Huitong Ding, Adrian Lister, Cody Karjadi, Rhoda Au, Honghuang Lin, Brian Bischoff, Phillip H Hwang
Background: With the aging global population and the rising burden of Alzheimer disease and related dementias (ADRDs), there is a growing focus on identifying mild cognitive impairment (MCI) to enable timely interventions that could potentially slow down the onset of clinical dementia. The production of speech by an individual is a cognitively complex task that engages various cognitive domains. The ease of audio data collection highlights the potential cost-effectiveness and noninvasive nature of using human speech as a tool for cognitive assessment.
Objective: This study aimed to construct a machine learning pipeline that incorporates speaker diarization, feature extraction, feature selection, and classification to identify a set of acoustic features derived from voice recordings that exhibit strong MCI detection capability.
Methods: The study included 100 MCI cases and 100 cognitively normal controls matched for age, sex, and education from the Framingham Heart Study. Participants' spoken responses on neuropsychological tests were recorded, and the recorded audio was processed to identify segments of each participant's voice from recordings that included voices of both testers and participants. A comprehensive set of 6385 acoustic features was then extracted from these voice segments using OpenSMILE and Praat software. Subsequently, a random forest model was constructed to classify cognitive status using the features that exhibited significant differences between the MCI and cognitively normal groups. The MCI detection performance of various audio lengths was further examined.
Results: An optimal subset of 29 features was identified that resulted in an area under the receiver operating characteristic curve of 0.87, with a 95% CI of 0.81-0.94. The most important acoustic feature for MCI classification was the number of filled pauses (importance score=0.09, P=3.10E-08). There was no substantial difference in the performance of the model trained on the acoustic features derived from different lengths of voice recordings.
Conclusions: This study showcases the potential of monitoring changes to nonsemantic and acoustic features of speech as a way of early ADRD detection and motivates future opportunities for using human speech as a measure of brain health.
{"title":"Detection of Mild Cognitive Impairment From Non-Semantic, Acoustic Voice Features: The Framingham Heart Study.","authors":"Huitong Ding, Adrian Lister, Cody Karjadi, Rhoda Au, Honghuang Lin, Brian Bischoff, Phillip H Hwang","doi":"10.2196/55126","DOIUrl":"10.2196/55126","url":null,"abstract":"<p><strong>Background: </strong>With the aging global population and the rising burden of Alzheimer disease and related dementias (ADRDs), there is a growing focus on identifying mild cognitive impairment (MCI) to enable timely interventions that could potentially slow down the onset of clinical dementia. The production of speech by an individual is a cognitively complex task that engages various cognitive domains. The ease of audio data collection highlights the potential cost-effectiveness and noninvasive nature of using human speech as a tool for cognitive assessment.</p><p><strong>Objective: </strong>This study aimed to construct a machine learning pipeline that incorporates speaker diarization, feature extraction, feature selection, and classification to identify a set of acoustic features derived from voice recordings that exhibit strong MCI detection capability.</p><p><strong>Methods: </strong>The study included 100 MCI cases and 100 cognitively normal controls matched for age, sex, and education from the Framingham Heart Study. Participants' spoken responses on neuropsychological tests were recorded, and the recorded audio was processed to identify segments of each participant's voice from recordings that included voices of both testers and participants. A comprehensive set of 6385 acoustic features was then extracted from these voice segments using OpenSMILE and Praat software. Subsequently, a random forest model was constructed to classify cognitive status using the features that exhibited significant differences between the MCI and cognitively normal groups. The MCI detection performance of various audio lengths was further examined.</p><p><strong>Results: </strong>An optimal subset of 29 features was identified that resulted in an area under the receiver operating characteristic curve of 0.87, with a 95% CI of 0.81-0.94. The most important acoustic feature for MCI classification was the number of filled pauses (importance score=0.09, P=3.10E-08). There was no substantial difference in the performance of the model trained on the acoustic features derived from different lengths of voice recordings.</p><p><strong>Conclusions: </strong>This study showcases the potential of monitoring changes to nonsemantic and acoustic features of speech as a way of early ADRD detection and motivates future opportunities for using human speech as a measure of brain health.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e55126"},"PeriodicalIF":5.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11377909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142037272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: eHealth literacy is an essential skill for pursuing electronic health information, particularly for older people whose health needs increase with age. South Korea is now at the intersection of a rapidly digitalizing society and an increasingly aged population. eHealth literacy enables older people to maximize the effective use of emerging digital technology for their health and quality of life. Understanding the eHealth literacy of Korean older adults is critical to eliminating the gray digital divide and inequity in health information access.
Objective: This study aims to investigate factors influencing eHealth literacy in older Korean adults and its impact on health outcomes and eHealth use.
Methods: This was a cross-sectional survey. Community-dwelling older adults 65 years and older in 2 urban cities in South Korea were included. eHealth literacy was measured by the eHealth Literacy Scale. Ordinal logistic regression was used to analyze factors associated with eHealth literacy and multivariate ANOVA for the impact of eHealth literacy on health outcomes and eHealth use.
Results: In total, 434 participants were analyzed. A total of 22.3% (97/434) of participants had high eHealth literacy skills. Increasing age, higher monthly income, and time spent on the internet were significantly associated with eHealth literacy (P<.001), and social media users were 3.97 times (adjusted odds ratio 3.97, 95% CI 1.02-15.43; P=.04) more likely to have higher skill. Higher eHealth literacy was associated with better self-perceived health and frequent use of digital technologies for accessing health and care services (P<.001).
Conclusions: Disparity in socioeconomic status and engagement on the internet and social media can result in different levels of eHealth literacy skills, which can have consequential impacts on health outcomes and eHealth use. Tailored eHealth interventions, grounded on the social and digital determinants of eHealth literacy, could facilitate eHealth information access among older adults and foster a digitally inclusive healthy aging community.
{"title":"Sociodigital Determinants of eHealth Literacy and Related Impact on Health Outcomes and eHealth Use in Korean Older Adults: Community-Based Cross-Sectional Survey.","authors":"Myat Yadana Kyaw, Myo Nyein Aung, Yuka Koyanagi, Saiyud Moolphate, Thin Nyein Nyein Aung, Hok Ka Carol Ma, Hocheol Lee, Hae-Kweun Nam, Eun Woo Nam, Motoyuki Yuasa","doi":"10.2196/56061","DOIUrl":"10.2196/56061","url":null,"abstract":"<p><strong>Background: </strong>eHealth literacy is an essential skill for pursuing electronic health information, particularly for older people whose health needs increase with age. South Korea is now at the intersection of a rapidly digitalizing society and an increasingly aged population. eHealth literacy enables older people to maximize the effective use of emerging digital technology for their health and quality of life. Understanding the eHealth literacy of Korean older adults is critical to eliminating the gray digital divide and inequity in health information access.</p><p><strong>Objective: </strong>This study aims to investigate factors influencing eHealth literacy in older Korean adults and its impact on health outcomes and eHealth use.</p><p><strong>Methods: </strong>This was a cross-sectional survey. Community-dwelling older adults 65 years and older in 2 urban cities in South Korea were included. eHealth literacy was measured by the eHealth Literacy Scale. Ordinal logistic regression was used to analyze factors associated with eHealth literacy and multivariate ANOVA for the impact of eHealth literacy on health outcomes and eHealth use.</p><p><strong>Results: </strong>In total, 434 participants were analyzed. A total of 22.3% (97/434) of participants had high eHealth literacy skills. Increasing age, higher monthly income, and time spent on the internet were significantly associated with eHealth literacy (P<.001), and social media users were 3.97 times (adjusted odds ratio 3.97, 95% CI 1.02-15.43; P=.04) more likely to have higher skill. Higher eHealth literacy was associated with better self-perceived health and frequent use of digital technologies for accessing health and care services (P<.001).</p><p><strong>Conclusions: </strong>Disparity in socioeconomic status and engagement on the internet and social media can result in different levels of eHealth literacy skills, which can have consequential impacts on health outcomes and eHealth use. Tailored eHealth interventions, grounded on the social and digital determinants of eHealth literacy, could facilitate eHealth information access among older adults and foster a digitally inclusive healthy aging community.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e56061"},"PeriodicalIF":5.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11336493/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141976841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: As the aging population in the United States continues to increase rapidly, preserving the mobility and independence of older adults becomes increasingly critical for enabling aging in place successfully. While personal vehicular transport remains a popular choice among this demographic due to its provision of independence and control over their lives, age-related changes may heighten the risk of common driving errors and diminish driving abilities.
Objective: This study aims to investigate the driving practices of older adults and their efforts to maintain safe and confident driving habits. Specifically, we sought to identify the factors that positively and negatively influence older adults' driving performance and confidence, as well as the existing efforts put into sustaining their driving abilities.
Methods: We recruited 20 adults aged ≥65 years who remained active drivers during the recruitment from the greater New York area. Then, we conducted semistructured interviews with them to examine their perceptions, needs, and challenges regarding safe and confident driving.
Results: Our findings uncovered a notable disparity between older adults' self-perceived driving skills and the challenges they face, particularly caused by age-related limitations and health conditions such as vision and memory declines and medication routines. Drawing on these findings, we proposed strategies to bridge this gap and empower older adults to drive safely and confidently, including fostering a realistic understanding of their capabilities, encouraging open dialogue regarding their driving, encouraging regular assessments, and increasing awareness of available resources.
Conclusions: This study uncovered a noticeable disparity between the perceived driving competence of older adults and the actual challenges they confront while driving. This divergence underscores a significant need for better support beyond the existing aid available to preserve older adults' driving skills. We hope that our recommendations will offer valuable insights for practitioners and scholars committed to enhancing the overall well-being and quality of life for older adults as they age in their homes.
{"title":"Toward Safe and Confident Silver Drivers: Interview Study Investigating Older Adults' Driving Practices.","authors":"Sunyoung Kim, Phaneendra Sivangula","doi":"10.2196/57402","DOIUrl":"10.2196/57402","url":null,"abstract":"<p><strong>Background: </strong>As the aging population in the United States continues to increase rapidly, preserving the mobility and independence of older adults becomes increasingly critical for enabling aging in place successfully. While personal vehicular transport remains a popular choice among this demographic due to its provision of independence and control over their lives, age-related changes may heighten the risk of common driving errors and diminish driving abilities.</p><p><strong>Objective: </strong>This study aims to investigate the driving practices of older adults and their efforts to maintain safe and confident driving habits. Specifically, we sought to identify the factors that positively and negatively influence older adults' driving performance and confidence, as well as the existing efforts put into sustaining their driving abilities.</p><p><strong>Methods: </strong>We recruited 20 adults aged ≥65 years who remained active drivers during the recruitment from the greater New York area. Then, we conducted semistructured interviews with them to examine their perceptions, needs, and challenges regarding safe and confident driving.</p><p><strong>Results: </strong>Our findings uncovered a notable disparity between older adults' self-perceived driving skills and the challenges they face, particularly caused by age-related limitations and health conditions such as vision and memory declines and medication routines. Drawing on these findings, we proposed strategies to bridge this gap and empower older adults to drive safely and confidently, including fostering a realistic understanding of their capabilities, encouraging open dialogue regarding their driving, encouraging regular assessments, and increasing awareness of available resources.</p><p><strong>Conclusions: </strong>This study uncovered a noticeable disparity between the perceived driving competence of older adults and the actual challenges they confront while driving. This divergence underscores a significant need for better support beyond the existing aid available to preserve older adults' driving skills. We hope that our recommendations will offer valuable insights for practitioners and scholars committed to enhancing the overall well-being and quality of life for older adults as they age in their homes.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e57402"},"PeriodicalIF":5.0,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11347888/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141917595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: Digitalization in the German health care system is progressing slowly, even though it offers opportunities for improvement of care. In nursing homes, most of the staff's work is paper based. Following the pandemic, there has been a decrease in the use of telemedicine applications. To ensure long-term implementation, the views of users, in this case nurses, are of interest.
Objective: This cross-sectional study was conducted to describe which digital applications are already being used at inpatient care facilities, the attitude of nurses toward telemedicine, and for which areas the use of telemedicine in the facilities is considered appropriate by the participants.
Methods: All inpatient care facility staff in Schleswig-Holstein were invited to participate in the survey from August 1 to October 31, 2022. The questionnaire consists of 17 determinants that ask about the attitude, use, and possible applications of telemedicine. In addition to a descriptive analysis, the influence of the general attitude toward telemedicine on various determinants was examined using the Fisher exact test for nominal variables and Spearman correlation coefficient for metric variables.
Results: A total of 425 caregivers participated in the survey. Of these respondents, 10.7% (n=41) currently used video consultations, and 76.1% (n=321) of the respondents were in favor of video consultations being practiced in training. Furthermore, 74.8% (n=312) of the respondents would attend a training on telephone medical consultation. Respondents indicated that video consultations have a small added value compared to asynchronous telemedicine (eg, sending photos). However, video consultations were perceived as somewhat less time-consuming than other communication channels. Video consultations are perceived as most useful for clarifying urgent problems. The respondents estimated that one in five paramedic calls at their facilities could be reduced through telemedicine approaches. It was important to the participants that telemedicine is as simple as possible and that there is a high level of data security.
Conclusions: Although many caregivers have a positive attitude toward telemedicine and perceive its advantages, communication channels such as video consultation are still used infrequently in care facilities. To promote the use of telemedicine applications, it is important to emphasize their benefits. The presumed saving of paramedic calls thus represents a benefit, and it is crucial to train caregivers in the use of telemedicine to avoid uncertainties in dealing with the newer technologies. It is important to give them enough time and repetitions of the training.
{"title":"Perceptions Toward Telemedicine of Health Care Staff in Nursing Homes in Northern Germany: Cross-Sectional Study.","authors":"Pia Traulsen, Lisa Kitschke, Jost Steinhäuser","doi":"10.2196/47072","DOIUrl":"10.2196/47072","url":null,"abstract":"<p><strong>Background: </strong>Digitalization in the German health care system is progressing slowly, even though it offers opportunities for improvement of care. In nursing homes, most of the staff's work is paper based. Following the pandemic, there has been a decrease in the use of telemedicine applications. To ensure long-term implementation, the views of users, in this case nurses, are of interest.</p><p><strong>Objective: </strong>This cross-sectional study was conducted to describe which digital applications are already being used at inpatient care facilities, the attitude of nurses toward telemedicine, and for which areas the use of telemedicine in the facilities is considered appropriate by the participants.</p><p><strong>Methods: </strong>All inpatient care facility staff in Schleswig-Holstein were invited to participate in the survey from August 1 to October 31, 2022. The questionnaire consists of 17 determinants that ask about the attitude, use, and possible applications of telemedicine. In addition to a descriptive analysis, the influence of the general attitude toward telemedicine on various determinants was examined using the Fisher exact test for nominal variables and Spearman correlation coefficient for metric variables.</p><p><strong>Results: </strong>A total of 425 caregivers participated in the survey. Of these respondents, 10.7% (n=41) currently used video consultations, and 76.1% (n=321) of the respondents were in favor of video consultations being practiced in training. Furthermore, 74.8% (n=312) of the respondents would attend a training on telephone medical consultation. Respondents indicated that video consultations have a small added value compared to asynchronous telemedicine (eg, sending photos). However, video consultations were perceived as somewhat less time-consuming than other communication channels. Video consultations are perceived as most useful for clarifying urgent problems. The respondents estimated that one in five paramedic calls at their facilities could be reduced through telemedicine approaches. It was important to the participants that telemedicine is as simple as possible and that there is a high level of data security.</p><p><strong>Conclusions: </strong>Although many caregivers have a positive attitude toward telemedicine and perceive its advantages, communication channels such as video consultation are still used infrequently in care facilities. To promote the use of telemedicine applications, it is important to emphasize their benefits. The presumed saving of paramedic calls thus represents a benefit, and it is crucial to train caregivers in the use of telemedicine to avoid uncertainties in dealing with the newer technologies. It is important to give them enough time and repetitions of the training.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e47072"},"PeriodicalIF":5.0,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11322793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141903118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julian Jeyasingh-Jacob, Mark Crook-Rumsey, Harshvi Shah, Theresita Joseph, Subati Abulikemu, Sarah Daniels, David J Sharp, Shlomi Haar
Background: Markerless motion capture (MMC) uses video cameras or depth sensors for full body tracking and presents a promising approach for objectively and unobtrusively monitoring functional performance within community settings, to aid clinical decision-making in neurodegenerative diseases such as dementia.
Objective: The primary objective of this systematic review was to investigate the application of MMC using full-body tracking, to quantify functional performance in people with dementia, mild cognitive impairment, and Parkinson disease.
Methods: A systematic search of the Embase, MEDLINE, CINAHL, and Scopus databases was conducted between November 2022 and February 2023, which yielded a total of 1595 results. The inclusion criteria were MMC and full-body tracking. A total of 157 studies were included for full-text screening, out of which 26 eligible studies that met the selection criteria were included in the review. .
Results: Primarily, the selected studies focused on gait analysis (n=24), while other functional tasks, such as sit to stand (n=5) and stepping in place (n=1), were also explored. However, activities of daily living were not evaluated in any of the included studies. MMC models varied across the studies, encompassing depth cameras (n=18) versus standard video cameras (n=5) or mobile phone cameras (n=2) with postprocessing using deep learning models. However, only 6 studies conducted rigorous comparisons with established gold-standard motion capture models.
Conclusions: Despite its potential as an effective tool for analyzing movement and posture in individuals with dementia, mild cognitive impairment, and Parkinson disease, further research is required to establish the clinical usefulness of MMC in quantifying mobility and functional performance in the real world.
{"title":"Markerless Motion Capture to Quantify Functional Performance in Neurodegeneration: Systematic Review.","authors":"Julian Jeyasingh-Jacob, Mark Crook-Rumsey, Harshvi Shah, Theresita Joseph, Subati Abulikemu, Sarah Daniels, David J Sharp, Shlomi Haar","doi":"10.2196/52582","DOIUrl":"10.2196/52582","url":null,"abstract":"<p><strong>Background: </strong>Markerless motion capture (MMC) uses video cameras or depth sensors for full body tracking and presents a promising approach for objectively and unobtrusively monitoring functional performance within community settings, to aid clinical decision-making in neurodegenerative diseases such as dementia.</p><p><strong>Objective: </strong>The primary objective of this systematic review was to investigate the application of MMC using full-body tracking, to quantify functional performance in people with dementia, mild cognitive impairment, and Parkinson disease.</p><p><strong>Methods: </strong>A systematic search of the Embase, MEDLINE, CINAHL, and Scopus databases was conducted between November 2022 and February 2023, which yielded a total of 1595 results. The inclusion criteria were MMC and full-body tracking. A total of 157 studies were included for full-text screening, out of which 26 eligible studies that met the selection criteria were included in the review. .</p><p><strong>Results: </strong>Primarily, the selected studies focused on gait analysis (n=24), while other functional tasks, such as sit to stand (n=5) and stepping in place (n=1), were also explored. However, activities of daily living were not evaluated in any of the included studies. MMC models varied across the studies, encompassing depth cameras (n=18) versus standard video cameras (n=5) or mobile phone cameras (n=2) with postprocessing using deep learning models. However, only 6 studies conducted rigorous comparisons with established gold-standard motion capture models.</p><p><strong>Conclusions: </strong>Despite its potential as an effective tool for analyzing movement and posture in individuals with dementia, mild cognitive impairment, and Parkinson disease, further research is required to establish the clinical usefulness of MMC in quantifying mobility and functional performance in the real world.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e52582"},"PeriodicalIF":5.0,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11336506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141898533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sophie Clohessy, Christian Kempton, Kate Ryan, Peter Grinbergs, Mark T Elliott
Background: Digital technologies can assist and optimize health care processes. This is increasingly the case in the musculoskeletal health domain, where digital platforms can be used to support the self-management of musculoskeletal conditions, as well as access to services. However, given a large proportion of the population with musculoskeletal conditions are older adults (aged ≥60 years), it is important to consider the acceptability of such platforms within this demographic.
Objective: This study aims to explore participants' opinions and perceptions on the use of digital platforms for supporting the self-management of musculoskeletal conditions within older adult (aged ≥60 years) populations and to gather their opinions on real examples.
Methods: A total of 2 focus groups (focus group 1: 6/15, 40%; focus group 2: 9/15, 60%) were conducted, in which participants answered questions about their thoughts on using digital health platforms to prevent or manage musculoskeletal conditions. Participants were further presented with 2 example scenarios, which were then discussed. Interviews were audio recorded, transcribed, and analyzed thematically. Participants were aged ≥60 years and with or without current musculoskeletal conditions. Prior experience of using smartphone apps or other digital health platforms for musculoskeletal conditions was not required. Focus groups took place virtually using the Teams (Microsoft Corp) platform.
Results: A total of 6 themes were identified across both focus groups: "experiences of digital health platforms," "preference for human contact," "barriers to accessing clinical services," "individual differences and digital literacy," "trust in technology," and "features and benefits of digital health technologies." Each theme is discussed in detail based on the interview responses. The findings revealed that most participants had some existing experience with digital health platforms for preventing or managing musculoskeletal conditions. Overall, there was a lack of trust in and low expectations of quality for digital platforms for musculoskeletal health within this age group. While there was some concern about the use of digital platforms in place of in-person health consultations, several benefits were also identified.
Conclusions: Results highlighted the need for better communication on the benefits of using digital platforms to support the self-management of musculoskeletal conditions, without the platforms replacing the role of the health care professionals. The concerns about which apps are of suitable quality and trustworthiness lead us to recommend raising public awareness around the role of organizations that verify and assess the quality of digital health platforms.
{"title":"Exploring Older Adults' Perceptions of Using Digital Health Platforms for Self-Managing Musculoskeletal Health Conditions: Focus Group Study.","authors":"Sophie Clohessy, Christian Kempton, Kate Ryan, Peter Grinbergs, Mark T Elliott","doi":"10.2196/55693","DOIUrl":"10.2196/55693","url":null,"abstract":"<p><strong>Background: </strong>Digital technologies can assist and optimize health care processes. This is increasingly the case in the musculoskeletal health domain, where digital platforms can be used to support the self-management of musculoskeletal conditions, as well as access to services. However, given a large proportion of the population with musculoskeletal conditions are older adults (aged ≥60 years), it is important to consider the acceptability of such platforms within this demographic.</p><p><strong>Objective: </strong>This study aims to explore participants' opinions and perceptions on the use of digital platforms for supporting the self-management of musculoskeletal conditions within older adult (aged ≥60 years) populations and to gather their opinions on real examples.</p><p><strong>Methods: </strong>A total of 2 focus groups (focus group 1: 6/15, 40%; focus group 2: 9/15, 60%) were conducted, in which participants answered questions about their thoughts on using digital health platforms to prevent or manage musculoskeletal conditions. Participants were further presented with 2 example scenarios, which were then discussed. Interviews were audio recorded, transcribed, and analyzed thematically. Participants were aged ≥60 years and with or without current musculoskeletal conditions. Prior experience of using smartphone apps or other digital health platforms for musculoskeletal conditions was not required. Focus groups took place virtually using the Teams (Microsoft Corp) platform.</p><p><strong>Results: </strong>A total of 6 themes were identified across both focus groups: \"experiences of digital health platforms,\" \"preference for human contact,\" \"barriers to accessing clinical services,\" \"individual differences and digital literacy,\" \"trust in technology,\" and \"features and benefits of digital health technologies.\" Each theme is discussed in detail based on the interview responses. The findings revealed that most participants had some existing experience with digital health platforms for preventing or managing musculoskeletal conditions. Overall, there was a lack of trust in and low expectations of quality for digital platforms for musculoskeletal health within this age group. While there was some concern about the use of digital platforms in place of in-person health consultations, several benefits were also identified.</p><p><strong>Conclusions: </strong>Results highlighted the need for better communication on the benefits of using digital platforms to support the self-management of musculoskeletal conditions, without the platforms replacing the role of the health care professionals. The concerns about which apps are of suitable quality and trustworthiness lead us to recommend raising public awareness around the role of organizations that verify and assess the quality of digital health platforms.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e55693"},"PeriodicalIF":5.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11327635/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141876240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fabian Herold, Paula Theobald, Thomas Gronwald, Navin Kaushal, Liye Zou, Eling D de Bruin, Louis Bherer, Notger G Müller
A healthy lifestyle can be an important prerequisite to prevent or at least delay the onset of dementia. However, the large number of physically inactive adults underscores the need for developing and evaluating intervention approaches aimed at improving adherence to a physically active lifestyle. In this regard, hybrid physical training, which usually combines center- and home-based physical exercise sessions and has proven successful in rehabilitative settings, could offer a promising approach to preserving cognitive health in the aging population. Despite its potential, research in this area is limited as hybrid physical training interventions have been underused in promoting healthy cognitive aging. Furthermore, the absence of a universally accepted definition or a classification framework for hybrid physical training interventions poses a challenge to future progress in this direction. To address this gap, this article informs the reader about hybrid physical training by providing a definition and classification approach of different types, discussing their specific advantages and disadvantages, and offering recommendations for future research. Specifically, we focus on applying digital technologies to deliver home-based exercises, as their use holds significant potential for reaching underserved and marginalized groups, such as older adults with mobility impairments living in rural areas.
{"title":"The Best of Two Worlds to Promote Healthy Cognitive Aging: Definition and Classification Approach of Hybrid Physical Training Interventions.","authors":"Fabian Herold, Paula Theobald, Thomas Gronwald, Navin Kaushal, Liye Zou, Eling D de Bruin, Louis Bherer, Notger G Müller","doi":"10.2196/56433","DOIUrl":"10.2196/56433","url":null,"abstract":"<p><p>A healthy lifestyle can be an important prerequisite to prevent or at least delay the onset of dementia. However, the large number of physically inactive adults underscores the need for developing and evaluating intervention approaches aimed at improving adherence to a physically active lifestyle. In this regard, hybrid physical training, which usually combines center- and home-based physical exercise sessions and has proven successful in rehabilitative settings, could offer a promising approach to preserving cognitive health in the aging population. Despite its potential, research in this area is limited as hybrid physical training interventions have been underused in promoting healthy cognitive aging. Furthermore, the absence of a universally accepted definition or a classification framework for hybrid physical training interventions poses a challenge to future progress in this direction. To address this gap, this article informs the reader about hybrid physical training by providing a definition and classification approach of different types, discussing their specific advantages and disadvantages, and offering recommendations for future research. Specifically, we focus on applying digital technologies to deliver home-based exercises, as their use holds significant potential for reaching underserved and marginalized groups, such as older adults with mobility impairments living in rural areas.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e56433"},"PeriodicalIF":5.0,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11325123/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141856695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chang Liu, Kai Zhang, Xiaodong Yang, Bingbing Meng, Jingsheng Lou, Yanhong Liu, Jiangbei Cao, Kexuan Liu, Weidong Mi, Hao Li
<p><strong>Background: </strong>Myocardial injury after noncardiac surgery (MINS) is an easily overlooked complication but closely related to postoperative cardiovascular adverse outcomes; therefore, the early diagnosis and prediction are particularly important.</p><p><strong>Objective: </strong>We aimed to develop and validate an explainable machine learning (ML) model for predicting MINS among older patients undergoing noncardiac surgery.</p><p><strong>Methods: </strong>The retrospective cohort study included older patients who had noncardiac surgery from 1 northern center and 1 southern center in China. The data sets from center 1 were divided into a training set and an internal validation set. The data set from center 2 was used as an external validation set. Before modeling, the least absolute shrinkage and selection operator and recursive feature elimination methods were used to reduce dimensions of data and select key features from all variables. Prediction models were developed based on the extracted features using several ML algorithms, including category boosting, random forest, logistic regression, naïve Bayes, light gradient boosting machine, extreme gradient boosting, support vector machine, and decision tree. Prediction performance was assessed by the area under the receiver operating characteristic (AUROC) curve as the main evaluation metric to select the best algorithms. The model performance was verified by internal and external validation data sets with the best algorithm and compared to the Revised Cardiac Risk Index. The Shapley Additive Explanations (SHAP) method was applied to calculate values for each feature, representing the contribution to the predicted risk of complication, and generate personalized explanations.</p><p><strong>Results: </strong>A total of 19,463 eligible patients were included; among those, 12,464 patients in center 1 were included as the training set; 4754 patients in center 1 were included as the internal validation set; and 2245 in center 2 were included as the external validation set. The best-performing model for prediction was the CatBoost algorithm, achieving the highest AUROC of 0.805 (95% CI 0.778-0.831) in the training set, validating with an AUROC of 0.780 in the internal validation set and 0.70 in external validation set. Additionally, CatBoost demonstrated superior performance compared to the Revised Cardiac Risk Index (AUROC 0.636; P<.001). The SHAP values indicated the ranking of the level of importance of each variable, with preoperative serum creatinine concentration, red blood cell distribution width, and age accounting for the top three. The results from the SHAP method can predict events with positive values or nonevents with negative values, providing an explicit explanation of individualized risk predictions.</p><p><strong>Conclusions: </strong>The ML models can provide a personalized and fairly accurate risk prediction of MINS, and the explainable perspective can help identify pot
{"title":"Development and Validation of an Explainable Machine Learning Model for Predicting Myocardial Injury After Noncardiac Surgery in Two Centers in China: Retrospective Study.","authors":"Chang Liu, Kai Zhang, Xiaodong Yang, Bingbing Meng, Jingsheng Lou, Yanhong Liu, Jiangbei Cao, Kexuan Liu, Weidong Mi, Hao Li","doi":"10.2196/54872","DOIUrl":"10.2196/54872","url":null,"abstract":"<p><strong>Background: </strong>Myocardial injury after noncardiac surgery (MINS) is an easily overlooked complication but closely related to postoperative cardiovascular adverse outcomes; therefore, the early diagnosis and prediction are particularly important.</p><p><strong>Objective: </strong>We aimed to develop and validate an explainable machine learning (ML) model for predicting MINS among older patients undergoing noncardiac surgery.</p><p><strong>Methods: </strong>The retrospective cohort study included older patients who had noncardiac surgery from 1 northern center and 1 southern center in China. The data sets from center 1 were divided into a training set and an internal validation set. The data set from center 2 was used as an external validation set. Before modeling, the least absolute shrinkage and selection operator and recursive feature elimination methods were used to reduce dimensions of data and select key features from all variables. Prediction models were developed based on the extracted features using several ML algorithms, including category boosting, random forest, logistic regression, naïve Bayes, light gradient boosting machine, extreme gradient boosting, support vector machine, and decision tree. Prediction performance was assessed by the area under the receiver operating characteristic (AUROC) curve as the main evaluation metric to select the best algorithms. The model performance was verified by internal and external validation data sets with the best algorithm and compared to the Revised Cardiac Risk Index. The Shapley Additive Explanations (SHAP) method was applied to calculate values for each feature, representing the contribution to the predicted risk of complication, and generate personalized explanations.</p><p><strong>Results: </strong>A total of 19,463 eligible patients were included; among those, 12,464 patients in center 1 were included as the training set; 4754 patients in center 1 were included as the internal validation set; and 2245 in center 2 were included as the external validation set. The best-performing model for prediction was the CatBoost algorithm, achieving the highest AUROC of 0.805 (95% CI 0.778-0.831) in the training set, validating with an AUROC of 0.780 in the internal validation set and 0.70 in external validation set. Additionally, CatBoost demonstrated superior performance compared to the Revised Cardiac Risk Index (AUROC 0.636; P<.001). The SHAP values indicated the ranking of the level of importance of each variable, with preoperative serum creatinine concentration, red blood cell distribution width, and age accounting for the top three. The results from the SHAP method can predict events with positive values or nonevents with negative values, providing an explicit explanation of individualized risk predictions.</p><p><strong>Conclusions: </strong>The ML models can provide a personalized and fairly accurate risk prediction of MINS, and the explainable perspective can help identify pot","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e54872"},"PeriodicalIF":5.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11294761/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141861142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Angélique Roquet, Paolo Martinelli, Charikleia Lampraki, Daniela S Jopp
Background: Internet use has dramatically increased worldwide, with over two-thirds of the world's population using it, including the older adult population. Technical resources such as internet use have been shown to influence psychological processes such as stress positively. Following the Conservation of Resources theory by Hobfoll, stress experience largely depends on individuals' personal resources and the changes in these resources. While personal resource loss has been shown to lead to stress, we know little regarding the role that technical resources may play on the relationship between personal resources and stress.
Objective: This study aims to investigate the moderating effect of technical resources (internet use) on the relationship between personal resources and stress in younger and older adults.
Methods: A total of 275 younger adults (aged 18 to 30 years) and 224 older adults (aged ≥65 years) indicated their levels of stress; change in personal resources (ie, cognitive, social, and self-efficacy resource loss and gain); and internet use. Variance analyses, multiple regression, and moderation analyses were performed to investigate the correlates of stress.
Results: Results showed that older adults, despite experiencing higher levels of resource loss (questionnaire scores: 1.82 vs 1.54; P<.001) and less resource gain (questionnaire scores: 1.82 vs 2.31; P<.001), were less stressed than younger adults (questionnaire scores: 1.99 vs 2.47; P<.001). We observed that the relationship among resource loss, resource gain, and stress in older adults was moderated by their level of internet use (β=.09; P=.05). Specifically, older adults who used the internet more frequently were less stressed when they experienced high levels of both loss and gain compared to their counterparts who used internet the less in the same conditions. Furthermore, older adults with low resource gain and high resource loss expressed less stress when they used the internet more often compared to those with low internet use.
Conclusions: These findings highlight the importance of internet use in mitigating stress among older adults experiencing resource loss and gain, emphasizing the potential of digital interventions to promote mental health in this population.
背景:互联网的使用在全球范围内急剧增加,超过三分之二的世界人口使用互联网,其中包括老年人口。互联网使用等技术资源已被证明会对压力等心理过程产生积极影响。根据霍布福尔的资源保护理论,压力体验在很大程度上取决于个人的个人资源以及这些资源的变化。虽然个人资源的流失已被证明会导致压力,但我们对技术资源在个人资源与压力之间的关系中所起的作用知之甚少:本研究旨在调查技术资源(互联网使用)对年轻人和老年人的个人资源与压力之间关系的调节作用:共有275名年轻人(18至30岁)和224名老年人(年龄≥65岁)表示了他们的压力水平、个人资源变化(即认知、社会和自我效能资源的损失和增加)以及互联网使用情况。通过方差分析、多元回归和调节分析来研究压力的相关因素:结果显示,尽管老年人的资源损失程度较高(问卷得分:1.82 vs 1.54;1.82 vs 1.54;1.82 vs 1.54结果:结果表明,尽管老年人的资源损失程度较高(问卷得分:1.82 vs 1.54;PC 结论:这些结果突出了互联网使用的重要性:这些研究结果凸显了互联网的使用在缓解老年人资源损益压力方面的重要性,强调了数字干预在促进该人群心理健康方面的潜力。
{"title":"Internet Use as a Moderator of the Relationship Between Personal Resources and Stress in Older Adults: Cross-Sectional Study.","authors":"Angélique Roquet, Paolo Martinelli, Charikleia Lampraki, Daniela S Jopp","doi":"10.2196/52555","DOIUrl":"10.2196/52555","url":null,"abstract":"<p><strong>Background: </strong>Internet use has dramatically increased worldwide, with over two-thirds of the world's population using it, including the older adult population. Technical resources such as internet use have been shown to influence psychological processes such as stress positively. Following the Conservation of Resources theory by Hobfoll, stress experience largely depends on individuals' personal resources and the changes in these resources. While personal resource loss has been shown to lead to stress, we know little regarding the role that technical resources may play on the relationship between personal resources and stress.</p><p><strong>Objective: </strong>This study aims to investigate the moderating effect of technical resources (internet use) on the relationship between personal resources and stress in younger and older adults.</p><p><strong>Methods: </strong>A total of 275 younger adults (aged 18 to 30 years) and 224 older adults (aged ≥65 years) indicated their levels of stress; change in personal resources (ie, cognitive, social, and self-efficacy resource loss and gain); and internet use. Variance analyses, multiple regression, and moderation analyses were performed to investigate the correlates of stress.</p><p><strong>Results: </strong>Results showed that older adults, despite experiencing higher levels of resource loss (questionnaire scores: 1.82 vs 1.54; P<.001) and less resource gain (questionnaire scores: 1.82 vs 2.31; P<.001), were less stressed than younger adults (questionnaire scores: 1.99 vs 2.47; P<.001). We observed that the relationship among resource loss, resource gain, and stress in older adults was moderated by their level of internet use (β=.09; P=.05). Specifically, older adults who used the internet more frequently were less stressed when they experienced high levels of both loss and gain compared to their counterparts who used internet the less in the same conditions. Furthermore, older adults with low resource gain and high resource loss expressed less stress when they used the internet more often compared to those with low internet use.</p><p><strong>Conclusions: </strong>These findings highlight the importance of internet use in mitigating stress among older adults experiencing resource loss and gain, emphasizing the potential of digital interventions to promote mental health in this population.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"7 ","pages":"e52555"},"PeriodicalIF":5.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11297370/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141724615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gordana Dermody, Daniel Wadsworth, Melissa Dunham, Courtney Glass, Roschelle Fritz
Background: Background: The population of older adults across the world continues to increase, placing higher demands on primary health care and long-term care. The costs of housing older people in care facilities have economic and societal impacts which are unsustainable without innovative solutions. Many older people wish to remain independent in their homes and age-in-place. Assistive technology such as health-assistive smart homes with clinician monitoring could be a widely adopted alternative to aged care facilities in the future. Whilst studies have found that older persons have demonstrated a readiness to adopt health-assistive smart homes, little is known about clinician readiness to adopt this technology to support older adults to age as independently as possible.
Objective: Objective: The purpose of this systematic review was to identify the factors that affect clinician readiness to adopt smart home technology for remote health monitoring.
Methods: Methods: The review protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO, CRD42020195989) prior to the commencement of the database searches. This review was conducted in accordance with the Joanna Briggs Institute Methodology for Systematic Reviews and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for reporting.
Results: Results: Several factors affected clinicians' perspectives on their readiness to adopt smart home technology for remote health monitoring including challenges such as patient privacy and dignity, data security, and ethical use of 'invasive' technologies. Perceived benefits included enhancing the quality of care and outcomes.
Conclusions: Conclusion: Clinicians including nurses reported both challenges and benefits to adopt smart home technology for remote health monitoring. Clear strategies and frameworks to allay fears and overcome professional concerns and misconceptions form key parts of the Readiness to Adoption Pathway proposed. The use of more rigorous scientific methods and reporting is needed to advance the state of the science.
Clinicaltrial: The review protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO, CRD42020195989) prior to the commencement of the database searches.
{"title":"Factors Affecting Clinician Readiness to Adopt Smart Home Technology for Remote Health Monitoring: A Systematic Review.","authors":"Gordana Dermody, Daniel Wadsworth, Melissa Dunham, Courtney Glass, Roschelle Fritz","doi":"10.2196/64367","DOIUrl":"https://doi.org/10.2196/64367","url":null,"abstract":"<p><strong>Background: </strong>Background: The population of older adults across the world continues to increase, placing higher demands on primary health care and long-term care. The costs of housing older people in care facilities have economic and societal impacts which are unsustainable without innovative solutions. Many older people wish to remain independent in their homes and age-in-place. Assistive technology such as health-assistive smart homes with clinician monitoring could be a widely adopted alternative to aged care facilities in the future. Whilst studies have found that older persons have demonstrated a readiness to adopt health-assistive smart homes, little is known about clinician readiness to adopt this technology to support older adults to age as independently as possible.</p><p><strong>Objective: </strong>Objective: The purpose of this systematic review was to identify the factors that affect clinician readiness to adopt smart home technology for remote health monitoring.</p><p><strong>Methods: </strong>Methods: The review protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO, CRD42020195989) prior to the commencement of the database searches. This review was conducted in accordance with the Joanna Briggs Institute Methodology for Systematic Reviews and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for reporting.</p><p><strong>Results: </strong>Results: Several factors affected clinicians' perspectives on their readiness to adopt smart home technology for remote health monitoring including challenges such as patient privacy and dignity, data security, and ethical use of 'invasive' technologies. Perceived benefits included enhancing the quality of care and outcomes.</p><p><strong>Conclusions: </strong>Conclusion: Clinicians including nurses reported both challenges and benefits to adopt smart home technology for remote health monitoring. Clear strategies and frameworks to allay fears and overcome professional concerns and misconceptions form key parts of the Readiness to Adoption Pathway proposed. The use of more rigorous scientific methods and reporting is needed to advance the state of the science.</p><p><strong>Clinicaltrial: </strong>The review protocol was registered with the International Prospective Register of Systematic Reviews (PROSPERO, CRD42020195989) prior to the commencement of the database searches.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":" ","pages":""},"PeriodicalIF":5.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141627943","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}