JMIR Aging最新文献

Background: AI has demonstrated superior diagnostic accuracy compared to medical practitioners, highlighting its growing importance in healthcare. SMART-Pred (Shiny Multi-Algorithm R Tool for Predictive Modeling) is an innovative AI-based application for Alzheimer's disease (AD) prediction using handwriting analysis.

Objective: To develop and evaluate a non-invasive, cost-effective AI tool for early AD detection, addressing the need for accessible and accurate screening methods.

Methods: The study employed Principal Component Analysis (PCA) for dimensionality reduction of handwriting data, followed by training and evaluation of ten diverse AI models, including logistic regression, Naïve Bayes, random forest, AdaBoost, Support Vector Machine (SVM), and neural network. Model performance was assessed using accuracy, sensitivity, specificity, F1-score, and ROC-AUC metrics. The DARWIN dataset, comprising handwriting samples from 174 participants (89 AD patients, 85 healthy controls) was used for validation.

Results: The Neural Network classifier achieved an accuracy of 91% with a 95% CI ranging from 0.79-0.97 and an AUC of 94%, on the test set after identifying the most significant features for AD prediction. These results surpass current clinical diagnostic tools, which typically achieve around 81% accuracy. SMART-Pred's performance aligns with recent AI advancements in AD prediction, such as the Cambridge scientists' AI tool achieving 82% accuracy in identifying AD progression within three years using cognitive tests and MRI scans. The variables "air_time" and "paper_time" consistently emerged as critical predictors for AD across all ten AI models, highlighting their potential importance in early detection and risk assessment. To augment transparency and interpretability, we incorporated the principles of explainable AI, specifically using SHapley Additive exPlanations (SHAP) values, a state-of-the-art method to emphasize the features responsible for our model's efficacy.

Conclusions: SMART-Pred offers non-invasive, cost-effective, and efficient AD prediction, demonstrating the transformative potential of AI in healthcare. While clinical validation is necessary to confirm the practical applicability of the identified key variables, this study contributes to the growing body of research on AI-assisted AD diagnosis and may lead to improved patient outcomes through early detection and intervention.

Clinicaltrial:

Background: First-line management for hip and knee osteoarthritis includes lifestyle treatments, such as exercise and weight loss (if appropriate), whereas joint replacement surgery is recommended only for severe symptoms after these options have been exhausted. However, many people with osteoarthritis hold misconceptions about the condition, leading to lower acceptance of nonsurgical treatments, such as exercise, and the mistaken belief that surgery is their only option. Novel patient education approaches that address these misconceptions are recommended to improve uptake of lifestyle treatments, reduce unnecessary surgery, and improve outcomes for people with osteoarthritis. We developed a 4-week self-directed consumer e-learning course on osteoarthritis management. In a randomized controlled trial, using the course led to immediate and sustained improvements in osteoarthritis knowledge. However, participants' perspectives on the course and an understanding of how it impacted osteoarthritis beliefs, treatment choices, and outcomes were unknown.

Objective: This study aims to explore how an e-learning course for people with hip and knee osteoarthritis may have impacted their osteoarthritis beliefs, treatment choices, and outcomes.

Methods: In this qualitative study, we conducted semistructured individual interviews (N=20) with randomized controlled trial participants with hip or knee osteoarthritis who accessed a 4-week consumer e-learning course on osteoarthritis and its management. Interviews were audio recorded, transcribed verbatim, and thematically analyzed following a framework approach, which was guided by the common sense model of self-regulation.

Results: Four themes were developed from the interviews: (1) participants reshaped their beliefs and attitudes toward osteoarthritis and its management, (2) participants adopted a proactive approach to management, (3) participants developed a more positive mindset, and (4) the course supported learning and shifts in beliefs.

Conclusions: The e-learning course resulted in shifts in participants' beliefs and attitudes toward osteoarthritis and its management, increasing their confidence in living with osteoarthritis and resulting in a more optimistic outlook on the future. The e-learning course is freely available and could be a useful resource for people with osteoarthritis to enhance their understanding of the condition and its management.

Background: The global aging population and the high incidence of falls among this population highlight the need for effective preventive strategies. Home-based exercise programs, such as the Otago protocol, have demonstrated efficacy in reducing fall risk but often face barriers related to user adherence. Mobile health (mHealth) apps offer promising tools to support health promotion and enhance autonomy in older adults.

Objective: This study aims to develop and validate a prototype mobile app, Mais Equilíbrio (More Balance), designed to guide older adults in performing home-based physical exercises adapted from the Otago protocol.

Methods: This methodological study was conducted in two phases: (1) content validation by 22 experts in physical education and physiotherapy using the Suitability Assessment of Materials (SAM) scale, and (2) usability testing with 24 older adults (aged 60 to 80 y), using the System Usability Scale (SUS). An overall score above 70% on the SAM and above 85 on the SUS were considered indicators of high quality and excellent usability, respectively.

Results: The Mais Equilíbrio (More Balance) app was developed based on the Otago protocol and tailored for independent home use. A Content Validity Index above 0.95 was observed for all items. An overall average score of 81.20 (SD 15.78) on the SAM scale was found, classifying the material as "superior." Usability tests with older adults showed an average score of 95.98 (SD 5.58) on the SUS, indicating excellent usability. The highest scores were observed in "ease of use" and "user confidence."

Conclusions: The Mais Equilíbrio (More Balance) app, distinct for digitally adapting the Otago protocol to the Brazilian context and for its dual validation process with experts and older adults, has proven to be a valid and highly usable tool for guiding home-based physical exercise in older adults, with potential to promote fall prevention and autonomy.

Background: Measuring and promoting healthy aging at an individual level remains challenging as promoting healthy longevity requires real-time, personalized tools to assess risk and guide interventions in clinical practice.

Objective: This study aimed to develop and validate a novel Healthy Longevity Index (HLI) for use in primary care settings in older adults.

Methods: Using data from the Taiwan Longitudinal Study on Aging (TLSA; n=4470), we developed a nomogram-based HLI incorporating demographics, lifestyle factors, intrinsic capacity (IC) measures, and chronic conditions to predict 4-, 8-, and 12-year disability- and dementia-free survival (absence of physical disability, dementia, or mortality). The HLI was internally validated in a TLSA subset and externally validated in the Japanese National Institute for Longevity Sciences, Longitudinal Study of Aging (NILS-LSA) cohort (n=1090).

Results: The 12-year HLI nomogram demonstrated robust performance, with C-statistics of 0.79 (bootstrapped 95% CI 0.78-0.80) in the TLSA training cohort and 0.77 (bootstrapped 95% CI 0.75-0.79) in the TLSA validation cohort. External validation in the NILS-LSA yielded a C-statistic of 0.71 (bootstrapped 95% CI 0.66-0.76). The HLI effectively stratified participants into risk tertiles, with the highest-risk group showing only 27.8% probability of 12-year disability- and dementia-free survival compared to 87.8% in the lowest-risk group. Key predictors included age, sex, education, and, particularly, IC impairments in locomotion, visual acuity, and cognition-all assessable during routine primary care consultations.

Conclusions: The HLI provides a practical tool for real-time, personalized assessment of healthy longevity risk in primary care settings. Its design enables providers to deliver person-centered care through targeted interventions and individualized prevention strategies that promote healthy aging across populations, especially in older adults.

Background: Caregivers of frail older adults face substantial challenges, often managing their own health while providing care. To address these issues, we developed the caregiver support model (CSM), a structured approach that uses systematic assessment, personalized intervention planning, and sustained support to address informal family caregivers' diverse and evolving needs and leverage their resources.

Objective: This study aims to evaluate the effectiveness of CSM.

Methods: A blinded cluster randomized controlled trial was conducted across 8 centers providing services for older adults in Hong Kong. The CSM is a social worker-guided intervention that integrates a structured assessment of caregiver needs and resources, personalized service planning, and ongoing monitoring over 6 months. Meanwhile, the control group continued with their usual procedures without a standardized caregiver assessment. Data were collected at baseline, 3 months, and 6 months.

Results: We recruited 565 informal family caregivers (281/565, 49.7% CSM intervention; 284/565, 50.3% standard care control). Both groups improved over time; compared with the control group, the CSM produced greater reductions in caregiver needs, particularly in role conflict, and greater gains in resources, such as health awareness. Improvements were more pronounced at 6 months compared to 3 months, indicating a lasting effect and consolidation of gains. The intervention was particularly effective for caregivers in other relationships (not spouse or child) and those with higher education than spousal caregivers.

Conclusions: These findings highlight the importance of long-term tailored interventions that adapt to the evolving needs of caregivers through systematic assessment. The CSM offers a promising approach to enhancing the well-being of caregivers and managing the complex demands of caregiving, particularly in an aging population.

Background: Global aging presents significant socioeconomic and health challenges, particularly for older adults who face an increased risk of chronic diseases and reduced physical activity levels. Although physical activity is crucial for maintaining health, most older adults do not meet the recommended guidelines. Gamification and mobile health (mHealth) technologies offer innovative solutions to motivate physical activity; however, research focusing on older adults is limited, especially regarding the effectiveness and sustainability of such interventions.

Objective: This study aims to synthesize evidence on the effectiveness of mHealth-based gamified interventions for improving physical activity in older adults.

Methods: This systematic review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses and Meta-Analysis of Observational Studies in Epidemiology guidelines and analyzed studies from PubMed, Embase, Web of Science, CINAHL, Scopus, and Wiley Online Library, covering relevant literature from their inception up to May 2025. The inclusion criteria focused on gamified mHealth interventions for adults aged 60+ years, excluding serious games. Quality assessment was conducted according to the Joanna Briggs Institute standards, with data extracted on study design, gamification elements, and outcomes such as step counts and moderate-to-vigorous physical activity.

Results: Of 2944 studies identified from the database search, 1454 individuals from 8 trials were included. Gamified interventions significantly increased daily step counts and time spent in moderate-to-vigorous physical activity among older adults. Goal setting and rewards were the most frequently used components, and the combined use of mobile and wearable devices offered greater flexibility and accessibility. A classification framework indicated that interventions integrating multiple gamification elements with hybrid technology systems were most effective, particularly when guided by a theoretical basis. However, the heterogeneity in study designs, small sample sizes, and lack of long-term follow-up studies limited the generalizability of the findings.

Conclusions: mHealth-based gamification interventions demonstrate potential for increasing physical activity in older adults. Future interventions should consider employing multifaceted designs combining advanced gamification with hybrid technology systems, while also prioritizing theoretical integration, long-term sustainability, and caregiver involvement to improve sustainability and inclusivity. This review highlights the need for theory-driven, technology-mediated strategies that address the unique health needs of older adults.

[This corrects the article DOI: 10.2196/77140.].

Background: Little is known about how surrogates make end-of-life care choices for patients who lack the ability to make decisions for themselves.

Objective: The study aims (1) to identify key themes that emerged from participants' free-text responses to a large nationally representative vignette survey about surrogate decision-making in end-of-life care and (2) to determine if an advanced artificial intelligence (AI) chatbot could assist us in accurately and efficiently performing qualitative analyses.

Methods: Our dataset included 3931 free-text responses from a nationally representative survey of 6109 individuals. In this qualitative study, we first familiarized ourselves with the free-text responses and hand-coded the first 200 responses until we reached saturation. We then created a codebook, initial themes, subthemes, and illustrative quotes. Subsequently, we prompted ChatGPT-4o to analyze the entire dataset of 3931 responses and identify frequent keywords and generate themes and quotable quotes. We validated responses by comparing the AI's keyword counts to qualitative software (NVivo, Lumivero) counts and cross-validating AI-generated quotes with the original transcripts.

Results: We identified several key themes: surrogates more often chose comfort care for care recipients with dementia, particularly at advanced stages. They also strongly weighed the patients' perceived quality of life and functional status. Many reported making surrogate decisions based on their own lived experiences or values, rather than making decisions aligned with the patients' previously stated wishes. There was no significant difference between the AI and qualitative software's keyword counts. The most frequent keywords included "life" (2051/81,713, 2.51%), "quality" (903/81,713, 1.11%), and dementia (507/81,713, 0.62%). Overall, AI-generated themes closely aligned with aforementioned human-generated themes. Manual coding of the first 200 free-text responses required 4 hours, including codebook development. In contrast, ChatGPT-4o generated themes in <10 seconds using the predefined codebook. However, dataset preparation, output verification, iterative prompting, debugging, and validation required several weeks.

Conclusions: Surrogates often base end-of-life decisions on dementia stage, perceived quality of life, and their own lived experiences, rather than patient preferences. Using an AI chatbot to perform qualitative analysis on free-text responses may help extend the work of qualitatively trained investigators, especially for large datasets such as free-text responses to large surveys.