Rehabilitation is a tedious process both for patients and physiotherapists. Many games have been developed, especially for upper limb rehabilitation, to help training more enjoyable for patients which results in an increase in participation and shortening recovery time. Using game, patient's performance in each training course is assessed by the score patient receives after the session. Although these scores might correlate to the range of motion (ROM) of the arm, they cannot be used to directly for evaluation. In this study, a game was created for upper limb rehabilitation which also provides summary of upper limp movement over training session in terms of ROM by using Kinect camera. Formulae to obtain seven upper limb's ROM angles i.e., especially for shoulder flexion, shoulder extension, shoulder abduction, shoulder adduction, shoulder internal rotation, shoulder external rotation and elbow flexion, have been derived. Experiments were conducted to evaluate accuracy of the ROM obtained from the calculation with respect to conventional measurement using goniometer. The results show that, with proper setting (position and orientation) of the Kinect sensor, ROM values obtained from the Kinect sensor match well to the goniometer to within +/-13.5%. Various statistics related to ROM data can be analyzed after each training session. This game would be a useful tool for physiotherapist to monitor and evaluate the progress of patient's recovery.
{"title":"Evaluation of Upper Limb Joint's Range of Motion Data by Kinect Sensor for Rehabilitation Exercise Game","authors":"Peng Nan, Amnad Tongtib, T. Wongratanaphisan","doi":"10.1145/3340037.3340061","DOIUrl":"https://doi.org/10.1145/3340037.3340061","url":null,"abstract":"Rehabilitation is a tedious process both for patients and physiotherapists. Many games have been developed, especially for upper limb rehabilitation, to help training more enjoyable for patients which results in an increase in participation and shortening recovery time. Using game, patient's performance in each training course is assessed by the score patient receives after the session. Although these scores might correlate to the range of motion (ROM) of the arm, they cannot be used to directly for evaluation. In this study, a game was created for upper limb rehabilitation which also provides summary of upper limp movement over training session in terms of ROM by using Kinect camera. Formulae to obtain seven upper limb's ROM angles i.e., especially for shoulder flexion, shoulder extension, shoulder abduction, shoulder adduction, shoulder internal rotation, shoulder external rotation and elbow flexion, have been derived. Experiments were conducted to evaluate accuracy of the ROM obtained from the calculation with respect to conventional measurement using goniometer. The results show that, with proper setting (position and orientation) of the Kinect sensor, ROM values obtained from the Kinect sensor match well to the goniometer to within +/-13.5%. Various statistics related to ROM data can be analyzed after each training session. This game would be a useful tool for physiotherapist to monitor and evaluate the progress of patient's recovery.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126020030","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}
I. Muzychenko, I. Apollonova, David A. Evans, Li Zhang
Have you ever studied or worked abroad? Most people assume it would be stressful --- but would you ever think that it could be detrimental to your health, though? Stress literature relates cross-cultural transactions to the chances of gaining higher levels of chronic stress. The present article aims to study if the psychological stress linked to relocation to a different country can possibly lead to psychobiological effects of chronic stress, namely elevated levels of resting heart rate. A longitudinal pilot study was conducted for 10 expatriate students during the first 2-5 months (with a mean of 3.6 months) of their relocation. Quantitative data was gathered via surveys cross-sectionally, the health data and daily activity journals were collected weekly and provided continuous information about the participants' pulse rate and clues of what its changes can be related to. The results show that the participants have changes in the resting heart rate (RHR) baseline and thus are consistent with those of previous chronic stress research. However, additional further research is required for the consistency of the data and for identifying risk markers and individual stress pathways, with the goal of identifying "at-risk" students and providing treatment options before any serious harm is done to their health.
{"title":"The Psychophysiological Effects of Cross-Cultural Transaction in Foreign Students in Russia: a Pilot Study","authors":"I. Muzychenko, I. Apollonova, David A. Evans, Li Zhang","doi":"10.1145/3340037.3340062","DOIUrl":"https://doi.org/10.1145/3340037.3340062","url":null,"abstract":"Have you ever studied or worked abroad? Most people assume it would be stressful --- but would you ever think that it could be detrimental to your health, though? Stress literature relates cross-cultural transactions to the chances of gaining higher levels of chronic stress. The present article aims to study if the psychological stress linked to relocation to a different country can possibly lead to psychobiological effects of chronic stress, namely elevated levels of resting heart rate. A longitudinal pilot study was conducted for 10 expatriate students during the first 2-5 months (with a mean of 3.6 months) of their relocation. Quantitative data was gathered via surveys cross-sectionally, the health data and daily activity journals were collected weekly and provided continuous information about the participants' pulse rate and clues of what its changes can be related to. The results show that the participants have changes in the resting heart rate (RHR) baseline and thus are consistent with those of previous chronic stress research. However, additional further research is required for the consistency of the data and for identifying risk markers and individual stress pathways, with the goal of identifying \"at-risk\" students and providing treatment options before any serious harm is done to their health.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125742441","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 this article, we described the digital rights management of medical information in an information-centric networking (ICN). ICN is a new Internet 3.0-based network architecture that is a way to transform a host-centric internet infrastructure into an information-centric mobile environment. In this new era, the privacy and copyright protection of personal medical information is an important issue of information security. How to use the ICN architecture to establish cross-domain sharing and personal medical information copyright authorization is the most important contribution of this paper. Specially, we used blockchain technology to establish authorization and used zero knowledge key agreement authentication mechanisms to establish each blockchain and data communication. Finally, we designed a mechanism to create and authorize the information sharing of personal medical media using the ICN architecture. The personal medical records that we designed for ICN environment can be securely accessed anytime, anywhere, and can be securely shared with different healthcare professionals to provide data certified by different medical units in the upcoming high-bandwidth network.
{"title":"Medical Information Digital Right Management on the Information-Centric Networking","authors":"Y. Kuo, J. Shieh","doi":"10.1145/3340037.3340066","DOIUrl":"https://doi.org/10.1145/3340037.3340066","url":null,"abstract":"In this article, we described the digital rights management of medical information in an information-centric networking (ICN). ICN is a new Internet 3.0-based network architecture that is a way to transform a host-centric internet infrastructure into an information-centric mobile environment. In this new era, the privacy and copyright protection of personal medical information is an important issue of information security. How to use the ICN architecture to establish cross-domain sharing and personal medical information copyright authorization is the most important contribution of this paper. Specially, we used blockchain technology to establish authorization and used zero knowledge key agreement authentication mechanisms to establish each blockchain and data communication. Finally, we designed a mechanism to create and authorize the information sharing of personal medical media using the ICN architecture. The personal medical records that we designed for ICN environment can be securely accessed anytime, anywhere, and can be securely shared with different healthcare professionals to provide data certified by different medical units in the upcoming high-bandwidth network.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134123512","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}
Chwei-Shyong Tsai, Qi-Xian Huang, Tsung-Hung Lin, Tian-Fu Lee
A three-party encrypted key exchange (3PEKE) protocol for telecare medicine information systems (TMISs) enables two communicating parties, such as patients, doctors, nurses and health visitors, sharing a long-lived secret only with a trusted third party- Medical Center Server (MCS) to exchange confidential and authenticated Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) with another party over an insecure network. Recently, Lee et al. presented an improved 3PEKE protocol to solve the weaknesses of previous protocols. However, this study states that Lee et al.'s improved 3PEKE protocol still has some security faults such that their protocol cannot execute correctly and fails to resist password guessing attacks. This study also develops an enhanced protocol which is based on Lee et al.'s improved 3PEKE protocol. Additionally, the enhanced protocol protects the user's password by using a one-time key shared with the MCS, eliminates the redundant computations, and rearranges the messages. Compared with related protocols, the enhanced protocol not only has higher security, but also increases efficiency in computation and transmission.
{"title":"Computation-Efficient Three-Party Encrypted Key Exchange for Telecare Medicine Information Systems","authors":"Chwei-Shyong Tsai, Qi-Xian Huang, Tsung-Hung Lin, Tian-Fu Lee","doi":"10.1145/3340037.3340064","DOIUrl":"https://doi.org/10.1145/3340037.3340064","url":null,"abstract":"A three-party encrypted key exchange (3PEKE) protocol for telecare medicine information systems (TMISs) enables two communicating parties, such as patients, doctors, nurses and health visitors, sharing a long-lived secret only with a trusted third party- Medical Center Server (MCS) to exchange confidential and authenticated Electronic Medical Records (EMRs) and Electronic Health Records (EHRs) with another party over an insecure network. Recently, Lee et al. presented an improved 3PEKE protocol to solve the weaknesses of previous protocols. However, this study states that Lee et al.'s improved 3PEKE protocol still has some security faults such that their protocol cannot execute correctly and fails to resist password guessing attacks. This study also develops an enhanced protocol which is based on Lee et al.'s improved 3PEKE protocol. Additionally, the enhanced protocol protects the user's password by using a one-time key shared with the MCS, eliminates the redundant computations, and rearranges the messages. Compared with related protocols, the enhanced protocol not only has higher security, but also increases efficiency in computation and transmission.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124930143","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}
mHealth interventions have been widely adopted across health systems in attempts to improve healthcare delivery particularly in underserved contexts, Kenya included. This has made mHealth more established as opposed to telemedicine. However, the effectiveness of the interventions is questionable as there lacks a clear sustenance and scale-up strategy for successful implementation, despite mHealth having been adopted as one of the pillars for Kenya's national e-health strategy. Apparently, there is a paucity of empirical evidence to understand the complex nature of technology use in mHealth services from design thinking perspective. Also, the role of stakeholders in designing these services has not been well recognized. This paper focuses on mHealth as a healthcare service facilitated by technologies that incorporate mobile technologies. Objectives of the study include: (1) To identify and engage relevant stakeholders, (2) To establish design characteristics of the desired solution, (3) To design & develop context-specific solutions, (4) To evaluate new services in-use situation. A generic model is proposed to guide design and evaluation process for mHealth services, using both lens of service design research and stakeholder theory. Two distinct phases were added to the double diamond process of service design i.e. 'engage context' as pre-implementation evaluation phase at the start and 'evaluate in-use' as post-implementation evaluation phase at the end of the process. The new model was empirically tested by fifteen participants (n=15), of which the outcome met expectations according to validation scorecard. In so doing, our study extends and complement existing body of knowledge.
{"title":"Evaluating mHealth Interventions in an Underserved Context Using Service Design Strategy: A Case of Kenya","authors":"D. Nyatuka, R. D. L. Harpe","doi":"10.1145/3340037.3340060","DOIUrl":"https://doi.org/10.1145/3340037.3340060","url":null,"abstract":"mHealth interventions have been widely adopted across health systems in attempts to improve healthcare delivery particularly in underserved contexts, Kenya included. This has made mHealth more established as opposed to telemedicine. However, the effectiveness of the interventions is questionable as there lacks a clear sustenance and scale-up strategy for successful implementation, despite mHealth having been adopted as one of the pillars for Kenya's national e-health strategy. Apparently, there is a paucity of empirical evidence to understand the complex nature of technology use in mHealth services from design thinking perspective. Also, the role of stakeholders in designing these services has not been well recognized. This paper focuses on mHealth as a healthcare service facilitated by technologies that incorporate mobile technologies. Objectives of the study include: (1) To identify and engage relevant stakeholders, (2) To establish design characteristics of the desired solution, (3) To design & develop context-specific solutions, (4) To evaluate new services in-use situation. A generic model is proposed to guide design and evaluation process for mHealth services, using both lens of service design research and stakeholder theory. Two distinct phases were added to the double diamond process of service design i.e. 'engage context' as pre-implementation evaluation phase at the start and 'evaluate in-use' as post-implementation evaluation phase at the end of the process. The new model was empirically tested by fifteen participants (n=15), of which the outcome met expectations according to validation scorecard. In so doing, our study extends and complement existing body of knowledge.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121881443","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}
Prostate cancer is a common cancer treated with multi-modality. The combinations of modalities are numerous and complex. Clinical practice guidelines and rules have already been proven in many studies. However, the hypotheses of these studies came from physicians' and experts' experiences and observation. Association analysis, as an importance component of data mining, has been proved to be helpful for us to discover rules from big medical databases. We believe association analysis is able to help us to discover new rules between comorbidities and modalities in subjects of prostate cancer, so that employed it to analyze prostate cancer dataset derived from million people file of NHIRD. We successfully found six rules and rule 1,2,3,5,6 could be well explained with known knowledge and literatures, which were "Young prostate cancer patient who were spared from definite treatment tend to be spared from HT.", "TRUS is associated with younger age group, while TURP is associated with older Age.", "RT is associated with HT.", "CT is highly associated with RT.", "Hemiplegia, cerebrovascular disease, moderate to severe renal disease, diabetes with end organ damage is associated with TURP. Patients with TURP are associated with more comorbidity." We also discovered rule 4: "Younger patients who received HT is highly associated with previous RP.", which are still hypothesis and deserve our validation.
{"title":"Association Analysis Among Treatment Modalities and Comorbidity for Prostate Cancer","authors":"Yi-Ting Lin, Mingchih Chen, Yen-Chun Huang","doi":"10.1145/3340037.3340070","DOIUrl":"https://doi.org/10.1145/3340037.3340070","url":null,"abstract":"Prostate cancer is a common cancer treated with multi-modality. The combinations of modalities are numerous and complex. Clinical practice guidelines and rules have already been proven in many studies. However, the hypotheses of these studies came from physicians' and experts' experiences and observation. Association analysis, as an importance component of data mining, has been proved to be helpful for us to discover rules from big medical databases. We believe association analysis is able to help us to discover new rules between comorbidities and modalities in subjects of prostate cancer, so that employed it to analyze prostate cancer dataset derived from million people file of NHIRD. We successfully found six rules and rule 1,2,3,5,6 could be well explained with known knowledge and literatures, which were \"Young prostate cancer patient who were spared from definite treatment tend to be spared from HT.\", \"TRUS is associated with younger age group, while TURP is associated with older Age.\", \"RT is associated with HT.\", \"CT is highly associated with RT.\", \"Hemiplegia, cerebrovascular disease, moderate to severe renal disease, diabetes with end organ damage is associated with TURP. Patients with TURP are associated with more comorbidity.\" We also discovered rule 4: \"Younger patients who received HT is highly associated with previous RP.\", which are still hypothesis and deserve our validation.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121098577","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}
Ting-Ying Chien, Y. Hsieh, Hou-Cheng Lee, Yun-Jui Hsieh
Background: Plantar fasciitis is one of the most common foot pain problems in adults. The current diagnosis mainly relies on the inquiry of medical history and a physical examination of the body. In the objective laboratory examination, the blood test has not yet provided an effective diagnostic reference. In this study, we combine a deep learning algorithm architecture with thermal imaging to develop a plantar fasciitis medical decision system that predicts whether the patient has the condition. Methods: This study collected patient image-related data, including 360-degree thermal video and RGB images of the affected area (foot), and patient clinical data. In data preprocessing, we first adjust the thermal image data, based on the different detection environments. After data processing, we employed the Convolutional Neural Networks (CNN) deep learning architecture to develop a prediction model. Results: In total, 1,000 frames were used as the training dataset in this study---300 cases that had the condition and 700 cases that did not. The results showed that the CNN model can effectively predict plantar fasciitis. The inflammatory response is often accompanied by redness and swelling. This study used thermal imaging to detect the temperature of the affected area, which it combined with a deep learning algorithm to successfully detect the inflammatory condition. In the future, this technique can be used to detect other inflammatory reactions such as wound healing and hemorrhoids.
{"title":"Plantar Fasciitis Detection Based on Deep Learning Architecture","authors":"Ting-Ying Chien, Y. Hsieh, Hou-Cheng Lee, Yun-Jui Hsieh","doi":"10.1145/3340037.3340056","DOIUrl":"https://doi.org/10.1145/3340037.3340056","url":null,"abstract":"Background: Plantar fasciitis is one of the most common foot pain problems in adults. The current diagnosis mainly relies on the inquiry of medical history and a physical examination of the body. In the objective laboratory examination, the blood test has not yet provided an effective diagnostic reference. In this study, we combine a deep learning algorithm architecture with thermal imaging to develop a plantar fasciitis medical decision system that predicts whether the patient has the condition. Methods: This study collected patient image-related data, including 360-degree thermal video and RGB images of the affected area (foot), and patient clinical data. In data preprocessing, we first adjust the thermal image data, based on the different detection environments. After data processing, we employed the Convolutional Neural Networks (CNN) deep learning architecture to develop a prediction model. Results: In total, 1,000 frames were used as the training dataset in this study---300 cases that had the condition and 700 cases that did not. The results showed that the CNN model can effectively predict plantar fasciitis. The inflammatory response is often accompanied by redness and swelling. This study used thermal imaging to detect the temperature of the affected area, which it combined with a deep learning algorithm to successfully detect the inflammatory condition. In the future, this technique can be used to detect other inflammatory reactions such as wound healing and hemorrhoids.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132806810","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}
Chia-Chi Teng, B. Redfearn, Craig Nuttall, Sabrina Jarvis, James Carr, Jarin Jensen, Sandy Kanuch, J. Peterson, David Taylor
Recent research and development projects have demonstrated the use of virtual reality (VR) technology in the healthcare environment, although most applications are still limited to medical simulations and training applications. Whereas VR removes a user from their immediate environment, augmented and mixed reality (AR/MR) adds virtual content to a user's immediate environment. We endeavor to develop an MR application for hospital medical providers which will enable them to directly monitor any patient and their pertinent medical information from any location, at a glance. With this system, the provider could view a live-stream of patients from other locations and their vital signs to provide information for rapid medical decision making. Such application could significantly improve patient safety, allow quicker response times for emergency and critical situations, and reduce medical errors. It could also enhance the effectiveness of the medical team and allow the providers to more closely monitor their patients, improving patient care outcomes and decreasing costs. A prototype of this proposed MR application is developed with a state-of-the-art head mounted display and the result is presented below.
{"title":"Mixed Reality Patients Monitoring Application for Critical Care Nurses","authors":"Chia-Chi Teng, B. Redfearn, Craig Nuttall, Sabrina Jarvis, James Carr, Jarin Jensen, Sandy Kanuch, J. Peterson, David Taylor","doi":"10.1145/3340037.3340050","DOIUrl":"https://doi.org/10.1145/3340037.3340050","url":null,"abstract":"Recent research and development projects have demonstrated the use of virtual reality (VR) technology in the healthcare environment, although most applications are still limited to medical simulations and training applications. Whereas VR removes a user from their immediate environment, augmented and mixed reality (AR/MR) adds virtual content to a user's immediate environment. We endeavor to develop an MR application for hospital medical providers which will enable them to directly monitor any patient and their pertinent medical information from any location, at a glance. With this system, the provider could view a live-stream of patients from other locations and their vital signs to provide information for rapid medical decision making. Such application could significantly improve patient safety, allow quicker response times for emergency and critical situations, and reduce medical errors. It could also enhance the effectiveness of the medical team and allow the providers to more closely monitor their patients, improving patient care outcomes and decreasing costs. A prototype of this proposed MR application is developed with a state-of-the-art head mounted display and the result is presented below.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115716160","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}
Stroke, also known as cerebrovascular events, is mainly caused by the obstruction of blood flow in the brain, which leads to an inability to supply oxygen to the brain. By 2013, stroke had become the second most common cause of death in Taiwan (accounting for about 12% of all deaths). This study used image processing technology and speech recognition, following the Cincinnati Prehospital Stroke Scale, to determine whether or not the user had a stroke. The Cincinnati Prehospital Stroke Scale has three indicators, including facial droop, arm drift, and speech. Patients with 1 of these 3 findings have a 72% probability of having had an ischemic stroke. If all satisfies, the probability of the stroke is more than 85%. In addition, we developed a mobile APP based on this method to detect whether or not the user had a stroke, and hope to reduce stroke hazards.
{"title":"A Stroke Detection System Based on Cincinnati Prehospital Stroke Scale","authors":"Ting-Ying Chien, Chong-Yi Chen, Guo-Lun Jin","doi":"10.1145/3340037.3340052","DOIUrl":"https://doi.org/10.1145/3340037.3340052","url":null,"abstract":"Stroke, also known as cerebrovascular events, is mainly caused by the obstruction of blood flow in the brain, which leads to an inability to supply oxygen to the brain. By 2013, stroke had become the second most common cause of death in Taiwan (accounting for about 12% of all deaths). This study used image processing technology and speech recognition, following the Cincinnati Prehospital Stroke Scale, to determine whether or not the user had a stroke. The Cincinnati Prehospital Stroke Scale has three indicators, including facial droop, arm drift, and speech. Patients with 1 of these 3 findings have a 72% probability of having had an ischemic stroke. If all satisfies, the probability of the stroke is more than 85%. In addition, we developed a mobile APP based on this method to detect whether or not the user had a stroke, and hope to reduce stroke hazards.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130178448","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}
Automated skin lesion boundary detection has become a common issue in Health Care. On the one hand, a broad variety of image processing algorithms already exist and they are power consuming on mobile devices. On the other hand, the use of machine learning algorithms is on the rise and new frameworks have been developed to use these techniques with improved on-device-performance. Since iOS 11.0, Apple is providing a Core Machine Learning Interface to use machine learning models. Moreover, conversion tools allow integration of 3rd party models into iOS applications. In this paper, we present an overview of available frameworks for iOS devices as well as their limitations and evaluate in practice the performance and maturity level of Neural Network frameworks for skin lesion boundary detection using only freely available pictures.
{"title":"Skin Lesion Boundary Detection with Neural Networks on iOS Devices","authors":"Bianca Schnalzer, Baptiste Alcalde","doi":"10.1145/3340037.3340057","DOIUrl":"https://doi.org/10.1145/3340037.3340057","url":null,"abstract":"Automated skin lesion boundary detection has become a common issue in Health Care. On the one hand, a broad variety of image processing algorithms already exist and they are power consuming on mobile devices. On the other hand, the use of machine learning algorithms is on the rise and new frameworks have been developed to use these techniques with improved on-device-performance. Since iOS 11.0, Apple is providing a Core Machine Learning Interface to use machine learning models. Moreover, conversion tools allow integration of 3rd party models into iOS applications. In this paper, we present an overview of available frameworks for iOS devices as well as their limitations and evaluate in practice the performance and maturity level of Neural Network frameworks for skin lesion boundary detection using only freely available pictures.","PeriodicalId":340774,"journal":{"name":"Proceedings of the 3rd International Conference on Medical and Health Informatics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126678950","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：