{"title":"Evaluating the Effectiveness of Digital Social Robots in Reducing Loneliness Among Community-Dwelling Older Adults in Japan: Randomized Controlled Trial and Qualitative Analysis.","authors":"Hiroshi Murayama, Mai Takase","doi":"10.2196/74422","DOIUrl":"10.2196/74422","url":null,"abstract":"<p><strong>Background: </strong>Most studies on interventions using social robots to reduce loneliness have been conducted in facilities in Western countries.</p><p><strong>Objective: </strong>This study evaluated the effectiveness of digital social robot interventions in reducing loneliness among community-dwelling older Japanese adults using a randomized controlled trial and qualitative analysis.</p><p><strong>Methods: </strong>Individuals aged ≥65 years who lived alone in Tokyo and neighboring areas and experienced loneliness were recruited. In total, 73 eligible participants were randomly assigned to either an intervention or a control group. The 4-week intervention involved a humanoid social communication robot (BOCCO emo), which facilitated conversations with human operators and family members and reminded participants of daily tasks. The primary outcome was loneliness, with mental health (psychological well-being, depression, and self-rated health), the frequency of laughter in daily life, health competence, and interpersonal relationships (social network and generalized trust) as secondary outcomes. Participants were evaluated at baseline and follow-up using a self-administered questionnaire. In the follow-up survey, participants in the intervention group provided open-ended responses regarding their experiences using the social robot.</p><p><strong>Results: </strong>In total, 68 participants completed both the baseline and follow-up surveys (34 in each group). The average age of the participants was 82.3 (SD 6.5) years, and 64 (N=68, 94%) participants were women. A linear mixed-effects model with a random intercept indicated that loneliness decreased more in the intervention group than in the control group (difference-in-difference -3.1, 95% CI -5.9 to -0.4). Psychological well-being also improved in the intervention group (difference-in-difference 1.9, 95% CI 0.1 to 3.7). We identified 4 categories through content analysis: emotional support and psychological connection, lifestyle assistance, enrichment of social interaction, and cognitive and mental stimulation.</p><p><strong>Conclusions: </strong>Social robots can reduce loneliness among community-dwelling older adults in non-Western societies. Information and communication technology appears to be an effective approach for alleviating loneliness and enhancing well-being among older adults in community settings.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e74422"},"PeriodicalIF":4.8,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12543208/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145348967","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}
Sofia Fernandes, Joëlle Rosselet Amoussou, Carla Gomes da Rocha, Elodie Perruchoud, Armin von Gunten, Cédric Mabire, Henk Verloo
{"title":"Using Artificial Intelligence-Based Technologies for the Early Detection of Behavioral and Psychological Symptoms of Dementia: Scoping Review.","authors":"Sofia Fernandes, Joëlle Rosselet Amoussou, Carla Gomes da Rocha, Elodie Perruchoud, Armin von Gunten, Cédric Mabire, Henk Verloo","doi":"10.2196/76074","DOIUrl":"https://doi.org/10.2196/76074","url":null,"abstract":"<p><strong>Background: </strong>People with dementia commonly display behavioral and psychological symptoms, which have multiple negative consequences. Artificial intelligence-based technologies (AITs) have the potential to support earlier detection of the behavioral and psychological symptoms of dementia (BPSD). The recent surge of interest in this topic underscores the need to comprehensively examine the existing evidence.</p><p><strong>Objective: </strong>This scoping review aimed to identify and summarize the types and uses of AITs currently used for the early detection of BPSD among people diagnosed with the disease. We also examined which health care professionals were involved, nursing involvement and experience, the care settings in which these technologies are used, and the characteristics of the BPSD that were assessed.</p><p><strong>Methods: </strong>Our scoping review was conducted in accordance with the Joanna Briggs Institute manual for scoping reviews. Searches were conducted in March 2025 in the following bibliographic databases: MEDLINE ALL Ovid, Embase, APA PsycINFO Ovid, CINAHL EBSCO, Web of Science Core Collection, the Cochrane Library Wiley, and ProQuest Dissertations and Theses A&I. Additional searches were performed using citation tracking strategies and by consulting the Association for Computing Machinery Digital Library. Eligible studies included primary research involving people with dementia and examining the use of AITs for the detection of BPSD in real-world care settings.</p><p><strong>Results: </strong>After screening 3670 articles for eligibility, the review includes 12 studies. The studies retained were conducted between 2012 and 2025 in 5 countries and encompassed a range of care settings. The AITs used were predominantly based on classic machine learning approaches and used information from environmental sensors, wearable devices, and data recording systems. These studies primarily assessed behavioral and physiological parameters and focused specifically on symptoms, such as agitation and aggression. None of the retained studies explored nurses' roles or their specific skills in using these technologies.</p><p><strong>Conclusions: </strong>The use of AITs for managing BPSD represents an emerging field of research offering novel opportunities to enhance their detection in various health care contexts. We recommended that nurses be actively engaged in developing and assessing these technologies. Future research should prioritize investigations into how effective AITs are across diverse populations, whether they can have a long-term impact on managing BPSD, and whether they can improve the quality of life of patients and caregivers.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e76074"},"PeriodicalIF":4.8,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12539798/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145348981","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}
Nina Parchmann, Marcin Orzechowski, Simone Brefka, Florian Steger
{"title":"Evaluation of an AI-Based Clinical Decision Support System for Perioperative Care of Older Patients: Ethical Analysis of Focus Groups With Older Adults.","authors":"Nina Parchmann, Marcin Orzechowski, Simone Brefka, Florian Steger","doi":"10.2196/71568","DOIUrl":"10.2196/71568","url":null,"abstract":"<p><strong>Background: </strong>The development and introduction of an artificial intelligence (AI)-based clinical decision support system (CDSS) in surgical departments as part of the \"Supporting Surgery with Geriatric Co-management and AI\" project addresses the challenges of an increasingly aging population. The system enables digital comanagement of older patients by providing evidence-based evaluations of their health status, along with corresponding medical recommendations, with the aim of improving their perioperative care.</p><p><strong>Objective: </strong>The use of an AI-based CDSS in patient care raises ethical challenges. Gathering the opinions, expectations, and concerns of older adults (as potential patients) regarding the CDSS enables the identification of ethical opportunities, concerns, and limitations associated with implementing such a system in hospitals.</p><p><strong>Methods: </strong>We conducted 5 focus groups with participants aged 65 years or older. The transcripts were evaluated using qualitative content analysis and ethically analyzed. Categories were inductively generated, followed by a thematic classification of participants' statements. We found that technical understanding did not influence the older adults' opinions.</p><p><strong>Results: </strong>Ethical opportunities and concerns were identified. On the one hand, diagnosis and treatment could be accelerated, the patient-AI-physician interaction could enhance medical treatment, and the coordination of hospital processes could be improved. On the other hand, the quality of the CDSS depends on an adequate data foundation and robust cybersecurity. Potential risks included habituation effects, loss of a second medical opinion, and illness severity influencing patients' attitude toward medical recommendations. The risk of overdiagnosis and overtreatment was discussed controversially, and treatment options could be influenced by interests and finances. Additional concerns included challenges with time savings, potential declines in medical skills, and effects on the length of hospital stay.</p><p><strong>Conclusions: </strong>To address the ethical challenges, we recommend allocating sufficient time for use of the CDSS and emphasizing individualized review of the CDSS results. Furthermore, we suggest limiting private financial sponsorship.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e71568"},"PeriodicalIF":4.8,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12533935/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145313970","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}
Emilie Schoebrechts, Johanna de Almeida Mello, Patricia Ann Ivonne Vandenbulcke, Hein Petrus Johannes van Hout, Jan De Lepeleire, Anja Declercq, Dominique Declerck, Joke Duyck
{"title":"Insights Into Associations Between Oral and General Health Outcomes of Nursing Home Residents Based on InterRAI Data: Cross-Sectional Study.","authors":"Emilie Schoebrechts, Johanna de Almeida Mello, Patricia Ann Ivonne Vandenbulcke, Hein Petrus Johannes van Hout, Jan De Lepeleire, Anja Declercq, Dominique Declerck, Joke Duyck","doi":"10.2196/72308","DOIUrl":"10.2196/72308","url":null,"abstract":"<p><strong>Background: </strong>Oral health of nursing home residents is generally poor, largely due to age-related conditions that increase their vulnerability and make them more dependent on others for oral care. Poor oral health can significantly impact general health and well-being, highlighting the important role of caregivers in preventing, detecting, and addressing residents' oral health problems in time. The interRAI Suite of instruments, widely used for comprehensive health assessments, offers the opportunity for nondental caregivers to assess oral health as part of general health and well-being and facilitates the integration of oral health in general care planning.</p><p><strong>Objective: </strong>Based on interRAI data, this study explored the associations between oral health and general health outcomes of nursing home residents in Flanders (Belgium) and the Netherlands.</p><p><strong>Methods: </strong>This cross-sectional study included baseline interRAI assessments of 2362 Flemish and Dutch residents aged 65 years and older, collected by caregivers (eg, nurses, nurse aids) between October 2020 and February 2024. Validated outcome scales (eg, Activities of Daily Living Hierarchy Scale, Cognitive Performance Scale, and Depression Rating Scale), health conditions such as diabetes and low weight (BMI ≤19), and family support and participation in social activities, included in the interRAI instrument, provided information on residents' general health and well-being. Oral health was defined according to the 9 items of the optimized Oral Health Screener (OHS) for use in the interRAI instruments. Adjusted logistic regression models were used to explore the associations between oral and general health outcomes.</p><p><strong>Results: </strong>Oral health problems were interconnected, with conditions in one oral structure impacting the health of others. When controlling for confounding variables, dependency on others for personal care and hygiene was significantly associated with poor oral hygiene (odds ratio [OR] 1.7, 95% CI 1.1-2.4), chewing difficulties (OR 2.2, 95% CI 1.3-3.5), compromised teeth (OR 1.7, 95% CI 1.1-2.5), and the need for dental referral (OR 1.8, 95% CI 1.4-2.3). Natural dentition and gender had a significant impact on oral health status. Low weight was associated with poor chewing function (OR 2.0, 95% CI 1.1-3.6) and dry mouth (OR 1.8, 95% CI 1.0-3.2), both associated with oral discomfort or pain (OR 6.8, 95% CI 3.3-14.0 and OR 3.5, 95% CI 1.8-6.9, respectively). Family support was identified as a facilitator in mitigating oral health problems.</p><p><strong>Conclusions: </strong>The interRAI instrument, including the OHS, is a valuable tool for monitoring residents' health and identifying areas requiring additional support. The results demonstrated the importance of prioritizing oral health as an integral component of comprehensive care. Recognizing the interconnection between oral health and other health conditions, i","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e72308"},"PeriodicalIF":4.8,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12533934/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145313926","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}
{"title":"Intraoperative Hypotension and Major Adverse Cardiac Events Among Older Adult Patients Undergoing Noncardiac Surgery: Retrospective Cohort Study.","authors":"Kai Zhang, Chang Liu, Meng Wang, Ting Zhang, Bingbing Meng, Siyi Yao, Jingsheng Lou, Qiang Fu, Yanhong Liu, Jiangbei Cao, Lulong Bo, Weidong Mi, Hao Li","doi":"10.2196/67177","DOIUrl":"10.2196/67177","url":null,"abstract":"<p><strong>Background: </strong>Intraoperative hypotension (IOH) is an important risk factor for major adverse cardiac events (MACE) in patients undergoing noncardiac surgery. However, the IOH threshold in older adult patients remains controversial.</p><p><strong>Objective: </strong>This study aimed to explore an appropriate IOH threshold in older adult patients to decrease the risk of MACE.</p><p><strong>Methods: </strong>This study involved older adult patients undergoing noncardiac surgery (age ≥65 y) from January 2012 to August 2019 in the Chinese People's Liberation Army General Hospital (PLAGH; 35,262 patients) and Shanghai Changhai Hospital from January 2024 to December 2024 (13,418 patients). Univariate moving-average plots and multivariate restricted cubic splines were used to determine the IOH thresholds associated with an increased risk of MACE. The relationship between the IOH threshold and MACE was assessed using univariate and multivariate logistic regression analyses by 3 different hypotension exposure forms (duration, area, and time-weighted average mean arterial pressure [MAP]).</p><p><strong>Results: </strong>Out of 35,262 patients, 874 developed MACE in PLAGH, and 296 of 13,418 patients developed MACE in Changhai Hospital. In PLAGH, MAP below an absolute threshold of 70 mm Hg was associated with MACE. When the IOH absolute threshold was 70 mm Hg, the risk of MACE demonstrated a \"dose-increasing\" effect with changes in IOH exposure, and the risk of MACE was significantly increased when the duration lasted >15 minutes (odds ratio 1.51, 95% CI 1.22-1.88; P<.001). The stratified analysis showed that in patients younger than 80 years, when intraoperative MAP dropped below 70 mm Hg for more than 15 minutes, the odds ratio was 1.38 (95% CI 0.86-2.28), P<.01. In Changhai hospital, intraoperative MAP <70 mm Hg was also significantly associated with MACE. Furthermore, IOH lasting longer than 15 minutes substantially increased the risk of MACE.</p><p><strong>Conclusions: </strong>For older adult patients undergoing noncardiac surgery, intraoperative MAP should be kept above 70 mm Hg to reduce the risk of postoperative MACE.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e67177"},"PeriodicalIF":4.8,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12530642/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145309353","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}
Céline Madeleine Aldenhoven, Matthew Milton, Lisa D'Ambrosio, Chaiwoo Lee, Sophia Ashebir, Elisabeth André
{"title":"An Accessible Multifunctional System to Support Safe and Independent Aging in Place: Iterative Development and Qualitative Analysis.","authors":"Céline Madeleine Aldenhoven, Matthew Milton, Lisa D'Ambrosio, Chaiwoo Lee, Sophia Ashebir, Elisabeth André","doi":"10.2196/72579","DOIUrl":"10.2196/72579","url":null,"abstract":"<p><strong>Background: </strong>The global population of older adults is rapidly increasing, while the number of relative caregivers is declining. This creates a critical need for solutions that support caregiving and enable older adults to age in place while maintaining their independence. Many existing caregiving technologies focus on easing caregivers' burdens through surveillance-based systems, which often prioritize caregivers' needs over those of older adults. Such designs can unintentionally disempower older adults by devaluing their autonomy and decision-making capabilities.</p><p><strong>Objective: </strong>This study explored older adults' and designers' reactions to a technology-enabled system called LifeTomorrow that was built by centering older adults as the primary users. The system aims to support their autonomy to make informed choices and their desire for independent living, while balancing their social and functional needs with those of informal caregivers.</p><p><strong>Methods: </strong>A total of 37 participants, including older adults, caregivers, and designers, engaged in 2 iterative rounds of user studies to explore daily caregiving needs and technology usage. The system's design and features were refined based on these insights. A qualitative thematic analysis was conducted using the framework of the self-determination theory to evaluate how the system fulfills the basic psychological needs of competence, autonomy, and relatedness.</p><p><strong>Results: </strong>The analysis underscored the system's value to older adults and their caregivers, and its fulfillment of basic human psychological needs (competence, autonomy, and relatedness), consistent with the goals of supporting a high quality of life for older users and caregivers. We found that relatedness is fostered through features enabling remote connection and communication, such as chat functions and shared health data. Autonomy is supported by empowering older adults to manage their health information, make informed choices about data sharing, and benefit from safety features like fall detection and emergency calls. Competence is enhanced through accessible design elements, including intuitive navigation, high-contrast visuals, and multigenerational usability. These features allow older adults and caregivers to confidently engage with the system and are targeted at improving their overall quality of life.</p><p><strong>Conclusions: </strong>Through evaluation of the LifeTomorrow system, this study suggests possibilities for using a holistic, inclusive solution to support safe and independent aging in place and prioritizing the autonomy and empowerment of older adults while addressing caregivers' needs for support and connection. By centering older adults as active participants rather than passive recipients of care, the system exemplifies a shift toward equitable, user-centered technology in caregiving. Future research should investigate the long-term impacts of su","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e72579"},"PeriodicalIF":4.8,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12530453/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145309407","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}
Baldwin Pok Man Kwan, Marissa Dickins, Sue Williams, Frances Batchelor, Kerry Hwang, Kate Fulford, Tony Walsh, Helena Jakupovic, Tanya E Davison
{"title":"The Use of Technology to Deliver In-Home Aged Care Services: Mixed Methods Study of Australian Staff Perspectives.","authors":"Baldwin Pok Man Kwan, Marissa Dickins, Sue Williams, Frances Batchelor, Kerry Hwang, Kate Fulford, Tony Walsh, Helena Jakupovic, Tanya E Davison","doi":"10.2196/76141","DOIUrl":"10.2196/76141","url":null,"abstract":"<p><strong>Background: </strong>With a global aging population, technology has been proposed as a solution to address the growing demand for services in the in-home aged care sector. Despite the potential of technology, there are difficulties when implementing technology into routine care delivery. There is a lack of evidence regarding the specific factors affecting technology use in the in-home aged care setting from the perspective of the direct care workforce.</p><p><strong>Objective: </strong>This study aimed to understand in-home aged care staff members' views of (1) the digital enablement potential of direct in-home care tasks, (2) benefits and drawbacks of technology use, and (3) enablers and barriers for technology use in Australian in-home aged care.</p><p><strong>Methods: </strong>An explanatory sequential mixed methods research design was used, with a cross-sectional survey and semistructured staff interviews. Participants were recruited from in-home aged care staff members working at a national Australian in-home health and aged care organization.</p><p><strong>Results: </strong>In total, 226 participants completed the survey, and 18 participants completed the interviews. Overall, participants felt that many care tasks within in-home aged care could be digitally enabled, with more than half (56%) of the common direct care tasks identified as being likely to be digitally enabled. Participants also discussed a range of quality of care-, staff-, and organization-related benefits and drawbacks in the use of technology. Finally, participants agreed that most of the researcher-proposed enablers and barriers were important, while suggesting additional enablers and barriers such as client preferences regarding technology use and poor data connectivity.</p><p><strong>Conclusions: </strong>This study provides insight into staff members' views regarding the use of technology to deliver in-home aged care services. The results could help inform technology developers and in-home aged care providers, providing key information to guide technology implementation into care delivery. Further research is required to ensure that appropriate strategies are available to ensure successful implementation of technology into in-home aged care.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e76141"},"PeriodicalIF":4.8,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12520620/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145293959","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}
{"title":"Comparative Diagnostic Accuracy of AI-Assisted Fluorine-18 Fluorodeoxyglucose Positron Emission Tomography Versus Structural Magnetic Resonance Imaging in Alzheimer Disease: Systematic Review and Meta-Analysis.","authors":"Bingbing Wang, Tailiang Zhao, Rongrong Ma, Xiaochuan Huo, Xiaoxiao Xiong, Minjie Wu, Yuran Wang, Liu Liu, Zhijiang Zhuang, Bin Wang, Jixin Shou","doi":"10.2196/76981","DOIUrl":"10.2196/76981","url":null,"abstract":"<p><strong>Background: </strong>Neuroimaging is crucial in the diagnosis of Alzheimer disease (AD). In recent years, artificial intelligence (AI)-based neuroimaging technology has rapidly developed, providing new methods for accurate diagnosis of AD, but its performance differences still need to be systematically evaluated.</p><p><strong>Objective: </strong>This study aims to conduct a systematic review and meta-analysis comparing the diagnostic performance of AI-assisted fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG PET) and structural magnetic resonance imaging (sMRI) for AD.</p><p><strong>Methods: </strong>Databases including Web of Science, PubMed, and Embase were searched from inception to January 2025 to identify original studies that developed or validated AI models for AD diagnosis using 18F-FDG PET or sMRI. Methodological quality was assessed using the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-Artificial Intelligence) checklist. A bivariate mixed-effects model was employed to calculate pooled sensitivity, specificity, and summary receiver operating characteristic curve area (SROC-AUC).</p><p><strong>Results: </strong>A total of 38 studies were included, with 28 moderate-to-high-quality studies analyzed. Pooled SROC-AUC values were 0.94 (95% CI 0.92-0.96) for sMRI and 0.96 (95% CI 0.94-0.98) for 18F-FDG PET, demonstrating statistically significant intermodal differences (P=.02). Subgroup analyses revealed that for machine learning, pooled SROC-AUCs were 0.89 (95% CI 0.86-0.92) for sMRI and 0.95 (95% CI 0.92-0.96) for 18F-FDG PET, while for deep learning, these values were 0.96 (95% CI 0.94-0.97) and 0.97 (95% CI 0.96-0.99), respectively. Meta-regression identified heterogeneity arising from study quality stratification, algorithm types, and validation strategies.</p><p><strong>Conclusions: </strong>Both AI-assisted 18F-FDG PET and sMRI exhibit high diagnostic accuracy in AD, with 18F-FDG PET demonstrating superior overall diagnostic performance compared to sMRI.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e76981"},"PeriodicalIF":4.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12507341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145253046","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}
Pricilia Tanoto, Hannah En Ye, Seyed Ehsan Saffari, Yi Jin Leow, Ashwati Vipin, Faith Phemie Hui En Lee, Smriti Ghildiyal, Shan Yao Liew, Adnan Azam Mohammed, Gurveen Kaur Sandhu, Kiirtaara Aravindhan, Gursimar Bhalla, Rasyiqah Binte Shaik Mohamed Salim, Nagaendran Kandiah
{"title":"Detection of Vascular Mild Cognitive Impairment in Southeast Asia Using the Visual Cognitive Assessment Test: Machine Learning Analysis From the BIOCIS (Biomarkers and Cognition Study, Singapore).","authors":"Pricilia Tanoto, Hannah En Ye, Seyed Ehsan Saffari, Yi Jin Leow, Ashwati Vipin, Faith Phemie Hui En Lee, Smriti Ghildiyal, Shan Yao Liew, Adnan Azam Mohammed, Gurveen Kaur Sandhu, Kiirtaara Aravindhan, Gursimar Bhalla, Rasyiqah Binte Shaik Mohamed Salim, Nagaendran Kandiah","doi":"10.2196/76847","DOIUrl":"10.2196/76847","url":null,"abstract":"<p><strong>Background: </strong>Vascular mild cognitive impairment (VMCI) is a significant global health concern, particularly in Asia. The visual cognitive assessment test (VCAT) has shown promise as a language-neutral screening tool for cognitive impairment.</p><p><strong>Objective: </strong>This study aims to assess the effectiveness of the VCAT in detecting VMCI and compare its diagnostic performance with the widely used and validated Montreal Cognitive Assessment (MoCA).</p><p><strong>Methods: </strong>Cross-sectional data from 524 community-dwelling participants were analyzed from the BIOCIS (Biomarkers and Cognition Study, Singapore) and classified into cognitively unimpaired, non-VMCI, and VMCI groups. The participants underwent neuropsychological assessments and 3-T magnetic resonance imaging. The random forest technique and multivariable logistic regression were applied to assess the discriminative properties of the tests.</p><p><strong>Results: </strong>Participants with VMCI exhibited significantly lower performance across various neuropsychological tests (P<.001) and higher rates of vascular risk factors (P<.001). At a cutoff of 27, the VCAT achieved near-perfect accuracy in discriminating the VMCI group from the cognitively unimpaired group (area under the receiver operating characteristic curve=1; sensitivity=1; specificity=0.991). For differentiating the VMCI group from the non-VMCI group, both the VCAT and the MoCA showed optimal performance at a cutoff of 25 (area under the receiver operating characteristic curve=1.00; sensitivity=1.00; specificity=1.00).</p><p><strong>Conclusions: </strong>The VCAT could be a valuable tool for detecting VMCI, particularly in diverse, multilingual populations. Its comparable or even superior performance to the MoCA, combined with its language-neutral design, positions the VCAT as a strong addition to cognitive assessment toolkits for VMCI. However, the complex nature of cognitive processing in VMCI suggests that a multifaceted approach that integrates both visual and verbal assessments may ultimately offer the most comprehensive evaluation.</p><p><strong>International registered report identifier (irrid): </strong>RR2-10.14283/jpad.2024.89.</p>","PeriodicalId":36245,"journal":{"name":"JMIR Aging","volume":"8 ","pages":"e76847"},"PeriodicalIF":4.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12547338/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145253039","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}