Pub Date : 2022-07-01DOI: 10.1109/icdh55609.2022.00046
{"title":"Message from the 2022 Steering Committee Chair-Elect","authors":"","doi":"10.1109/icdh55609.2022.00046","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00046","url":null,"abstract":"","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":"122242667","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/ICDH55609.2022.00028
O. Tudorache, J. Kenemer, Janna Pruiett, Maria Valero, M. L. Hedenstrom, H. Shahriar, S. Sneha
As SARS-COV-2 or COVID-19 (COVID) increasingly spread across the world, nurses in the United States increasingly became at risk for contagion, as well as experiencing higher levels of anxiety and concerns related to safety in the workplace. The rise of COVID and the underlying desire to secure protections for healthcare workers created a higher demand for technology and online workspaces where clinicians can provide sustainable care for patients while also reinforcing the need for staff safety. To streamline the patient discharge process, increase patient safety, comprehension, and satisfaction, while simultaneously preventing undesirable readmission rates, a Virtual Nurse application, via remote monitoring and video capabilities, is expected to take over indirect patient tasks such as patient education, discharge instructions, pain monitoring, telemonitoring, communication with the primary nurse and others. By automation, the Virtual Nurse will alleviate repetitive and time-consuming tasks, thus, freeing up nurses to focus on direct patient care tasks and human-to-human quality interaction. This study strives to investigate the feasibility of the implementation of a Virtual Nurse role in the patient discharge process performed at a large healthcare system. This study will start by presenting a brief literature review focused on the technologies currently being employed in healthcare settings around the U.S. Our study aims to present the methodologies utilized in data acquisition and analysis, as well as population sample characteristics.
{"title":"Implementing Virtual Nursing in Health Care: An evaluation of effectiveness and sustainability","authors":"O. Tudorache, J. Kenemer, Janna Pruiett, Maria Valero, M. L. Hedenstrom, H. Shahriar, S. Sneha","doi":"10.1109/ICDH55609.2022.00028","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00028","url":null,"abstract":"As SARS-COV-2 or COVID-19 (COVID) increasingly spread across the world, nurses in the United States increasingly became at risk for contagion, as well as experiencing higher levels of anxiety and concerns related to safety in the workplace. The rise of COVID and the underlying desire to secure protections for healthcare workers created a higher demand for technology and online workspaces where clinicians can provide sustainable care for patients while also reinforcing the need for staff safety. To streamline the patient discharge process, increase patient safety, comprehension, and satisfaction, while simultaneously preventing undesirable readmission rates, a Virtual Nurse application, via remote monitoring and video capabilities, is expected to take over indirect patient tasks such as patient education, discharge instructions, pain monitoring, telemonitoring, communication with the primary nurse and others. By automation, the Virtual Nurse will alleviate repetitive and time-consuming tasks, thus, freeing up nurses to focus on direct patient care tasks and human-to-human quality interaction. This study strives to investigate the feasibility of the implementation of a Virtual Nurse role in the patient discharge process performed at a large healthcare system. This study will start by presenting a brief literature review focused on the technologies currently being employed in healthcare settings around the U.S. Our study aims to present the methodologies utilized in data acquisition and analysis, as well as population sample characteristics.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"3 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":"126505804","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/ICDH55609.2022.00041
Lee Solomon, Reddy Bhavya Gudi, Humera Asfandiyar, S. Sneha, H. Shahriar
The functional efficiency of a healthcare enterprise is dependent on how its multiple disciplines create, share, and manage knowledge. The way in which a healthcare organization manages patient-centered knowledge is well-established. On the contrary, management of process-related knowledge is not well-established. There remains a tremendous amount of room for improvement in the realm of workflow, process, and day-to-day detail documentation, specifically regarding inter-facility variability in a large healthcare enterprise. In this work-in-progress paper, we aim to propose a technical solution for a collaborative approach to knowledge management in a multimodal healthcare enterprise.
{"title":"Knowledge Management in a Healthcare Enterprise: Creation of a Digital Knowledge Repository","authors":"Lee Solomon, Reddy Bhavya Gudi, Humera Asfandiyar, S. Sneha, H. Shahriar","doi":"10.1109/ICDH55609.2022.00041","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00041","url":null,"abstract":"The functional efficiency of a healthcare enterprise is dependent on how its multiple disciplines create, share, and manage knowledge. The way in which a healthcare organization manages patient-centered knowledge is well-established. On the contrary, management of process-related knowledge is not well-established. There remains a tremendous amount of room for improvement in the realm of workflow, process, and day-to-day detail documentation, specifically regarding inter-facility variability in a large healthcare enterprise. In this work-in-progress paper, we aim to propose a technical solution for a collaborative approach to knowledge management in a multimodal healthcare enterprise.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"22 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":"115734990","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/icdh55609.2022.00005
{"title":"ICDH 2022 Organizing Committee","authors":"","doi":"10.1109/icdh55609.2022.00005","DOIUrl":"https://doi.org/10.1109/icdh55609.2022.00005","url":null,"abstract":"","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"35 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":"124888769","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/ICDH55609.2022.00024
M. Subu, Imam Waluyo, Nabeel Al-Yateem, Ika Riana, J. Dias, A. Saifan, S. Rahman, Sheikh Iqbal Ahamed, Jinten Jumiati, F. Ahmed, Amina Al-Marzouqi
Introduction: Smartphone addiction among teenagers is related to self-esteem and self-confidence and is influenced by materialistic factors. Different types of social media consumption affect the level of self-esteem and there is an indirect relationship between smartphone overuse and self-esteem among teenagers. Excessive screen time is also associated with online harassment, sleep deprivation, and poor body mass index status in teenagers. Objective: This study aimed to understand the relationship between smartphone addiction and self-esteem among teenage students aged 12–15 years in Jakarta Province, Indonesia. Methods: We used a cross-sectional design and included teenagers aged 12–15 years from four junior high schools in the East area of Jakarta Province. Study variables included age, gender, parental characteristics, smartphone addiction, and teenagers' self-esteem. Participants completed the Smartphone Addiction Proneness Scale and the Rosenberg Self Esteem Scale. Results: In total, 315 students participated (52.7% girls). We found that 284 (90.2%) students were in the low self-esteem category, 27 (8.6%) were in the normal self-esteem category, and four (1.3%) were in the high self-esteem category. Most students experienced low smartphone addiction and had low self-esteem; however, those that had high smartphone addiction also had high self-esteem. Although unidirectional and weak, this relationship was statistically significant. Conclusion: Given the relationship between smartphone addiction and self-esteem, we recommend that educators and teachers explore various school-based activities that increase students' self-esteem and social interaction. This may also help reduce the time available for using smartphones. Educators could also vary teaching patterns to keep students engaged in the learning process. Further longitudinal and case-control studies are needed to clarify the causes and effects of the association between smartphones and self-esteem among teenagers.
{"title":"Smartphone Addiction and Self-Esteem among Indonesian Teenage Students","authors":"M. Subu, Imam Waluyo, Nabeel Al-Yateem, Ika Riana, J. Dias, A. Saifan, S. Rahman, Sheikh Iqbal Ahamed, Jinten Jumiati, F. Ahmed, Amina Al-Marzouqi","doi":"10.1109/ICDH55609.2022.00024","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00024","url":null,"abstract":"Introduction: Smartphone addiction among teenagers is related to self-esteem and self-confidence and is influenced by materialistic factors. Different types of social media consumption affect the level of self-esteem and there is an indirect relationship between smartphone overuse and self-esteem among teenagers. Excessive screen time is also associated with online harassment, sleep deprivation, and poor body mass index status in teenagers. Objective: This study aimed to understand the relationship between smartphone addiction and self-esteem among teenage students aged 12–15 years in Jakarta Province, Indonesia. Methods: We used a cross-sectional design and included teenagers aged 12–15 years from four junior high schools in the East area of Jakarta Province. Study variables included age, gender, parental characteristics, smartphone addiction, and teenagers' self-esteem. Participants completed the Smartphone Addiction Proneness Scale and the Rosenberg Self Esteem Scale. Results: In total, 315 students participated (52.7% girls). We found that 284 (90.2%) students were in the low self-esteem category, 27 (8.6%) were in the normal self-esteem category, and four (1.3%) were in the high self-esteem category. Most students experienced low smartphone addiction and had low self-esteem; however, those that had high smartphone addiction also had high self-esteem. Although unidirectional and weak, this relationship was statistically significant. Conclusion: Given the relationship between smartphone addiction and self-esteem, we recommend that educators and teachers explore various school-based activities that increase students' self-esteem and social interaction. This may also help reduce the time available for using smartphones. Educators could also vary teaching patterns to keep students engaged in the learning process. Further longitudinal and case-control studies are needed to clarify the causes and effects of the association between smartphones and self-esteem among teenagers.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"39 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":"125489564","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/ICDH55609.2022.00025
Y. Argyris, Nan Zhang, Bidhan Bashyal, Pang-Ning Tan
Anti-vaccine content is rapidly propagated via social media, fostering vaccine hesitancy, while pro-vaccine content has not replicated the opponent's successes. Despite this dis-parity in the dissemination of anti- and pro-vaccine posts, linguistic features that facilitate or inhibit the propagation of vaccine-related content remain less known. Moreover, most prior machine-learning algorithms classified social-media posts into binary categories (e.g., misinformation or not) and have rarely tackled a higher-order classification task based on divergent perspectives about vaccines (e.g., anti-vaccine, pro-vaccine, and neutral). Our objectives are (1) to identify sets of linguistic features that facilitate and inhibit the propagation of vaccine-related content and (2) to compare whether anti-vaccine, pro-vaccine, and neutral tweets contain either set more frequently than the others. To achieve these goals, we collected a large set of social media posts (over 120 million tweets) between Nov. 15 and Dec. 15, 2021, coinciding with the Omicron variant surge. A two-stage framework was developed using a fine-tuned BERT classifier, demonstrating over 99 and 80 percent accuracy for binary and ternary classification. Finally, the Linguistic Inquiry Word Count text analysis tool was used to count linguistic features in each classified tweet. Our regression results show that anti-vaccine tweets are propagated (i.e., retweeted), while pro-vaccine tweets garner passive endorsements (i.e., favorited). Our results also yielded the two sets of linguistic features as facilitators and inhibitors of the propagation of vaccine-related tweets. Finally, our regression results show that anti-vaccine tweets tend to use the facilitators, while pro-vaccine counterparts employ the inhibitors. These findings and algorithms from this study will aid public health officials' efforts to counteract vaccine misinformation, thereby facilitating the delivery of preventive measures during pandemics and epidemics.
反疫苗的内容通过社交媒体迅速传播，助长了对疫苗的犹豫，而支持疫苗的内容并没有复制对手的成功。尽管在反疫苗和支持疫苗的帖子传播方面存在这种差异，但促进或抑制疫苗相关内容传播的语言特征仍然鲜为人知。此外，大多数先前的机器学习算法将社交媒体帖子分为二元类别(例如，错误信息或非错误信息)，并且很少处理基于对疫苗的不同观点(例如，反疫苗，支持疫苗和中立)的高阶分类任务。我们的目标是:(1)识别促进和抑制疫苗相关内容传播的语言特征集;(2)比较反疫苗、支持疫苗和中立推文中哪一组的使用频率高于其他推文。为了实现这些目标，我们在2021年11月15日至12月15日期间收集了大量社交媒体帖子(超过1.2亿条推文)，与Omicron变体激增相吻合。使用微调的BERT分类器开发了一个两阶段框架，对二进制和三元分类显示了超过99%和80%的准确率。最后，使用Linguistic Inquiry Word Count文本分析工具对每条分类推文中的语言特征进行计数。我们的回归结果表明，反疫苗推文被传播(即转发)，而支持疫苗的推文获得被动认可(即被点赞)。我们的结果还得出了两组语言特征作为疫苗相关推文传播的促进者和抑制剂。最后，我们的回归结果表明，反疫苗推文倾向于使用促进因子，而支持疫苗的推文则倾向于使用抑制剂。本研究的这些发现和算法将有助于公共卫生官员努力消除疫苗错误信息，从而促进在大流行和流行病期间提供预防措施。
{"title":"Using Deep Learning to Identify Linguistic Features that Facilitate or Inhibit the Propagation of Anti- and Pro-Vaccine Content on Social Media","authors":"Y. Argyris, Nan Zhang, Bidhan Bashyal, Pang-Ning Tan","doi":"10.1109/ICDH55609.2022.00025","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00025","url":null,"abstract":"Anti-vaccine content is rapidly propagated via social media, fostering vaccine hesitancy, while pro-vaccine content has not replicated the opponent's successes. Despite this dis-parity in the dissemination of anti- and pro-vaccine posts, linguistic features that facilitate or inhibit the propagation of vaccine-related content remain less known. Moreover, most prior machine-learning algorithms classified social-media posts into binary categories (e.g., misinformation or not) and have rarely tackled a higher-order classification task based on divergent perspectives about vaccines (e.g., anti-vaccine, pro-vaccine, and neutral). Our objectives are (1) to identify sets of linguistic features that facilitate and inhibit the propagation of vaccine-related content and (2) to compare whether anti-vaccine, pro-vaccine, and neutral tweets contain either set more frequently than the others. To achieve these goals, we collected a large set of social media posts (over 120 million tweets) between Nov. 15 and Dec. 15, 2021, coinciding with the Omicron variant surge. A two-stage framework was developed using a fine-tuned BERT classifier, demonstrating over 99 and 80 percent accuracy for binary and ternary classification. Finally, the Linguistic Inquiry Word Count text analysis tool was used to count linguistic features in each classified tweet. Our regression results show that anti-vaccine tweets are propagated (i.e., retweeted), while pro-vaccine tweets garner passive endorsements (i.e., favorited). Our results also yielded the two sets of linguistic features as facilitators and inhibitors of the propagation of vaccine-related tweets. Finally, our regression results show that anti-vaccine tweets tend to use the facilitators, while pro-vaccine counterparts employ the inhibitors. These findings and algorithms from this study will aid public health officials' efforts to counteract vaccine misinformation, thereby facilitating the delivery of preventive measures during pandemics and epidemics.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"133 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":"127362816","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/ICDH55609.2022.00022
Maximilian Kapsecker, Simon Osterlehner, Stephan M. Jonas
Cognitive decline is associated with a variety of neurological disorders. Assessment of cognitive domains beyond the clinical environment can support the detection of short- and long-term changes. It is particularly relevant in the early diagnosis of neurocognitive diseases and gaining insights into treatment progress. In this context, the most commonly used feature of mobile phones, the keyboard, provides a rich source to measure specific dimensions of cognition. The objective of this work involves revealing patterns of typing behavior among a population of healthy subjects and evaluating the applied methodology concerning a prospective clinical study on the determination of digital biomarkers for neurocognitive diseases. Therefore, this work introduces a modified version of the iOS default keyboard to measure typing speed and variation in character usage. A study is conducted on eleven healthy subjects to collect typing metrics for one week. The core results of the data analysis yield a positive-skewed distribution for typing speed and homogeneity in typing behavior among the population. Due to the similar statistical properties in typing behavior among healthy people, further studies surrounding subjects with neurocognitive impairment and diverse demographics are encouraged.
{"title":"Analysis of Mobile Typing Characteristics in the Light of Cognition","authors":"Maximilian Kapsecker, Simon Osterlehner, Stephan M. Jonas","doi":"10.1109/ICDH55609.2022.00022","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00022","url":null,"abstract":"Cognitive decline is associated with a variety of neurological disorders. Assessment of cognitive domains beyond the clinical environment can support the detection of short- and long-term changes. It is particularly relevant in the early diagnosis of neurocognitive diseases and gaining insights into treatment progress. In this context, the most commonly used feature of mobile phones, the keyboard, provides a rich source to measure specific dimensions of cognition. The objective of this work involves revealing patterns of typing behavior among a population of healthy subjects and evaluating the applied methodology concerning a prospective clinical study on the determination of digital biomarkers for neurocognitive diseases. Therefore, this work introduces a modified version of the iOS default keyboard to measure typing speed and variation in character usage. A study is conducted on eleven healthy subjects to collect typing metrics for one week. The core results of the data analysis yield a positive-skewed distribution for typing speed and homogeneity in typing behavior among the population. Due to the similar statistical properties in typing behavior among healthy people, further studies surrounding subjects with neurocognitive impairment and diverse demographics are encouraged.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"42 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":"131380826","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/ICDH55609.2022.00008
Yasunori Yamada, Masatomo Kobayashi, Kaoru Shinkawa, M. Nemoto, Miho Ota, K. Nemoto, T. Arai
Early diagnosis of dementia, particularly in the prodromal stage (i.e., mild cognitive impairment, or MCI), has become a research and clinical priority but remains challenging. Automated analysis of the drawing process has been studied as a promising means for screening prodromal and clinical dementia, providing multifaceted information encompassing features, such as drawing speed, pen posture, writing pressure, and pauses. We examined the feasibility of using these features not only for detecting prodromal and clinical dementia but also for predicting the severity of cognitive impairments assessed using Mini-Mental State Examination (MMSE) as well as the severity of neuropathological changes assessed by medial temporal lobe (MTL) atrophy. We collected drawing data with a digitizing tablet and pen from 145 older adults of cognitively normal (CN), MCI, and dementia. The nested cross-validation results indicate that the combination of drawing features could be used to classify CN, MCI, and dementia with an AUC of 0.909 and 75.1% accuracy (CN vs. MCI: 82.4% accuracy; CN vs. dementia: 92.2% accuracy; MCI vs. dementia: 80.3% accuracy) and predict MMSE scores with an $R2$ of 0.491 and severity of MTL atrophy with an $R2$ of 0.293. Our findings suggest that automated analysis of the drawing process can provide information about cognitive impairments and neuropathological changes due to dementia, which can help identify prodromal and clinical dementia as a digital biomarker.
痴呆症的早期诊断，特别是在前驱阶段(即轻度认知障碍，或MCI)，已成为研究和临床重点，但仍然具有挑战性。绘图过程的自动分析已被研究为一种有前途的筛查前驱和临床痴呆的手段，提供多方面的信息，包括特征，如绘图速度，笔的姿势，书写压力和停顿。我们研究了使用这些特征的可行性，不仅用于检测前驱和临床痴呆，还用于预测使用迷你精神状态检查(MMSE)评估的认知障碍的严重程度，以及通过内侧颞叶(MTL)萎缩评估的神经病理改变的严重程度。我们用数字化平板和笔收集了145名认知正常(CN)、轻度认知障碍(MCI)和痴呆老年人的绘画数据。嵌套交叉验证结果表明，结合绘图特征可用于CN、MCI和痴呆的分类，AUC为0.909，准确率为75.1% (CN vs MCI: 82.4%;CN与痴呆:准确率为92.2%;MCI与痴呆:准确率为80.3%)，预测MMSE评分的R2为0.491,MTL萎缩严重程度的R2为0.293。我们的研究结果表明，绘制过程的自动化分析可以提供有关痴呆症引起的认知障碍和神经病理变化的信息，这有助于识别前驱和临床痴呆症作为数字生物标志物。
{"title":"Automated Analysis of Drawing Process for Detecting Prodromal and Clinical Dementia","authors":"Yasunori Yamada, Masatomo Kobayashi, Kaoru Shinkawa, M. Nemoto, Miho Ota, K. Nemoto, T. Arai","doi":"10.1109/ICDH55609.2022.00008","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00008","url":null,"abstract":"Early diagnosis of dementia, particularly in the prodromal stage (i.e., mild cognitive impairment, or MCI), has become a research and clinical priority but remains challenging. Automated analysis of the drawing process has been studied as a promising means for screening prodromal and clinical dementia, providing multifaceted information encompassing features, such as drawing speed, pen posture, writing pressure, and pauses. We examined the feasibility of using these features not only for detecting prodromal and clinical dementia but also for predicting the severity of cognitive impairments assessed using Mini-Mental State Examination (MMSE) as well as the severity of neuropathological changes assessed by medial temporal lobe (MTL) atrophy. We collected drawing data with a digitizing tablet and pen from 145 older adults of cognitively normal (CN), MCI, and dementia. The nested cross-validation results indicate that the combination of drawing features could be used to classify CN, MCI, and dementia with an AUC of 0.909 and 75.1% accuracy (CN vs. MCI: 82.4% accuracy; CN vs. dementia: 92.2% accuracy; MCI vs. dementia: 80.3% accuracy) and predict MMSE scores with an $R2$ of 0.491 and severity of MTL atrophy with an $R2$ of 0.293. Our findings suggest that automated analysis of the drawing process can provide information about cognitive impairments and neuropathological changes due to dementia, which can help identify prodromal and clinical dementia as a digital biomarker.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"241 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":"133447092","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/ICDH55609.2022.00032
M. Qirtas, D. Pesch, E. Zafeiridi, E. Bantry-White
Today's smartphones have sensors that enable monitoring and collecting data on users' daily activities, which may be converted into behavioral indicators of users' health and well-being. Although previous research has used passively sensed data through smartphones to identify users' mental health state, including loneliness, anxiety, depression, and even schizophrenia, the issue of user data privacy in this context has not been well addressed. Here we focus on the feeling of loneliness, which, if persistent, is associated with a number of negative health outcomes. While modern artificial intelligence technology, specifically machine learning, can assist in detecting loneliness or depression, current approaches have applied machine learning to centrally collected user data at a single location with the potential to compromise user data privacy. To address the issue of privacy, we investigated the feasibility of using federated learning on single user data to identify loneliness collected by different smartphone sensors. Federated learning can help protect user privacy by avoiding the transmission of sensitive data from mobile devices to a central server location. To evaluate the federated method's performance in detecting loneliness, we also trained models on all user data using a centralised machine learning approach and compared the results. The results indicate that federated learning has considerable promise for detecting loneliness in a binary classification problem while maintaining user data privacy.
{"title":"Privacy Preserving Loneliness Detection: A Federated Learning Approach","authors":"M. Qirtas, D. Pesch, E. Zafeiridi, E. Bantry-White","doi":"10.1109/ICDH55609.2022.00032","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00032","url":null,"abstract":"Today's smartphones have sensors that enable monitoring and collecting data on users' daily activities, which may be converted into behavioral indicators of users' health and well-being. Although previous research has used passively sensed data through smartphones to identify users' mental health state, including loneliness, anxiety, depression, and even schizophrenia, the issue of user data privacy in this context has not been well addressed. Here we focus on the feeling of loneliness, which, if persistent, is associated with a number of negative health outcomes. While modern artificial intelligence technology, specifically machine learning, can assist in detecting loneliness or depression, current approaches have applied machine learning to centrally collected user data at a single location with the potential to compromise user data privacy. To address the issue of privacy, we investigated the feasibility of using federated learning on single user data to identify loneliness collected by different smartphone sensors. Federated learning can help protect user privacy by avoiding the transmission of sensitive data from mobile devices to a central server location. To evaluate the federated method's performance in detecting loneliness, we also trained models on all user data using a centralised machine learning approach and compared the results. The results indicate that federated learning has considerable promise for detecting loneliness in a binary classification problem while maintaining user data privacy.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"7 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":"130396039","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/ICDH55609.2022.00019
Braden Tabisula, Chinazunwa Uwaoma
Many people experienced an increase in mental health distress due to the isolation requirements arising from the COVID-19 pandemic. The pandemic and the resulting isolation protocols to control the spread of the virus no doubt, sparked researchers' interest in seeking solutions to address the impact on people's mental health in different situations. One of such solutions is the use of technologies to cope with mental health challenges. Though a plethora of technology exists for communication and socialization with several others proposed to deal with mental health breakdown during the pandemic, there is no ‘one-size fits all’ technology that has been identified to address every individual's distress level and coping strategy. This study thus, examines the existing technologies that have been used by people to manage their mental health distress, and proposes a sociotechnical model that can be used to identify current technologies and the effectiveness of such technologies in addressing an individual's mental health distress and symptoms.
{"title":"The Need for an Adaptive Sociotechnical Model for Managing Mental Health in a Pandemic","authors":"Braden Tabisula, Chinazunwa Uwaoma","doi":"10.1109/ICDH55609.2022.00019","DOIUrl":"https://doi.org/10.1109/ICDH55609.2022.00019","url":null,"abstract":"Many people experienced an increase in mental health distress due to the isolation requirements arising from the COVID-19 pandemic. The pandemic and the resulting isolation protocols to control the spread of the virus no doubt, sparked researchers' interest in seeking solutions to address the impact on people's mental health in different situations. One of such solutions is the use of technologies to cope with mental health challenges. Though a plethora of technology exists for communication and socialization with several others proposed to deal with mental health breakdown during the pandemic, there is no ‘one-size fits all’ technology that has been identified to address every individual's distress level and coping strategy. This study thus, examines the existing technologies that have been used by people to manage their mental health distress, and proposes a sociotechnical model that can be used to identify current technologies and the effectiveness of such technologies in addressing an individual's mental health distress and symptoms.","PeriodicalId":120923,"journal":{"name":"2022 IEEE International Conference on Digital Health (ICDH)","volume":"59 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":"123445294","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：