracking is evaluated by comparing reconstructed and real hand 3D trajectories. The proposed solution is then tested on a cohort of healthy volunteers to estimate specific kinematic features for each task. Finally, these features are used to train supervised classifiers and distinguish between “normal” and “altered” performance by simulating typical motor behaviour of real impaired subjects. The preliminary results show the ability of the proposed solution to automatically highlight alterations in hand performance, providing an easy-to-use and non-invasive tool suitable for remote monitoring of hand motor skills.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"21 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":"130788333","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：