TY - JOUR AU - Newton, J. Terry AU - Shah, Nilesh AU - Lewis, Katherine AU - Zocchi, S. Mark AU - Bixler, R. Felicia AU - Etingen, Bella AU - Lipschitz, M. Jessica AU - Robinson, A. Stephanie AU - Hogan, P. Timothy AU - Shimada, L. Stephanie PY - 2025/6/6 TI - Developing Infrastructure to Realize the Value of Patient-Generated Health Data in a Large Integrated Health Care System: The Veterans Health Administration Experience JO - J Med Internet Res SP - e70755 VL - 27 KW - patient-generated health data KW - Veterans Health Administration KW - mobile health apps KW - health data interoperability KW - clinical decision-making UR - https://www.jmir.org/2025/1/e70755 UR - http://dx.doi.org/10.2196/70755 ID - info:doi/10.2196/70755 ER - TY - JOUR AU - Nagino, Ken AU - Akasaki, Yasutsugu AU - Fuse, Nobuo AU - Ogishima, Soichi AU - Shimizu, Atsushi AU - Uruno, Akira AU - Sutoh, Yoichi AU - Otsuka-Yamasaki, Yayoi AU - Nagami, Fuji AU - Seita, Jun AU - Nakamura, Tomohiro AU - Nagaie, Satoshi AU - Taira, Makiko AU - Kobayashi, Tomoko AU - Shimizu, Ritsuko AU - Hozawa, Atsushi AU - Kuriyama, Shinichi AU - Eguchi, Atsuko AU - Midorikawa-Inomata, Akie AU - Nakamura, Masahiro AU - Murakami, Akira AU - Nakao, Shintaro AU - Inomata, Takenori PY - 2025/5/12 TI - Integration of Digital Phenotyping and Genomics for Dry Eye Disease: Protocol for a Prospective Cohort Study JO - JMIR Res Protoc SP - e67862 VL - 14 KW - dry eye syndrome KW - dry eye disease KW - mobile health KW - smartphone KW - biobank KW - ocular surface KW - digital health KW - genome-wide association study N2 - Background: Dry eye disease (DED) is a common ocular condition with diverse and heterogeneous symptoms. Current treatment standards of DED include the post facto management of associated symptoms through topical eye drops. However, there is a need for predictive, preventive, personalized, and participatory medicine. The DryEyeRhythm mobile health app enables real-time data collection on environmental, lifestyle, host, and digital factors in a patient?s daily environment. Combining these data with genetic information from biobanks could enhance our understanding of individual variations and facilitate the development of personalized treatment strategies for DED. Objective: This study aims to integrate digital data from the DryEyeRhythm smartphone app with the Tohoku Medical Megabank database to create a comprehensive database that elucidates the interplay between multifactorial factors and the onset and progression of DED. Methods: This prospective observational cohort study will include 1200 participants for the discovery stage and 1000 participants for the replication stage, all of whom have data available in the Tohoku Medical Megabank database. Participants will be recruited from the Community Support Center of Sendai, Miyagi Prefecture, Japan. Participant enrollment for the discovery stage was conducted from August 1, 2021, to June 30, 2022, and the replication stage will be conducted from August 31, 2024, to March 31, 2026. Participants will provide demographic data, medical history, lifestyle information, DED symptoms, and maximum blink interval measurements at baseline and after 30 days using the DryEyeRhythm smartphone app. Upon scanning a registration code, each participant?s cohort ID from the Tohoku Medical Megabank database will be linked to their smartphone app, enabling data integration between the Tohoku Medical Megabank and DryEyeRhythm database. The primary outcome will assess the association between genetic polymorphisms and DED using a genome-wide association study. Secondary outcomes will explore associations between DED and various factors, including sociodemographic characteristics, lifestyle habits, medical history, biospecimen analyses (eg, blood and urine), and physiological measurements (eg, height, weight, and eye examination results). Associations will be evaluated using logistic regression analysis, adjusting for potential confounding factors. Results: The discovery stage of participant enrollment was conducted from August 1, 2021, to June 30, 2022. The replication stage will take place from August 31, 2024, to March 31, 2026. Data analysis is expected to be completed by September 2026, with results reported by March 2027. Conclusions: This study highlights the potential of smartphone apps in advancing biobank research and deepening the understanding of multifactorial DED, paving the way for personalized treatment strategies in the future. International Registered Report Identifier (IRRID): DERR1-10.2196/67862 UR - https://www.researchprotocols.org/2025/1/e67862 UR - http://dx.doi.org/10.2196/67862 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/67862 ER - TY - JOUR AU - Nair, Subjagouri Rakhi Asokkumar AU - Hartung, Matthias AU - Heinisch, Philipp AU - Jaskolski, Janik AU - Starke-Knäusel, Cornelius AU - Veríssimo, Susana AU - Schmidt, Maria David AU - Cimiano, Philipp PY - 2025/4/14 TI - Summarizing Online Patient Conversations Using Generative Language Models: Experimental and Comparative Study JO - JMIR Med Inform SP - e62909 VL - 13 KW - patient experience KW - online communities KW - summarizing KW - large language models N2 - Background: Social media is acknowledged by regulatory bodies (eg, the Food and Drug Administration) as an important source of patient experience data to learn about patients? unmet needs, priorities, and preferences. However, current methods rely either on manual analysis and do not scale, or on automatic processing, yielding mainly quantitative insights. Methods that can automatically summarize texts and yield qualitative insights at scale are missing. Objective: The objective of this study was to evaluate to what extent state-of-the-art large language models can appropriately summarize posts shared by patients in web-based forums and health communities. Specifically, the goal was to compare the performance of different language models and prompting strategies on the task of summarizing documents reflecting the experiences of individual patients. Methods: In our experimental and comparative study, we applied 3 different language models (Flan-T5, Generative Pretrained Transformer [GPT], GPT-3, and GPT-3.5) in combination with various prompting strategies to the task of summarizing posts from patients in online communities. The generated summaries were evaluated with respect to 124 manually created summaries as a ground-truth reference. As evaluation metrics, we used 2 standard metrics from the field of text generation, namely, Recall-Oriented Understudy for Gisting Evaluation (ROUGE) and BERTScore, to compare the automatically generated summaries to the manually created reference summaries. Results: Among the zero-shot prompting?based large language models investigated, GPT-3.5 performed better than the other models with respect to the ROUGE metrics, as well as with respect to BERTScore. While zero-shot prompting seems to be a good prompting strategy, overall GPT-3.5 in combination with directional stimulus prompting in a 3-shot setting had the best results with respect to the aforementioned metrics. A manual investigation of the summarization of the best-performing method showed that the generated summaries were accurate and plausible compared to the manual summaries. Conclusions: Taken together, our results suggest that state-of-the-art pretrained language models are a valuable tool to provide qualitative insights about the patient experience to better understand unmet needs, patient priorities, and how a disease impacts daily functioning and quality of life to inform processes aimed at improving health care delivery and ensure that drug development focuses more on the actual priorities and unmet needs of patients. The key limitations of our work are the small data sample as well as the fact that the manual summaries were created by 1 annotator only. Furthermore, the results hold only for the examined models and prompting strategies, potentially not generalizing to other models and strategies. UR - https://medinform.jmir.org/2025/1/e62909 UR - http://dx.doi.org/10.2196/62909 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/62909 ER - TY - JOUR AU - Zhang, Chunyan AU - Wang, Ting AU - Dong, Caixia AU - Dai, Duwei AU - Zhou, Linyun AU - Li, Zongfang AU - Xu, Songhua PY - 2025/3/5 TI - Exploring Psychological Trends in Populations With Chronic Obstructive Pulmonary Disease During COVID-19 and Beyond: Large-Scale Longitudinal Twitter Mining Study JO - J Med Internet Res SP - e54543 VL - 27 KW - COVID-19 KW - chronic obstructive pulmonary disease (COPD) KW - psychological trends KW - Twitter KW - data mining KW - deep learning N2 - Background: Chronic obstructive pulmonary disease (COPD) ranks among the leading causes of global mortality, and COVID-19 has intensified its challenges. Beyond the evident physical effects, the long-term psychological effects of COVID-19 are not fully understood. Objective: This study aims to unveil the long-term psychological trends and patterns in populations with COPD throughout the COVID-19 pandemic and beyond via large-scale Twitter mining. Methods: A 2-stage deep learning framework was designed in this study. The first stage involved a data retrieval procedure to identify COPD and non-COPD users and to collect their daily tweets. In the second stage, a data mining procedure leveraged various deep learning algorithms to extract demographic characteristics, hashtags, topics, and sentiments from the collected tweets. Based on these data, multiple analytical methods, namely, odds ratio (OR), difference-in-difference, and emotion pattern methods, were used to examine the psychological effects. Results: A cohort of 15,347 COPD users was identified from the data that we collected in the Twitter database, comprising over 2.5 billion tweets, spanning from January 2020 to June 2023. The attentiveness toward COPD was significantly affected by gender, age, and occupation; it was lower in females (OR 0.91, 95% CI 0.87-0.94; P<.001) than in males, higher in adults aged 40 years and older (OR 7.23, 95% CI 6.95-7.52; P<.001) than in those younger than 40 years, and higher in individuals with lower socioeconomic status (OR 1.66, 95% CI 1.60-1.72; P<.001) than in those with higher socioeconomic status. Across the study duration, COPD users showed decreasing concerns for COVID-19 and increasing health-related concerns. After the middle phase of COVID-19 (July 2021), a distinct decrease in sentiments among COPD users contrasted sharply with the upward trend among non-COPD users. Notably, in the post-COVID era (June 2023), COPD users showed reduced levels of joy and trust and increased levels of fear compared to their levels of joy and trust in the middle phase of COVID-19. Moreover, males, older adults, and individuals with lower socioeconomic status showed heightened fear compared to their counterparts. Conclusions: Our data analysis results suggest that populations with COPD experienced heightened mental stress in the post-COVID era. This underscores the importance of developing tailored interventions and support systems that account for diverse population characteristics. UR - https://www.jmir.org/2025/1/e54543 UR - http://dx.doi.org/10.2196/54543 UR - http://www.ncbi.nlm.nih.gov/pubmed/40053739 ID - info:doi/10.2196/54543 ER - TY - JOUR AU - Southwick, Lauren AU - Sharma, Meghana AU - Rai, Sunny AU - Beidas, S. Rinad AU - Mandell, S. David AU - Asch, A. David AU - Curtis, Brenda AU - Guntuku, Chandra Sharath AU - Merchant, M. Raina PY - 2024/12/16 TI - Integrating Patient-Generated Digital Data Into Mental Health Therapy: Mixed Methods Analysis of User Experience JO - JMIR Ment Health SP - e59785 VL - 11 KW - digital data KW - social media KW - psychotherapy KW - latent Dirichlet allocation KW - LDA KW - mobile phone N2 - Background: Therapists and their patients increasingly discuss digital data from social media, smartphone sensors, and other online engagements within the context of psychotherapy. Objective: We examined patients? and mental health therapists? experiences and perceptions following a randomized controlled trial in which they both received regular summaries of patients? digital data (eg, dashboard) to review and discuss in session. The dashboard included data that patients consented to share from their social media posts, phone usage, and online searches. Methods: Following the randomized controlled trial, patient (n=56) and therapist (n=44) participants completed a debriefing survey after their study completion (from December 2021 to January 2022). Participants were asked about their experience receiving a digital data dashboard in psychotherapy via closed- and open-ended questions. We calculated descriptive statistics for closed-ended questions and conducted qualitative coding via NVivo (version 10; Lumivero) and natural language processing using the machine learning tool latent Dirichlet allocation to analyze open-ended questions. Results: Of 100 participants, nearly half (n=48, 49%) described their experience with the dashboard as ?positive,? while the other half noted a ?neutral? experience. Responses to the open-ended questions resulted in three thematic areas (nine subcategories): (1) dashboard experience (positive, neutral or negative, and comfortable); (2) perception of the dashboard?s impact on enhancing therapy (accountability, increased awareness over time, and objectivity); and (3) dashboard refinements (additional sources, tailored content, and privacy). Conclusions: Patients reported that receiving their digital data helped them stay ?accountable,? while therapists indicated that the dashboard helped ?tailor treatment plans.? Patient and therapist surveys provided important feedback on their experience regularly discussing dashboards in psychotherapy. Trial Registration: ClinicalTrials.gov NCT04011540; https://clinicaltrials.gov/study/NCT04011540 UR - https://mental.jmir.org/2024/1/e59785 UR - http://dx.doi.org/10.2196/59785 ID - info:doi/10.2196/59785 ER - TY - JOUR AU - Degen, Isabella AU - Robson Brown, Kate AU - Reeve, J. Henry W. AU - Abdallah, S. Zahraa PY - 2024/11/27 TI - Beyond Expected Patterns in Insulin Needs of People With Type 1 Diabetes: Temporal Analysis of Automated Insulin Delivery Data JO - JMIRx Med SP - e44384 VL - 5 KW - multivariate time series KW - k-means KW - clustering KW - machine learning KW - temporal patterns KW - data-driven KW - OpenAPS KW - open dataset KW - type 1 diabetes KW - insulin needs N2 - Background: Type 1 diabetes (T1D) is a chronic condition in which the body produces too little insulin, a hormone needed to regulate blood glucose. Various factors such as carbohydrates, exercise, and hormones impact insulin needs. Beyond carbohydrates, most factors remain underexplored. Regulating insulin is a complex control task that can go wrong and cause blood glucose levels to fall outside a range that protects people from adverse health effects. Automated insulin delivery (AID) has been shown to maintain blood glucose levels within a narrow range. Beyond clinical outcomes, data from AID systems are little researched; such systems can provide data-driven insights to improve the understanding and treatment of T1D. Objective: The aim is to discover unexpected temporal patterns in insulin needs and to analyze how frequently these occur. Unexpected patterns are situations where increased insulin does not result in lower glucose or where increased carbohydrate intake does not raise glucose levels. Such situations suggest that factors beyond carbohydrates influence insulin needs. Methods: We analyzed time series data on insulin on board (IOB), carbohydrates on board (COB), and interstitial glucose (IG) from 29 participants using the OpenAPS AID system. Pattern frequency in hours, days (grouped via k-means clustering), weekdays, and months were determined by comparing the 95% CI of the mean differences between temporal units. Associations between pattern frequency and demographic variables were examined. Significant differences in IOB, COB, and IG across temporal dichotomies were assessed using Mann-Whitney U tests. Effect sizes and Euclidean distances between variables were calculated. Finally, the forecastability of IOB, COB, and IG for the clustered days was analyzed using Granger causality. Results: On average, 13.5 participants had unexpected patterns and 9.9 had expected patterns. The patterns were more pronounced (d>0.94) when comparing hours of the day and similar days than when comparing days of the week or months (0.3