Journal of Medical Internet Research

Patient narratives can reveal aspects of health that standardized measures miss, yet collecting open-ended responses at population scale remains difficult. We evaluated whether speech-to-text (STT) could enable richer responses in online health surveys without the resource demands of interviews. Across four surveys involving people with post-COVID-19 condition, healthy adults, people who engage in sex work, and older adults, participants could answer open-ended questions by typing or using STT. We compared response length, lexical diversity, stopword proportion, and total unique content words, alongside STT uptake and participant feedback. Quantitative comparisons were made using a mixed-effects model including modality (STT vs typed) as fixed effect and a random intercept per participant. STT uptake varied markedly across populations (0.7-80.0%). Spoken responses were estimated to contain more characters than typed responses in two studies, by 245.0 and 891.8 characters on average (both p<0.001), and contained more unique content words, despite lower lexical diversity and higher stopword proportions. Participants generally valued STT for its convenience and spontaneity, but uptake was constrained by context, privacy, interface design and individual preferences. STT may enable population-scale collection of richer health narratives, provided implementation is tailored to the study population and research context.

Social media language and digital lifestyle behaviours are promoted as scalable signals of population mental health, but predictive models are often evaluated in ways that overstate accuracy. We analysed 20,000 tweets from 72 users, labelled by whether the account belonged to a user identified as depressed, and two synthetic datasets (100,000 and 30,000 records) linking screen time, sleep and social media use with self-reported stress. Under a conventional tweet-level split, a term-weighted logistic regression appeared accurate (area under the receiver operating characteristic curve 0.835), but when whole users were held out its performance fell to near chance (0.595; 95% confidence interval 0.505 to 0.686), because the model largely recognised users and their topics. Depression-associated tweets were more often negative (31.7% versus 24.2%), yet sentiment alone could not identify unseen users (0.539). The two behavioural datasets gave opposite answers: strong discrimination in one (0.926), driven by short sleep, and chance in the other (0.506), so synthetic results reflect how the data were generated. At a population prevalence of 10%, positive predictive values would be 0.10 to 0.30. Digital distress signals should be validated across individuals, on real linked data and at realistic prevalence before informing public health surveillance or prevention.

Background HPV-vaccination prevents HPV-related cancers, but uptake remains suboptimal. In the Netherlands, a catch-up campaign invited 18-27-year-olds for an additional cost-free opportunity to initiate or complete their HPV-vaccination in 2023-2024, which led to 24% of this invited population getting vaccinated. As young adults increasingly seek health information online, understanding online questions, concerns and misinformation in response to the campaign may help improve future vaccination efforts. Supplemental to overall evaluation of the vaccination campaign, we piloted online social listening processes to generate an insight report for Public Health Service (PHS) Amsterdam. Objective This study piloted online social listening processes at the PHS Amsterdam to identify actionable insights into questions, concerns and misinformation surrounding the HPV-vaccination catch-up campaign among young adults. Methods Upon inventory of potential platforms and data sources, a retrospective online social listening analysis was conducted across the platforms Instagram, Facebook, and X, collecting data from PHS, the National Public Health Institute for Public Health and the Environment (RIVM), the Dutch public broadcasting foundation (NOS), and LINDA.meiden sources from January 1, 2023, to June 1, 2024. Publicly available posts, comments, and engagement concerning HPV-vaccination were manually collected, and inductively coded. Themes were assessed for risk, based on expected potential harm and observed reach, and used to develop recommendations. Results A total of 821 posts and 5157 comments were collected and analysed. Ten recurring themes were identified across varying levels of risk. Two themes were classified as high risk: an information gap regarding the effectiveness of HPV-vaccination and concerns about the transparency on HPV-vaccine side effects. Three themes were classified as medium risk: questioning HPV-vaccine effectiveness under certain circumstances, reduced general vaccine trust following COVID-19, and accessibility issues related to vaccination locations and service times. Two themes were classified as neutral risk: questions regarding eligibility criteria for the campaign and calls for broader HIPV-prevention measures. Finally, three low risk themes concerned questions regarding HPV-vaccine brand specifics, campaign choices, and questions about scheduling or rescheduling HPV-appointments. Comments also referred to subsequent information sources, including reliable sources (public health institutes), false narratives and misinformation. Recommendations focused on addressing questions and information gaps (i.e. improving HPV risk perception and providing more detailed HPV-vaccine information), improving communication about HPV-vaccination, and reducing practical barriers to vaccination. Conclusions Manual social listening across selected online sources provided actionable insights into the public discourse during the HPV-vaccination catch-up campaign. Results mostly reflected questions, concerns and information gaps. Although some themes were critical of HPV-vaccination, false narratives and misinformation did not dominate the discourse. Recommendations aim to reduce practical barriers and address information needs. This pilot showed that online social listening can be effectively implemented even with limited resources.

BackgroundPatient education is critical to safe and effective postoperative bariatric surgery care. Large language models (LLMs) may improve access to personalized patient education but evidence regarding direct patient use in clinical settings remains limited. We evaluated BariBot, an LLM-powered educational application for patients undergoing bariatric surgery. MethodsWe conducted a prospective, single-arm mixed-methods feasibility study at a tertiary academic medical center from May 2024 to May 2025. Adult patients undergoing bariatric surgery used BariBot independently on postoperative day 1. The application provided conversational postoperative education and adapted language complexity to participants educational attainment. Outcomes included feasibility, usability, acceptability, perceived trustworthiness, and anticipated future use. Usability was assessed using the System Usability Scale (SUS). Immediately after BariBot use, participants completed a semi-structured qualitative interview assessing acceptability, perceived trustworthiness, and anticipated future use. Interview transcripts underwent thematic analysis. ResultsSixteen participants completed the BariBot use session, SUS assessment, and post-intervention interview. No technical failures prevented application use, and no participant requested early discontinuation. The median SUS score was 91.3 (IQR, 81.3-98.1), consistent with excellent perceived usability. Qualitative analysis showed that participants valued the applications immediacy, structured responses, conversational context, ability to address follow-up questions, judgement-free nature, and future availability between clinical encounters. Trust was strengthened by alignment with prior clinical guidance and perceived institutional association, although participants emphasized the need for transparency, clinician oversight, and use as an adjunct rather than a replacement of clinician guidance. ConclusionsBariBot was feasible to implement and was associated with high perceived usability and acceptability postoperatively after bariatric surgery. Larger, longitudinal, and comparative studies are needed to evaluate safety during unsupervised use and determine whether LLM-based educational applications improve patient understanding, engagement, and clinical outcomes.

Pain assessment remains challenging in clinical practice. Automated pain assessment using artificial intelligence (AI) and facial expression analysis has emerged as a potential approach to support more objective and continuous pain monitoring, particularly for patients who are unable to communicate effectively. However, successful implementation depends on clinician acceptance. We conducted a cross-sectional survey of physicians, advanced practice providers (APPs), and nurses at a tertiary academic medical center to evaluate current pain assessment practices and perceptions of a facial-analysis-based pain assessment system. Eighty-seven eligible clinicians participated. For current assessment practices, clinicians commonly relied on observational indicators of pain, including vital signs (88.5%), physical examination findings (85.1%), and facial expressions (79.3%). Attitudes toward automated pain assessment were generally neutral to positive. Half of respondents agreed that such a system would be useful for monitoring patients over time (50.6%), and many perceived value for nonverbal patients (86.5%), patients with dementia or cognitive impairment (78.4%), and patients with language barriers (62.2%). Most clinicians reported requiring high levels of accuracy before routine use, with nearly 60% requiring at least 90% accuracy. Key concerns included alert fatigue and unequal performance across patient populations. These findings suggest clinicians view automated facial-analysis systems as potentially valuable adjuncts for pain monitoring, particularly in communication-impaired populations, while emphasizing the importance of accuracy, fairness, explainability, and workflow integration during system development and implementation.

Objective: The Alimetry Gut-Brain Wellbeing (AGBW) Survey is a validated 10-item scale developed to assess mental health in patients with chronic gastroduodenal symptoms. While the original scale demonstrated strong psychometric properties overall, as part of an ongoing commitment to continuous instrument optimization, this study evaluated a revised, unidirectional version of the scale (AGBW-II) to enhance measurement precision. Methods: The psychometric properties of the revised AGBW-II were evaluated via an anonymous online questionnaire in a sample of 161 patients with chronic gastroduodenal symptoms. Score distributions, factor analysis, reliability, and validity were analyzed and compared with data from the validation study of the original scale (n= 311). Results: The AGBW-II total and subscale scores demonstrated robust reliability and validity, outperforming the original AGBW Survey. Notable improvements in the reliability and validity of the stress subscale were observed following item rewording. Confirmatory factor analysis verified the three-factor model separating the depression, stress, and anxiety subscales, with the AGBW-II showing improved model fit indices. Conclusions: The revised, unidirectional AGBW-II demonstrated improved reliability and validity, while maintaining the underlying psychometric properties of the original scale. Consequently, the AGBW-II provides a reliable, valid, and brief mental health assessment for patients with chronic gastroduodenal symptoms.

Introduction: Vaping public education campaigns are a central prevention strategy for young adults (YAs), but message effectiveness varies widely and formative testing typically evaluates one message attribute at a time. This study examined how four perceptual dimensions, including cognitive engagement, social relevance, emotional arousal, and emotional valence, relate to perceived message effectiveness (PME), and whether multiple combinations of these dimensions correspond to similarly high PME. Methods: In a cross-sectional online message-testing study conducted from March to April 2025, 540 U.S. YAs who vape each evaluated 15 messages randomly sampled from a corpus of 229 text-image vaping public education messages, yielding 8,100 message evaluations. Cross-classified multilevel models estimated associations between each perceptual dimension and PME. An Explainable Boosting Machine probed nonlinear associations, and k-means clustering of high-predicted-PME perceptual configurations identified distinct profiles. Analyses were conducted in 2026. Results: Cognitive engagement (b = 0.20, 95% CI [0.18, 0.22]) and social relevance (b = 0.15, 95% CI [0.13, 0.17]) showed the strongest associations with PME, followed by emotional arousal (b = 0.06, 95% CI [0.04, 0.08]); emotional valence showed no linear association (b = 0.00, 95% CI [-0.02, 0.02]). The Explainable Boosting Machine revealed a U-shaped valence pattern, with higher predicted PME at both the negative and positive ends of the scale. Clustering yielded five distinct perceptual profiles with similarly high predicted PME (4.10-4.25). Conclusions: Multiple perceptual configurations correspond to similarly high PME, supporting a configurational approach to formative message testing rather than a single optimal message formula.

Background: Patient Decision aids (PtDAs) are important tools that support shared decision-making (SDM) between clinicians and patients, enabling patients to be more informed and engaged in decisions regarding their care. The use of PtDAs can increase patient knowledge, reduce decisional regret, and engage the clinician and patient in meaningful dialogue. Shared decision-making relies on decision aids, but how patients receive the PtDA can vary. This qualitative study elucidated patient familiarity with PtDAs and the barriers, needs, and requirements of patients to access and confidently use DAs, including when received via a clinician-facing EHR-integrated Decision Aid Navigator System (DEANS). Methods: We conducted six focus groups (FG) with participants who were recruited from two academic medical centers. Focus groups included an introduction to what a PtDA is and an exploration of how patients or family members, i.e., people who had not made a medical decision for themselves using a PtDA, but who have helped a family member, had previously used PtDAs in their healthcare. The FGs focused on PtDA-users, affordances and barriers to using PtDAs, and PtDA-user needs and requirements of a proposed DEAN patient portal. We applied Rapid Qualitative Analysis (RQA) to summarize the data, using a consensus making approach to identify emerging themes. Results: We identified three overarching themes: 1) Patients had varied familiarity with PtDAs and often confused them with general health tools, but found value in SDM, 2) Patients perceived technology accessibility, PtDA credibility, and time as barriers potentially impeding PtDA use, and 3) Patients valued flexible, user-friendly, and accessible PtDAs that support patient-led decisions, particularly when introduced by clinicians and delivered via a patient portal. Conclusion: This study provides patient-derived insights into factors that influence PtDA uptake, highlighting common misconceptions about PtDAs and identifying key patient priorities such as accessibility, flexibility, clear content, and clinician-guided usage. Patient also expected clinicians to be familiar with PtDAs, especially when the PtDA covers a complex decision. These findings can inform the development of more patient-centered SDM infrastructure and strategies to support PtDA use in clinical practice, including clinician-supported delivery, accessibility, and integration into routine care to strengthen shared decision-making.

Youth are increasingly engaging with generative AI beyond its use as a productivity tool, with a growing share turning to AI for social interaction and emotional support. This leads to unknown risks for their well-being and development. Online community discussions reveal that youth already perceive risks that caregivers have not recognized.

Conversational systems based on large language models may support point-of-care evidence retrieval, but most evaluations use static benchmarks and few involve practicing physicians in low- and middle-income settings. We assessed the validity of answers produced by physicians using an evidence-traceable conversational system versus usual information-search practice, alongside response efficiency and acceptability. Physicians in Latin America were randomly assigned to answer four simulated clinical cases, four open-ended questions each, with system support or usual search practice. Two blinded specialists per area scored each response with a six-dimension rubric. The main outcome was the composite validity score aggregated per physician, analyzed with logistic regression adjusted for academic degree. Of 202 physicians who began, 71 completed and were analyzed, 26 supported and 45 using usual practice, yielding 1,136 responses. Physicians using the system scored higher, with medians of 2.83 versus 2.46 (difference 0.38; 95% CI 0.17 to 0.54; P < .001). In the adjusted model they were more likely to meet the validity threshold (odds ratio 3.61; 95% CI 1.16 to 11.17; P = .026). In the adjusted models the association held for the four criteria with the higher interrater agreement, and did not reach significance for accuracy alone. Response time and self-reported searches did not differ, though uneven missingness makes that comparison uninformative. Acceptability among supported physicians was high (mean total score 2.92 of 3). An evaluator outside the organization repeated the accuracy-only analysis, which showed no significant difference; the composite was designated the main outcome after that replication, so the three specifications are reported side by side. The analyzed sample comprises volunteers who completed the exercise, so the findings are exploratory.

Social media influencers serve as a key source of health information for adolescents but often lack expertise, have commercial motives, and may spread misleading or harmful content. This study examines the health-related content shared by influencers, the prevalence of advertising, and how adolescents evaluate potential benefits and risks. Using a mixed-methods approach, we employed a quantitative descriptive method involving citizen science (Study 1) and a qualitative content analysis (Study 2). In Study 1, 336 adolescents from 16 Austrian schools documented and categorized 2,147 posts from 255 influencers. The most common topics included sports and fitness (50.5%), beauty ideals (29.6%), food and nutrition (27.6%), and cooking (19.1%). Although advertisements appeared in 41.5% of posts, adolescents rated 60.4% of them as beneficial and only 4.5% as harmful. The qualitative analysis of a subsample of the 90 most prominent posts showed that adolescents appreciated motivational aspects (e.g., healthy eating) but often overlooked problematic elements such as misleading claims, sexualized body ideals, and the linking of health messages to commercial products. Enhancing persuasion knowledge and critical thinking through education, along with stricter regulation of harmful products, is crucial to safeguarding youth online.

Objective This study aimed at analyzing changes in the prevalence of excessive internet use and to analyze its associations with mental and cognitive health problems among adolescents. Method We used repeated cross-sectional data from the School Health Promotion study, a population-based nationwide classroom survey in Finland. All adolescents in grades 8-11 were invited, with a total of 602,226 responses in 2017-2023. Excessive internet use was measured with the five-item Excessive Internet Use Scale covering core behavioral addiction symptoms. Depressive symptoms, generalized anxiety, and social anxiety were measured with validated questionnaires. Problems in cognitive functioning were assessed with one-item indicators. Analyses were done with Chi-square tests and logistic regression. Results From 2017 to 2023, the prevalence of excessive internet use increased, especially among girls. The increasing trend was significantly (p<0.001) steeper among girls, with the OR for time (in years) being 1.12 in grades 8-9 and 1.14 in grades 10-11, while among boys the corresponding ORs were 1.00 and 1.04, respectively. Excessive internet use associated with short sleep, depressive, generalized anxiety, and social anxiety symptoms (ORs between 1.73-2.42 in boys; 1.92-2.26 in girls; p<0.001) and with difficulties in tasks requiring reading, writing, and mathematics, and difficulties in concentrating (ORs 1.84-2.31 in boys; 1.83-1.98 in girls; p<0.001). Conclusion The prevalence of excessive internet use showed an increasing trend, especially among girls. The associations of excessive internet use with mental health symptoms and cognitive challenges were clear.

Abstract Background: Large language models (LLMs) are increasingly explored as adjunct tools in graduate medical education, but their reliability for answering discipline-specific certification examinations remains incompletely characterized. In dentistry in China, the national dental examination serves as a milestone for stomatology trainees. Prior studies predominantly rely on single metric, limiting reproducibility and granularity. Objective: To systematically evaluate the performance of five LLMs in answering the national standardized training examination for dental residents. Method: A total of 1,318 questions covering the six dentistry disciplines were selected. Five LLMs (DeepSeek-V3, DeepSeek-R1, Qwen3-32B, Claude 3.5, and GPT-4o) were evaluated via a single-response protocol on the Dify-based Chatflow framework. Performance combined human verification with automated scoring using the Retrieval-Augmented Generation Systems (RAGAS) framework across seven dimensions. Tasks involving question classification, key-point categorization, and instructional requirement summarization were designed to enable a horizontal comparison of models' cognitive capabilities, assessed using inter-model consistency scores. Results: DeepSeek-R1 achieved the highest correct choice rate (80.90%, p < 0.001) and answer correctness score (0.853, p < 0.001), significantly outperforming the others. All models exhibited limitations, including information insufficiency, redundancy, and hallucination-related issues (lowest 44.20% in DeepSeek-R1). In classification and summarization tasks, Claude 3.5 showed higher consistency scores (186/181) than Qwen3-32B (152/151). Conclusion: Evaluated LLMs demonstrated good performance on dental examination questions and in executing tasks. DeepSeek-R1 consistently outperformed the others. While LLMs showed potential as supportive tools in dental education, further refinement and validation are needed before formal adoption in graduate medical educational and clinical training settings.

Many pathological conditions, including chronic pain (CP), can impair cognitive functions. These functions are essential for adapting and evolving in concordance with the environment, which are key processes for coping with CP. However, in CP centers, cognitive assessment is rarely included in CP patient follow-up due to a lack of time, appropriate tools, or trained health professionals. To fill this gap, our team developed EasyCog, a digital tool that enables rapid self-assessment of cognitive functions. It enables cognitive evaluation without an experimenter's help, thanks to speech recognition powered by an artificial neural network. In the initial validation steps, we established normative values for 7 cognitive functions on a cohort of 76 healthy subjects. Because EasyCog includes tests comparable to the Montreal Cognitive Assessment (MoCA) and the Mini-Mental State Examination (MMSE), we assessed its reliability against available normative values. To assess its specificity, we compared data from healthy subjects with 15 subjects with mild cognitive impairment (MCI) and 15 age-matched CP patients selected from a medical center. Finally, we tested EasyCog's test-retest reliability by repeating sessions at different time intervals. EasyCog showed excellent sensitivity to age-related decline, similar to MoCA normative values. Several cognitive functions were significantly and differentially impaired in MCI subjects and CP patients compared to normative values in healthy subjects, confirming good specificity. Finally, test-retest analysis showed no effect at a 4-month interval. In conclusion, EasyCog appears to be a convenient and reliable numeric tool for rapidly assessing and monitoring cognitive functions in patients.

Background: Social vulnerability is associated with adverse health outcomes, but existing social vulnerability indices often rely on cohort-based and self-reported data, potentially limiting their population-level applicability. Therefore, this study aimed to develop an SVI from routinely collected electronic health records (EHRs) using natural language processing (NLP) and examine its association with mortality and healthcare utilization. Method: EHR data from 193,629 individuals aged 35 to102 from the Wellbeing Services County of Central Finland between years 2010 and 2023 were used in this study. A 6 item SVI (total score 0 to 6) was developed from free-text clinical notes using deep-learning-based NLP. SVI scores were calculated at baseline and annually for individuals. Associations between baseline SVI and all cause mortality and healthcare utilization were assessed over 12-year follow-up using Cox and count models. Results: The mean baseline SVI among all participants was 0.35 (range 0 to 6). Women had higher SVI (0.39) than men (0.32, p<0.001). SVI increased with age. One unit increase in SVI was associated with a higher risk of mortality (Hazard Ratio (HR) 1.23; 95% Confidence Interval (CI) (1.21 to 1.24), a higher odds of using healthcare services (Odds Ratio (OR) = 1.20; 95% CI): 1.19 to 1.21) and a greater healthcare service use (Incidence Rate Ratio (IRR) = 1.07; 95% CI: 1.06 to 1.07). Discussion: An index capturing multiple domains of social vulnerability can be derived from EHRs using NLP. Higher SVI was associated with increased mortality and healthcare utilization. These findings support the potential of EHR data for assessing social vulnerability and related health risks.

Objective: Retrospective evaluation of clinical pathway adherence using electronic medical record (eMR) data is limited by heterogeneous data structures and statistical measures that do not account for patient-specific context, care sequence, or timing. We designed a modular event-based architecture to dynamically evaluate the New South Wales Adult Sepsis Pathway over time. Method: Data from eMRs were collected from adult emergency department encounters across four hospitals between July 2022 and June 2024 and processed through three sequential layers: event-stream transformation, pathway-relevance filtering, and state-based pathway evaluation. Heterogeneous records were standardized and organized into a chronological timeline for each encounter. The framework then updated the pathway state as new clinical information became available and assessed whether recommended care was delivered within the relevant timeframe and sequence. Result: The architecture processed 451,124 encounters. This included 57,631,084 clinical events extracted and transformed into encounter-level event streams. After filtering for pathway relevance, 43,951,146 events remained (76.3%). A total of 129,907 (34.6%) encounters entered the sepsis pathway, 50,118 (38.6%) entered YELLOW state, indicating progression to suspected sepsis, and 3,349 (2.6%) encounters progressed to RED state from GREEN, indicating the initial shock. Of 50,118 encounters entering YELLOW state, 2,426 (4.8%) progressed to shock, 8,700 (17.4%) encounters were recognized with sepsis through a blood culture order, and 4,287 (8.6%) encounters were recognized with sepsis through an antibiotic order. This demonstrates the ability of the architecture to prioritize higher-acuity states during evaluation rather than going through an intermediate state. Conclusion: The architecture developed shows the feasibility of transforming fragmented routine eMR data into a reusable longitudinal representation that supports context-dependent pathway evaluation. Separating data preparation from pathway rules improves transparency, maintainability, and adaptability and provides a foundation for future interoperable, near-real-time pathway monitoring

Background: Adolescents frequently consult online resources regarding sensitive health topics, including suicide. Although content analyses demonstrate that online platforms contain both suicide-preventive and pro-suicide material, they rarely incorporate subjective data from adolescents at elevated suicide risk. Aims: This exploratory study examined associations between reasons for seeking suicide-related information online and the digital media used to access such content among adolescents with suicidal ideation. Method: Over one year, 131 adolescents aged 13 to 18 with current or past suicidal ideation were recruited from the Emergency Department of an urban pediatric hospital to complete a cross-sectional survey. Participants reported whether they had sought suicide-related information online, the type of information sought, and the online locations used. Mixed-effects regression models examined associations between reasons for online searches and digital media used. Results: Of 131 enrolled adolescents, 113 completed the survey; 69 (61.1%) reported ever seeking suicide-related information online. Searches were more often intended to assist with acting on suicidal thoughts than to reduce suicidal thoughts (63.7% vs. 55.1%). Social media were used for help-seeking searches slightly more often than professional health organization websites (42.1% vs. 31.6%). Among adolescents who used social media for their searches, discussion forums were significantly more likely to be used when seeking information to act on suicidal thoughts (OR=7.0, p=.02). Conclusion: The majority of adolescents with suicidal ideation may seek out suicide-related content online, particularly to facilitate suicide planning. Social media may be used as frequently as professional mental health websites like 988 or The Trevor Project for suicide-related searches.

Depression is one of the most prevalent mental health disorders globally. Social media content can reflect emotional states, offering real-time signals of depressive symptoms. This study aimed to develop a deep learning model to predict depression using Twitter/X data, and to characterize potential causes of depression using a large language model (LLM). Twitter/X posts from April 20, 2023, to July 24, 2024, were obtained using the key phrase ("I" or "me") and "diagnosed with depression". After data cleaning and GPT-4o labelling, 2,275 depressive Twitter users, and an additional 1,661 non-depressive users from tweets using the keyword "today", were identified. A deep learning RoBERTa model for predicting depression was built on tweets from both user groups, with an 80/20 training-testing split. GPT-4o models were subsequently employed to analyze depressive users posts to understand potential causes for depression. The RoBERTa model achieved strong performance in predicting depression among Twitter users from their tweets, with an accuracy of 0.822, an F1 score of 0.855, and an AUC of 0.809. Common reasons for depression identified by GPT-4o models included societal pressure, low self-esteem, cultural influences, and identity-related challenges. These findings highlight the potential of deep learning models in early screening of depression using social media data. Insights into potential reasons for depression may inform targeted prevention strategies, public health interventions, and improved mental health support for at-risk populations.

Background: The first thousand days are a sensitive window for child health and social health inequalities. When routine care falls short, parents of young children turn to online sources and, recently, to generative artificial intelligence (AI). Evidence on their concerns, child-health literacy, and AI use is scarce. Objective: To describe health informational needs and concerns, child-health literacy, and use of AI for child-health questions, including differences by parental role and parity, among parents of young children. Methods: In this cross-sectional study, two anonymous self-administered online questionnaires were disseminated through a digital health application between May 12 and June 11, 2026, to French-speaking parents of at least one child aged 0 to 47 months in France. Questionnaire 1 covered unmet information needs, concerns across 16 topics, perceived intra-couple concordance, and confidence in routine care. Questionnaire 2 covered a four-item child-health literacy quiz and AI use (frequency, topics, 12-month trend, barriers, trust conditions, perceived effect on consultations, and disclosure). Results: In total, 12,634 parents responded (Questionnaire 1, n=5,410; Questionnaire 2, n=7,224), mostly mothers (94.6% and 92.9%). Most (61.8%) had searched for information without finding a clear, reliable answer, selecting a median of 4 (Interquartile range [IQR] 3-7) over 16 topics. Leading concerns were sleep (51.3%), nutrition (48.1%), and education (i.e., upbringing and behavior) (47.8%). Mothers were nearly twice as likely as fathers to select accident prevention (26.5% vs 16.3%) and parental mental health (38.7% vs 28.6%); first-time parents selected most topics more often than experienced parents, most markedly dental hygiene (43.8% vs 27.6%). The median child-health literacy score was 3 (IQR 3-4) on a 0-to-4 quiz, with 19.9% of parents scoring 2 or below; tooth-brushing age was the weakest item (68.4% correct). Mothers outscored fathers on every item. More than half of parents (54.2%) had used AI for a child-health question, 11.2% weekly; among those reporting a trend, 68.3% had increased AI use for child-health questions over the year and 6.2% decreased it. The main barriers to AI use were a preference for professionals (55.9%) and reliability concerns (48.7%); trust depended most on medical oversight of the tool (76.6%). AI use appeared additive, with 66.8% reporting no change in healthcare visit frequency. One third (35.5%) had told an AI something shared with neither a professional nor their network, rising to 64.1% among regular users. Conclusions: Parental informational needs were widespread and frequently unmet. AI has become a common and fast-rising source for child-health questions, at times a confidential one, used alongside rather than instead of professionals. Child-health literacy was generally high but uneven, with oral health the clearest gap. Strengths include the sample size and early-generative-AI timing; limitations include the cross-sectional design, self-report, digital-recruitment selection bias, and the small proportion of fathers.

Background: Passively collected smartphone and wearable data, combined with genomic information, may enable scalable early identification of youth who are at risk for substance use disorder. However, heterogeneous data collected in naturalistic settings limit researcher control over data quality, requiring substantial preprocessing. Data cleaning and feature engineering decisions can meaningfully influence analytic outcomes yet are often minimally described or omitted in published work. Objectives: We provide rationales and recommendations for common preprocessing challenges in passive sensing research, including establishing inclusion criteria when "outliers" may reflect true behavioral variability, analyzing differences across smartphone operating systems, handling observations collected outside protocol windows, and engineering features for machine learning applications. Methods: We illustrate principled approaches to these challenges using smartphone and Fitbit data from the Adolescent Brain Cognitive Development Study (ABCD). The sample was drawn from the available half of the year-4 follow-up (data release 5.1; N = 4,754; ages 13-14). Results: Extreme outlying observations were concentrated among low-engagement participants with few observed days. Smartphone usage among Apple users appeared under-recorded relative to Android users when compared with self-report measures. Fitbit-derived behavior differed systematically between observations collected within versus outside protocol windows. We also identified potential errors in the study's default preprocessing pipeline. Conclusion: We recommend prioritizing person-level inclusion criteria that preserve meaningful behavioral variability, examining temporal distributions rather than assuming observations are exchangeable, and thoroughly investigating and reporting data quality issues. Although illustrated using the ABCD Study, these principles broadly apply to research using smartphones, wearables, and other digital data sources.