JMIR Formative Research最新文献

{"title":"Multidomain Behavioral Change Digital Coaching for Chronic Disease Management in Patients With Type 2 Diabetes: Framework Development and Preliminary Evaluation.","authors":"Konstantina Kostopoulou, Danae Lekka, Aristodemos Pnevmatikakis, Nelina Angelova, Panagiotis Stafylas, Stefanos Tamouridis, Alexandra Bargiota, Sofoklis Kyriazakos","doi":"10.2196/73807","DOIUrl":"https://doi.org/10.2196/73807","url":null,"abstract":"<p><strong>Background: </strong>Unhealthy lifestyle behaviors have been identified as a major cause of numerous health issues, with a steady global increase in their prevalence. Addressing this challenge requires comprehensive behavioral changes to promote the adoption of a sustainable healthier lifestyle. However, despite the prevalent need, cost-effective and successful digital coaching for health-related behavior change remains scarce.</p><p><strong>Objective: </strong>This study aimed to present a holistic framework for designing, modeling, and executing behavior change strategies through a multiagent reasoning system that selected optimal digital coaching techniques based on individual assessments and integrated data-driven decision-making.</p><p><strong>Methods: </strong>Behavioral change theories have been explored to design a multiagent system aimed at achieving sustainable lifestyle changes. This system selected behavior change techniques based on individual user assessments, prioritizing those with the strongest impact on key behavioral components. The framework incorporated evidence-based practices stemming from behavioral change science and integrated them into Healthentia's behavioral change coaching scheme. Healthentia, a certified software as a medical device, implemented this framework in its non-medical modules that aim for lifestyle behavioral change and wellbeing specifically for chronic disease management, serving as an eHealth solution that advances decentralized care by enabling remote monitoring, data-driven content selection, and personalized digital coaching that adjusts to patient progress and engagement patterns.</p><p><strong>Results: </strong>This study explored the application of the Healthentia behavioral change coaching scheme in patients with type 2 diabetes. Behavioral attributes have been evaluated in 9 patients, yielding notable results in terms of fasting glucose dropping by an average of -17.3 mg/dL (Cohen d=1.5; P=.002), further underscored by a narrow 95% CI (-26.1 to -8.43), and in terms of weight and BMI, with mean reductions of -2.89 kg and -1.05 kg/m², respectively. These changes yielded large effect sizes (Cohen d approximately 1.05) and were statistically significant (P=.01). The positive outcomes were at least partly attributed to the personalized delivery of content, 71.66% (1125/1570) of which was well received by the patients.</p><p><strong>Conclusions: </strong>Our study of this multiagent system, which was tested through simulated patient behavior and preliminary, limited behavior observations of patients with type 2 diabetes, promises improved health outcomes using personalized digital coaching strategies. Future directions include optimizing the multiagent selection process; further exploring the type 2 diabetes program; conducting an in-depth evaluation of its results, including glycated hemoglobin measurements; and expanding its applications to other chronic conditions.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e73807"},"PeriodicalIF":2.0,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600479","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}

{"title":"A Web-Based Well-Being and Resilience Intervention for Family Members and Friends Supporting a Loved One Using Alcohol and Other Drugs: Mixed Methods Pilot Study.","authors":"Steph Kershaw, Jessica Deng, Madeleine Keaveny, Bronte Speirs, Anna Grager, Dara Sampson, Kate Ross, Nicola Newton, Maree Teeson, Frances Kay-Lambkin, Cath Chapman","doi":"10.2196/72425","DOIUrl":"10.2196/72425","url":null,"abstract":"<p><strong>Background: </strong>Despite the known psychosocial challenges associated with supporting a loved one using alcohol and other drugs (AOD), there is a scarcity of mental health and well-being interventions for affected friends and family members (AFFMs). Stigma has also been shown to discourage help-seeking among AFFMs. Web-based interventions may facilitate help-seeking by ensuring privacy and anonymity.</p><p><strong>Objective: </strong>This pilot study examines the usability, acceptability, and feasibility of the Family and Friend Support Program (FFSP), a world-first, evidence-based web-based resilience and well-being program designed with, and for, people caring for someone using AOD. This study also examined AFFM's experiences of caring for a loved one using AOD and their help-seeking behaviors and barriers.</p><p><strong>Methods: </strong>In 2021 (November-December), participants across Australia completed a baseline web-based cross-sectional survey that assessed the impact of caring for a loved one using AOD (adapted Short Questionnaire for Family Members-Affected by Addiction), and distress levels (Kessler Psychological Distress Scale [K-10]). Following baseline, participants were invited to interact with the FFSP over 10 weeks. Postprogram and follow-up surveys (10 and 14 wk postbaseline, respectively) and semistructured interviews assessed the usability and acceptability of the program, as well as help-seeking experiences and barriers.</p><p><strong>Results: </strong>Baseline surveys were completed by 131 AFFMs, with 37% (n=49) completing the postprogram survey and 24% (n=32) completing the follow-up survey. A total of 5 participants took part in individual semistructured interviews at postprogram. On average, K-10 scores fell in the moderate to severe range at baseline (mean 28.4, SD 8.6). At postprogram, the majority of participants (n=27, 55.1%) reported that they did not seek help to cope with or manage their role supporting their loved one and the most common endorsed barrier was cost (n=11, 28.6%). Overall, participants found the FFSP easy to use and provided them with relevant, helpful, and validating information. The majority (n=35, 71.5%) of participants said they would be likely to recommend the FFSP to a person supporting a loved one using AOD. Qualitative responses highlighted the need for free, accessible support for AFFMs such as the FFSP. Limitations included low program engagement and high attrition.</p><p><strong>Conclusions: </strong>Overall, the FFSP appears to be a promising mental health intervention for AFFMs. This study builds on existing research finding high levels of distress among AFFMs, while highlighting the ongoing barriers to help-seeking. Limitations and future directions for refinements and future efficacy evaluation of the FFSP are discussed including ways to address attrition and increase engagement.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e72425"},"PeriodicalIF":2.0,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12266297/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144600478","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":"Validation of The Umbrella Collaboration for Tertiary Evidence Synthesis in Geriatrics: Mixed Methods Study.","authors":"Beltran Carrillo, Marta Rubinos-Cuadrado, Jazmin Parellada, Alejandra Palacios, Beltran Carrillo-Rubinos, Fernando Canillas, Juan José Baztán Cortés, Javier Gómez-Pavón","doi":"10.2196/75215","DOIUrl":"10.2196/75215","url":null,"abstract":"<p><strong>Background: </strong>The synthesis of evidence in health care is essential for informed decision-making and policy development. This study aims to validate The Umbrella Collaboration (TU), an innovative, semiautomated tertiary evidence synthesis methodology, by comparing it with traditional umbrella reviews (TURs), which are currently the gold standard.</p><p><strong>Objective: </strong>The primary objective of this study is to evaluate whether TU, an artificial intelligence-assisted, software-driven system for tertiary evidence synthesis, can achieve effectiveness comparable to that of TURs, while offering a more timely, efficient, and comprehensive approach.</p><p><strong>Methods: </strong>This comparative study evaluated TU against TURs across 8 matched projects in geriatrics. For each selected TUR, a parallel TU project was conducted using the same research question. Outcomes of interest (OoIs), effect sizes, certainty ratings, and execution times were systematically compared. Effect sizes were assessed both quantitatively, by transforming TUR metrics to Cohen d and correlating them with TU's RTU metric, and qualitatively, through categorical classifications (trivial, small, moderate, and large). Certainty levels were compared by mapping Grading of Recommendations Assessment, Development, and Evaluation (GRADE) ratings and TU's sentiment analysis scores onto a common 0-1 scale. Execution time was measured precisely in TU, while TUR durations were estimated from literature benchmarks. Statistical analyses included chi-square tests and Spearman correlations.</p><p><strong>Results: </strong>Eight TURs in geriatrics were matched with parallel projects using TU. TU replicated 73 of the 86 (85%) OoIs identified by TURs and reported an additional 337 OoIs, representing a 4.77-fold increase in outcome identification. In the comparison of effect size classifications, full concordance was observed in 24 of the 48 (50%) cases, and consistent concordance (full plus 1-level deviation) in 45 of the 48 (94%) cases, with a moderate strength of association (Cramér V=0.339). The correlation of transformed certainty values between TU and GRADE yielded a statistically significant Spearman coefficient (ρ=0.446; P=.02). The average execution time per TU project was 4 hours and 46 minutes, compared with estimated durations of 6-12 months for TURs.</p><p><strong>Conclusions: </strong>The TU demonstrated high concordance with TURs, replicating 73 of the 86 (85%) outcomes identified by TURs and identifying nearly 5 times as many additional outcomes. The experimental effect size metric (RTU) showed moderate agreement with conventional measures, and the certainty ratings derived from sentiment analysis correlated acceptably with GRADE-based assessments. While further validation is needed, TU appears to be a valid and efficient approach for tertiary evidence synthesis, offering a scalable and time-efficient alternative when rapid results are required.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e75215"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12262930/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591210","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":"Assessment of Recommendations Provided to Athletes Regarding Sleep Education by GPT-4o and Google Gemini: Comparative Evaluation Study.","authors":"Lukas Masur, Matthew Driller, Haresh Suppiah, Manuel Matzka, Billy Sperlich, Peter Düking","doi":"10.2196/71358","DOIUrl":"https://doi.org/10.2196/71358","url":null,"abstract":"<p><strong>Background: </strong>Inadequate sleep is prevalent among athletes, affecting adaptation to training and performance. While education on factors influencing sleep can improve sleep behaviors, large language models (LLMs) may offer a scalable approach to provide sleep education to athletes.</p><p><strong>Objective: </strong>This study aims (1) to investigate the quality of sleep recommendations generated by publicly available LLMs, as evaluated by experienced raters, and (2) to determine whether evaluation results vary with information input granularity.</p><p><strong>Methods: </strong>Two prompts with differing information input granularity (low and high) were created for 2 use cases and inserted into ChatGPT-4o (GPT-4o) and Google Gemini, resulting in 8 different recommendations. Experienced raters (n=13) evaluated the recommendations on a 1-5 Likert scale, based on 10 sleep criteria derived from recent literature. A Friedman test with Bonferroni correction was performed to test for significant differences in all rated items between the training plans. Significance level was set to P<.05. Fleiss κ was calculated to assess interrater reliability.</p><p><strong>Results: </strong>The overall interrater reliability using Fleiss κ indicated a fair agreement of 0.280 (range between 0.183 and 0.296). The highest summary rating was achieved by GPT-4o using high input information granularity, with 8 ratings >3 (tendency toward good), 3 ratings equal to 3 (neutral), and 2 ratings <3 (tendency toward bad). GPT-4o outperformed Google Gemini in 9 of 10 criteria (P<.001 to P=.04). Recommendations generated with high input granularity received significantly higher ratings than those with low granularity across both LLMs and use cases (P<.001 to P=.049). High input granularity leads to significantly higher ratings in items pertaining to the used scientific sources (P<.001), irrespective of the analyzed LLM.</p><p><strong>Conclusions: </strong>Both LLMs exhibit limitations, neglecting vital criteria of sleep education. Sleep recommendations by GPT-4o and Google Gemini were evaluated as suboptimal, with GPT-4o achieving higher overall ratings. However, both LLMs demonstrated improved recommendations with higher information input granularity, emphasizing the need for specificity and a thorough review of outputs to securely implement artificial intelligence technologies into sleep education.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e71358"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591208","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}

{"title":"Vibrotactile Feedback Strategies for Trunk-Stabilizing Exercises in a Home-Based Scenario: Qualitative Interview Study Among Physiotherapists.","authors":"Kaya Holzmeyer, Lisa-Marie Lüneburg, Luca Oppici, Philipp Flößel, Doris Lachmann, Jens Krzywinski, Susanne Narciss","doi":"10.2196/62903","DOIUrl":"10.2196/62903","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Physiotherapy treatments frequently incorporate a combination of hands-on, therapist-led exercises and hands-off, home-based exercises, whereby patients perform exercises independently. A key challenge in home-based rehabilitation is providing patients with effective feedback to guide their movements. A range of strategies is being reviewed to address this issue and a starting point for developing effective and implementable strategies to gather feedback requirements from the end users is also being considered.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to derive requirements for designing a vibrotactile feedback strategy for a wearable device for physiotherapy home exercises. To achieve this, it is essential to consider the principles of feedback design as set forth by the field of instructional psychology and to involve physiotherapists in the process.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The feedback behavior of 9 physical therapists was observed during a staged training scenario. Guided interviews were conducted to explore their recommendations for a vibrotactile feedback system. Observational data and interviews were analyzed using a combined deductive and inductive category system. For each exercise-specific motion pattern, it was recorded whether feedback was provided. Instances of feedback were systematically coded according to feedback modality, timing, and content; haptic feedback was additionally categorized by localization. Interview statements referring to the use of vibrotactile feedback were categorized by modality, task requirements, localization, time, content, frequency, function, and individualization. Quantitative data from observations were evaluated using frequency distributions, and qualitative interview data were analyzed using content structuring content analysis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;On average, 50.2% (SD 13.4%) of the observed feedback content provided by each therapist consisted of the presentation of correct exercise execution. A smaller proportion was exclusively confirmatory feedback or the additional provision of elaborated information. Therapists provided feedback in 57.3% (SD 16.3%) of the movement repetitions, on average, while no feedback was given in 42.7% (SD 16.3%) of the repetitions. The interview data supported a reduction in feedback. Regarding feedback timing, 70.8% (SD 13.1%) of the feedback observations were given concurrently with the task across therapists; the proportion of feedback given after the exercise execution was smaller. On average, across therapists, 51.9% (SD 12.1%) of the feedback was auditory, and a further proportion was multimodal with an auditory component. Regarding feedback localization, haptic feedback was often given proximal to the trunk, in the knee and foot region. Frequent combinations of the categories were auditory, simple confirmatory feedback, often given when terminal, or the presentation of the correct exercise execution give","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e62903"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12262103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591211","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":"Online Tailored Decision Aid for Maternal Pertussis Vaccination in a Randomized Controlled Trial: Process Evaluation Study.","authors":"Charlotte Anraad, Pepijn van Empelen, Robert Ac Ruiter, Hilde M van Keulen","doi":"10.2196/50709","DOIUrl":"https://doi.org/10.2196/50709","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;To promote informed decision-making and maternal pertussis vaccination (MPV) uptake, we systematically developed an interactive, web-based decision aid for pregnant users. Intervention reach (the percentage of participants in the intervention group who used the intervention), use (how much and how long those participants used the intervention), and acceptability (how positively they evaluated the intervention) are essential for it to be effective and should be reported to assess which intervention components may have been effective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This is a process evaluation aiming to evaluate (1) the reach and (2) the use, and (3) the acceptability of the intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We analyzed the reach and use of the intervention among participants in the intervention group of a randomized controlled trial (RCT) that assessed the effects of an online tailored decision aid in the form of a web app. Participants were recruited via social media and midwifery clinics and invited via email to use the intervention at 18 weeks of pregnancy. Reach was measured objectively by assessing the number of participants who visited the intervention at least once. Use of the intervention was logged and included time spent on the decision aid, the number of times clicked, pages visited, and answers given in interactive components. Data from the baseline survey (at &lt;18 wk of pregnancy) were used to measure sociodemographics, informed decision-making, MPV uptake, and determinants of uptake. A posttest survey (20-22 weeks of pregnancy) was used to evaluate the acceptability of the decision aid. We report the findings descriptively and assess baseline differences between those who used versus those who did not use the intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of the 586 participants in the intervention group, 463 (79%) reached the home page of the intervention. Intervention reach appeared higher among those in their first pregnancy (8.35% difference, P=.11), those recruited via their midwife rather than via social media (10.56% difference, P=.04), and those who had completed a higher educational level (7.35% difference, P=.06). On average, participants spent 4.25 (SD 4.39) minutes on the decision aid. Most participants used the decision aid once (56.2% of those who reached it, n=260) or twice (26.6%, n=123). The average number of clicks was 27.24 (SD 25.08) and varied widely. Regarding acceptability, participants evaluated the decision aid positively with an overall grade of 8.0 out of 10 (SD 1.01). In total, 38.9% (180/463) of participants who used the intervention indicated that the decision aid helped them with their MPV decision-making.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The reach of the decision aid was successful with 79%, and participants were very positive about the decision aid. The use of the intervention (eg, time spent on the intervention) leaves room for improvement and should be","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e50709"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591209","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}

{"title":"AI in Qualitative Health Research Appraisal: Comparative Study.","authors":"August Landerholm","doi":"10.2196/72815","DOIUrl":"10.2196/72815","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Qualitative research appraisal is crucial for ensuring credible findings but faces challenges due to human variability. Artificial intelligence (AI) models have the potential to enhance the efficiency and consistency of qualitative research assessments.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to evaluate the performance of 5 AI models (GPT-3.5, Claude 3.5, Sonar Huge, GPT-4, and Claude 3 Opus) in assessing the quality of qualitative research using 3 standardized tools: Critical Appraisal Skills Programme (CASP), Joanna Briggs Institute (JBI) checklist, and Evaluative Tools for Qualitative Studies (ETQS).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;AI-generated assessments of 3 peer-reviewed qualitative papers in health and physical activity-related research were analyzed. The study examined systematic affirmation bias, interrater reliability, and tool-dependent disagreements across the AI models. Sensitivity analysis was conducted to evaluate the impact of excluding specific models on agreement levels.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Results revealed a systematic affirmation bias across all AI models, with \"Yes\" rates ranging from 75.9% (145/191; Claude 3 Opus) to 85.4% (164/192; Claude 3.5). GPT-4 diverged significantly, showing lower agreement (\"Yes\": 115/192, 59.9%) and higher uncertainty (\"Cannot tell\": 69/192, 35.9%). Proprietary models (GPT-3.5 and Claude 3.5) demonstrated near-perfect alignment (Cramer V=0.891; P&lt;.001), while open-source models showed greater variability. Interrater reliability varied by assessment tool, with CASP achieving the highest baseline consensus (Krippendorff α=0.653), followed by JBI (α=0.477), and ETQS scoring lowest (α=0.376). Sensitivity analysis revealed that excluding GPT-4 increased CASP agreement by 20% (α=0.784), while removing Sonar Huge improved JBI agreement by 18% (α=0.561). ETQS showed marginal improvements when excluding GPT-4 or Claude 3 Opus (+9%, α=0.409). Tool-dependent disagreements were evident, particularly in ETQS criteria, highlighting AI's current limitations in contextual interpretation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The findings demonstrate that AI models exhibit both promise and limitations as evaluators of qualitative research quality. While they enhance efficiency, AI models struggle with reaching consensus in areas requiring nuanced interpretation, particularly for contextual criteria. The study underscores the importance of hybrid frameworks that integrate AI scalability with human oversight, especially for contextual judgment. Future research should prioritize developing AI training protocols that emphasize qualitative epistemology, benchmarking AI performance against expert panels to validate accuracy thresholds, and establishing ethical guidelines for disclosing AI's role in systematic reviews. As qualitative methodologies evolve alongside AI capabilities, the path forward lies in collaborative human-AI workflows that leverage AI's efficiency w","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e72815"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12263093/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144591207","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":"User-Driven Development of a Digital Behavioral Intervention for Chronic Pain: Multimethod Multiphase Study.","authors":"Afra Selma Taygar, Sara Laureen Bartels, Rocío de la Vega, Ida Flink, Linnéa Engman, Suzanne Petersson, Sophie I Johnsson, Katja Boersma, Lance M McCracken, Rikard K Wicksell","doi":"10.2196/74064","DOIUrl":"https://doi.org/10.2196/74064","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Recent research shows that chronic pain affects 27% of the adult population. For many, pain significantly impairs quality of life and everyday functioning. Behavioral interventions have shown utility, but access remains limited. Digital health solutions can increase reach, but there is a need for user-friendly, feasible, and evidence-based digital interventions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to clarify how a digital behavioral intervention for people with chronic pain can be developed through a user-centered approach to address the needs and preferences of the target population.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This study used a multimethod approach involving end users, namely, patients with chronic pain and therapists, to develop prototypes for a digital behavioral intervention across 3 phases. In the preparation phase (phase 0), fictional patient personas (n=3) were created to represent the diversity of the target population while emphasizing transdiagnostic features across people with chronic pain. In the design phase (phase 1), qualitative data from focus groups with patients (n=5; aged 37-51 years; 4/5, 80% women; 2/5, 40% diagnosed with Ehlers-Danlos syndrome; 3/5, 60% either undiagnosed or uncertain about their diagnosis) and therapists (n=12 licensed psychologists; aged 29-64 years; 9/12, 75% women) were collected to explore end-user preferences for the intervention design and content. In the testing phase (phase 2), the initial full prototype of the digital intervention was piloted with patients (n=11; aged 36-58 years; 9/11, 82% women; with diverse diagnoses, including migraine, arthritis, fibromyalgia, complex regional pain syndrome, hypermobile Ehlers-Danlos syndrome, herniated disc, chronic fatigue syndrome, and 1/11, 9% cases of undiagnosed pain) and therapists (n=3 licensed psychologists; aged 36-58 y; 3/3, 100% women). The Consolidated Framework for Implementation Research was used to structure analyses of end-user feedback.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;On the basis of end-user input, a 6-week digital behavioral intervention for chronic pain was created. Focus groups highlighted the importance of accessibility and adaptability of the digital intervention, emphasizing the need for tailored content, flexibility (eg, contact with the therapist via asynchronous messaging, telephone, or video calls), and user-friendly design (eg, easy navigation between modules, short microsessions, and visualizations). Average weekly ratings (scale from 1=not at all to 7=very much) by patients during pilot-testing indicated that the intervention was helpful (mean range 4.27-5.45, SD range 1.20-2.20), enjoyable (mean range 3.81-4.81, SD range 1.12-2.08), and understandable (mean range 4.45-6, SD range 1.30-1.86), suggesting initial acceptability and usability of the intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The results illustrated the utility of the patient personas when preparing, of the f","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e74064"},"PeriodicalIF":2.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144583915","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}

{"title":"Association of a Brief Computerized Cognitive Assessment With Cholinergic Neurotransmission: Assessment Validation Study.","authors":"Mouna Attarha, Ana De Figueiredo Pelegrino, Lydia Ouellet, Paule-Joanne Toussaint, Sarah-Jane Grant, Thomas Van Vleet, Etienne de Villers-Sidani","doi":"10.2196/68374","DOIUrl":"10.2196/68374","url":null,"abstract":"<p><strong>Background: </strong>Computerized cognitive assessments are most often validated against standard neuropsychological measures with limited validation against biological indices of brain health.</p><p><strong>Objective: </strong>This study aimed to evaluate whether a self-administered computerized cognitive assessment is associated with cholinergic neurotransmission using the vesicular acetylcholine transporter ligand [18F]fluoroethoxybenzovesamicol (FEOBV) and positron emission tomography (PET).</p><p><strong>Methods: </strong>In a retrospective analysis, we report baseline data from the Improving Neurological Health in Aging via Neuroplasticity-Based Computerized Exercise (INHANCE) trial. This study provides normative data for healthy older adults aged 65 years and above. We evaluate the validity of the Double Decision cognitive assessment (from the BrainHQ assessment platform) by examining its association with tracer binding in the anterior cingulate cortex, as measured by FEOBV-PET. We also assess concurrent validity with neuropsychological performance using standardized measures of executive function and global cognition.</p><p><strong>Results: </strong>The intent-to-treat population from the INHANCE trial analyzed in this study included 92 healthy adults with a mean age of 71.9 (SD 4.86, range 65-83) years, the majority of whom were female (61/92, 66%), with an average of 16.45 (SD 3.40, range 9-27) years of education. The Double Decision assessment is associated with FEOBV binding in the anterior cingulate cortex, explaining 8% of the variance, and was associated with neuropsychological performance measures. The assessment was sensitive to age and was not influenced by education level or gender. Psychometric properties supported its usability and the assessment showed an average completion time of 3 (SD 1.12) minutes.</p><p><strong>Conclusions: </strong>We present the first brief, self-administered computerized cognitive assessment associated with cholinergic network health. This tool is scalable and accessible to individuals with an internet-connected device, offering a practical and cost-efficient approach to cognitive screening. The findings provide valuable insights into brain health, particularly for early detection of cognitive decline, and hold significant potential for broad applications across both clinical and nonclinical contexts.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e68374"},"PeriodicalIF":2.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12257569/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144575451","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":"Co-Design of a Health Screening Program Fact Sheet by People Experiencing Homelessness and ChatGPT: Focus Group Study.","authors":"Nóra Radó, Orsolya Németh, Sándor Békási","doi":"10.2196/68316","DOIUrl":"10.2196/68316","url":null,"abstract":"<p><strong>Background: </strong>People experiencing homelessness have worse oral health outcomes and a notable health informational asymmetry compared to the general population. Screening programs present a viable option for this population; however, barriers to access, such as lower levels of health literacy, lack of information, and mistrust, narrow their chances to participate in such programs.</p><p><strong>Objective: </strong>The aim of this study is to investigate the applicability of generative artificial intelligence (AI) in designing a homeless health screening program fact sheet with experts by experience using co-design principles.</p><p><strong>Methods: </strong>Six fact sheet text variants were created by the open-access version of ChatGPT 3.5 for an oral cancer screening program targeting people experiencing homelessness in Budapest, Hungary. Clients of homeless social services (N=23) were invited to a short questionnaire survey and 3 semistructured focus group discussions between May and July 2024. General opinions regarding generative AI technology and direct feedback on the text variants were obtained. Additionally, a standardized readability assessment of the text variants was completed via the Sydney Health Literacy Lab Editor.</p><p><strong>Results: </strong>Almost two-thirds of participants (17/23) stated that they had previously heard about AI; however, their self-assessment regarding the extent of their knowledge resulted in an average of 2.38 (n=16) on a 5-point Likert scale. During the first focus group discussion, all 6 variants received a high score (between 4.63 and 4.92 on a 5-point Likert scale). In the next sessions, participants remained positive when the pool was narrowed to 4 versions, although they scored the texts lower. During open discussions, text variants were considered understandable, while difficulties with medical expressions, lengthiness of sentences, and references to a stereotypical homeless subgroup (rough sleepers) were also reported. The health literacy editor showed that most AI-generated text variants were difficult to read and too complex for the target group.</p><p><strong>Conclusions: </strong>The co-design process revealed that focus group participants actively wanted to shape the fact sheet drafts. They shared their insights on how to make the text variants more appealing for the target audience. Moreover, the involvement of generative AI technology revealed that the participants have heard about the concept of AI and text generation as a potential function, and they have not rejected its use in health care settings.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e68316"},"PeriodicalIF":2.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12248257/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144564802","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}