Tag: pubmed

JMIR Form Res. 2026 Feb 3;10:e84023. doi: 10.2196/84023.

ABSTRACT

BACKGROUND: Poor sleep is a concerning public health problem in the United States. Previous sleep interventions often face barriers such as high costs, limited accessibility, and low user engagement. Recent advancements in artificial intelligence (AI) technologies offer a novel approach to overcoming these limitations. In response, our team developed a prototype AI sleep chatbot powered by a large language model to deliver personalized, accessible sleep support.

OBJECTIVE: This study aimed to examine the feasibility, usability, acceptability, and preliminary efficacy of the AI chatbot for sleep promotion.

METHODS: We conducted a quasi-experimental, single-group study with adults in the United States aged 18 to 75 years who self-reported poor sleep. The chatbot was integrated into a commercially available messaging app. Participants were asked to engage with a virtual sleep therapist via texting over 2 weeks. The chatbot provided ongoing, individualized sleep guidance and adapted recommendations based on participants’ prior conversations. Feasibility, usability, and acceptability were descriptively summarized. Sleep was assessed using questionnaires before and after the intervention.

RESULTS: Of the 107 adults who enrolled in the study, 88 (82.2%) completed chatbot registration. Among these 88 participants, 65 (73.9%) initiated interactions, and 44 (50%) completed the 2-week intervention. The final analysis included 42 adults (mean age 36, SD 11 years; n=12, 28.6% male). On average, participants engaged with the chatbot for 58 (SD 42) minutes, with each chat session lasting approximately 9 (SD 6) minutes. Most reported favorable experiences with the chatbot. The average usability score was 85.2 (SD 10.7) out of 100, which was well above the benchmark of 68. The chatbot was rated as highly acceptable, with a satisfaction score of 27.3 (SD 4.1) out of 32. All participants perceived the chatbot as effective, with ratings ranging from “slightly effective” to “extremely effective.” The preliminary evidence showed improved sleep outcomes after chatbot use: total sleep time increased by 1.4 hours (P<.001); sleep onset latency decreased by 30.9 minutes (P<.001); sleep efficiency increased by 7.8% (P=.007); and scores improved for perceived sleep quality (mean difference [MD] -5.4; P<.001), insomnia severity (MD -7.9; P<.001), daytime sleepiness (MD -4.7; P<.001), and sleep hygiene skills (MD -13.2; P<.001). No significant change was observed in sleep environment (MD -1.1; P=.16).

CONCLUSIONS: Our AI chatbot demonstrated satisfactory feasibility, usability, and acceptability. Improvements were observed following chatbot use, although causality cannot be established. These findings highlight the potential of integrating state-of-the-art large language models into behavioral interventions for sleep promotion. Future research should include objective sleep measurements and conduct randomized controlled trials to validate the study findings. If confirmed, this AI chatbot could be scaled to support sleep health on a broader level.

PMID:41632970 | DOI:10.2196/84023

J Med Internet Res. 2026 Feb 3;28:e82170. doi: 10.2196/82170.

ABSTRACT

BACKGROUND: While artificial intelligence (AI) holds significant promise for health care, excessive trust in these tools may unintentionally delay patients from seeking professional care, particularly among patients with chronic illnesses. However, the behavioral dynamics underlying this phenomenon remain poorly understood.

OBJECTIVE: This study aims to quantify the influence of AI trust on health care delays through integrated survey-based mediation analysis and real-world research, and to simulate intervention efficacy using agent-based modeling (ABM).

METHODS: A cross-sectional online survey was conducted in China from December 2024 to May 2025. Participants were recruited via convenience sampling on social media (WeChat and QQ) and hospital portals. The survey included a 21-item questionnaire measuring AI trust (5-point Likert scale), AI usage frequency (6-point scale), chronic disease status (physician-diagnosed, binary), and self-reported health care delay (binary). Responses with completion time <90 seconds, logical inconsistencies, missing values, or duplicates were excluded. Analyses included descriptive statistics, multivariable logistic regression (α=.05), mediation analysis with nonparametric bootstrapping (500 iterations), and moderation testing. Subsequently, an ABM simulated 2460 agents within a small-world network over 14 days to model behavioral feedback and test 3 interventions: broadcast messaging, behavioral reward, and network rewiring.

RESULTS: The final sample included 2460 adults (mean age 34.46, SD 11.62 years; n=1345, 54.7% female). Higher AI trust was associated with increased odds of delays (odds ratio [OR] 1.09, 95% CI 1.00-1.18; P=.04), with usage frequency partially mediating this relationship (indirect OR 1.24, 95% CI 1.20-1.29; P<.001). Chronic disease status amplified the delay odds (OR 1.42, 95% CI 1.09-1.86; P=.01). The ABM demonstrated a bidirectional trust erosion loop, with population delay rates declining from 10.6% to 9.5% as mean AI trust decreased from 1.91 to 1.52. Interventions simulation found broadcast messaging most effective in reducing delay odds (OR 0.94, 95% CI 0.94-0.95; P<.001), whereas network rewiring increased odds (OR 1.04, 95% CI 1.04-1.05; P<.001), suggesting a “trust polarization” effect.

CONCLUSIONS: This study reveals a nuanced relationship between AI trust and delayed health care-seeking. While trust in AI enhances engagement, it can also lead to delayed care, particularly among patients with chronic conditions or frequent AI users. Integrating survey data with ABM highlights how AI trust and delay behaviors can strengthen one another over time. Our findings indicate that AI health tools should prioritize calibrated decision support rather than full automation to balance autonomy, odds, and decision quality in digital health. Unlike previous studies that focus solely on static associations, this research emphasizes the dynamic interactions between AI trust and delay behaviors.

PMID:41632964 | DOI:10.2196/82170

JMIR Cancer. 2026 Feb 3;12:e70354. doi: 10.2196/70354.

ABSTRACT

BACKGROUND: Ostomy creation for cancer treatment negatively impacts the quality of life of both patients and caregivers. Hispanic patients with cancer and caregivers often face additional challenges, including limited access to supportive care programs.

OBJECTIVE: This study aimed to examine the experiences and preferences of Hispanic patients with cancer living with ostomies and their caregivers to inform the cultural adaptation of an existing intervention program and the design of Ostomy Self-Care Program (Programa de AutoCuidado de Estoma [PACE]).

METHODS: In this 2-stage study, conducted between March and August 2023 in San Antonio, Texas, we used a qualitatively driven mixed methods design, starting with an initial survey followed by qualitative interviews to explore the experiences, needs, and intervention preferences of Hispanic patients and caregivers managing ostomy care. We used Braun and Clarke’s 6-phase thematic analysis approach to analyze the qualitative data and performed descriptive analysis for the quantitative data. Subsequently, we applied affinity diagramming and persuasive systems design principles to guide the design of PACE.

RESULTS: In total, 14 Hispanic participants managing an ostomy (9 patients with cancer and 5 caregivers) completed a survey and participated in interviews, continuing until data saturation was reached. Participants had a mean age of 58.9 (SD 13.01, range 37-79) years, and most (n=12) reported a high school diploma or General Educational Development as their highest education level. Around 5 (36%) participants scored below 26 on the eHealth Literacy Scale (eHEALS), indicating low digital health literacy, and the average Charlson Comorbidity Index (CCI) was 3.21 (SD 1.86, range 0-6). Overall, 3 major themes emerged from the qualitative data analysis, namely perceptions of living with an ostomy, seeking support, and postsurgery challenges. Additionally, two primary themes emerged from participant interviews: (1) importance of preferred language and multimedia delivery and (2) patients and caregivers desire early introduction, multimodal delivery of materials, and inclusion of peer and family support. These themes informed the design and development of a culturally appropriate, web-based, bilingual PACE intervention that integrates content visualization, cultural adaptations, and persuasive technologies-strategies designed to encourage user engagement.

CONCLUSIONS: Our findings emphasize the importance of understanding the ostomy care experiences, supportive care needs, and intervention preferences of Hispanic patients and caregivers. Informed by stakeholders’ insights, we culturally adapted the original intervention program using persuasive systems design principles to design and develop the PACE intervention, aiming to enhance engagement among Hispanic patients with cancer and caregivers, support effective self-management of ostomy care, and improve health outcomes.

PMID:41632962 | DOI:10.2196/70354

JMIR Mhealth Uhealth. 2026 Feb 3;14:e75005. doi: 10.2196/75005.

ABSTRACT

BACKGROUND: Young African American men who have sex with men (AAMSM) experience disproportionately high HIV incidence and are less likely to achieve viral suppression compared to White men who have sex with men, an outcome that relies on antiretroviral therapy (ART) adherence. We created My Personal Health Guide, a talking relational agent-based mobile health app to improve ART adherence among young AAMSM.

OBJECTIVE: The objective was to determine the efficacy of My Personal Health Guide on improving ART adherence among young AAMSM living with HIV.

METHODS: We implemented a randomized controlled trial among young (aged 18-34 years) AAMSM with nonoptimal ART adherence throughout the United States between February 2020 and September 2023, predominantly through social media and by word of mouth, provider referral, and fliers in selected health care settings. Participants were randomized in a 1:1 ratio using permuted blocks of 8 to the intervention, My Personal Health Guide, or the attention control arm. ART adherence was assessed with Wilson’s 3-item self-reported adherence measurement and dichotomized at ≥80%. Logistic regression models using backward selection were used to evaluate the efficacy of My Personal Health Guide on ≥80% ART adherence at 1-month follow-up.

RESULTS: Among the 253 AAMSM at baseline, most (n=180, 71.1%) self-reported being ≥80% adherent to ART, over half (n=145, 57.3%) resided in the Southern United States, but all US regions were represented, nearly half (n=175, 42.3%) had some college education, over one-third (n=96, 37.9%) had less than optimal literacy, and approximately one-quarter (n=61, 24.1%) experienced housing insecurity in the past 6 months. The sample for analysis of the My Personal Health Guide app efficacy was 131 (intervention=76 and control=55). The odds of being ≥80% adherent to ART at 1-month follow-up were 3.97 (95% CI 1.26-12.55) times greater among participants randomized to the My Personal Health Guide app compared to the controls, after adjusting for ART adherence at baseline, treatment adherence self-efficacy, and ever being incarcerated. Additionally, for every 1-point increase in the HIV Treatment Adherence Self-Efficacy Scale, the odds of ≥80% ART adherence increased by 3% (odds ratio 1.03, 95% CI 1.00-1.06).

CONCLUSIONS: Participants randomized to receive My Personal Health Guide reported nearly 4 times greater odds of being ≥80% adherent to ART compared to the attention control group at 1-month follow-up. To our knowledge, this is the first randomized controlled trial demonstrating improved medication adherence using a relational agent-based behavioral intervention. These findings provide evidence of short-term efficacy of My Personal Health Guide to improve ART adherence among young AAMSM. We recommend further research on the inclusion of relational agents in behavioral research, especially in populations affected by stigma and nonoptimal health literacy, where this nonhuman supportive and educational approach may be complementary to health care systems.

TRIAL REGISTRATION: ClinicalTrials.gov NCT04217174; https://clinicaltrials.gov/study/NCT04217174.

PMID:41632958 | DOI:10.2196/75005

J Med Internet Res. 2026 Feb 3;28:e79671. doi: 10.2196/79671.

ABSTRACT

BACKGROUND: The HIV epidemic in the United States disproportionately impacts gay, bisexual, and other men who have sex with men (MSM). Despite the effectiveness of HIV preexposure prophylaxis (PrEP) in preventing HIV acquisition, uptake among MSM remains suboptimal. Motivational interviewing (MI) has demonstrated efficacy at increasing PrEP uptake among MSM but is resource-intensive, limiting scalability. The use of artificial intelligence, particularly large language models with conversational agents (ie, “chatbots”) such as ChatGPT, may offer a scalable approach to delivering MI-based counseling for PrEP and HIV prevention.

OBJECTIVE: This internal usability testing aimed to evaluate the development of an artificial intelligence-based chatbot, including its ability to provide MI-aligned education about PrEP and HIV prevention and potential to support PrEP uptake.

METHODS: The Chatbot for HIV Prevention and Action (CHIA) was built on a GPT-4o base model embedded with a validated knowledge database on HIV and PrEP in English and Spanish. The CHIA was fine-tuned through training on a large MI dataset and prompt engineering. The use of the AutoGen multiagent framework enabled the CHIA to integrate 2 agents, the PrEP Counselor Agent and the Assistant Agent, which specialized in providing MI-based counseling and handling function calls (eg, assessment of HIV risk), respectively. During internal testing from March 10-April 28, 2025, we systematically evaluated the CHIA’s performance in English and Spanish using a set of 5-point Likert scales to measure accuracy, conciseness, up-to-dateness, trustworthiness, and alignment with aspects of the MI spirit (eg, collaboration, autonomy support) and MI-consistent behaviors (eg, affirmation, open-ended questions). Descriptive statistics and mixed linear regression were used to analyze the data.

RESULTS: A total of 296 responses, including 145 English responses and 151 Spanish responses, were collected during the internal testing period. Overall, the CHIA demonstrated strong performance across both languages, receiving the highest combined scores in the general response quality metrics including up-to-dateness (mean 4.6, SD 0.8), trustworthiness (mean 4.5, SD 0.9), accuracy (mean 4.4, SD 0.9), and conciseness (mean 4.2, SD 1.1). The CHIA generally received higher combined scores for metrics that assessed alignment with the MI spirit (ie, empathy, evocation, autonomy support, and collaboration) and lower combined scores for MI-consistent behaviors (ie, affirmation, open-ended questions, and reflections). Spanish responses had significantly lower mean scores than English responses across nearly all MI-based metrics.

CONCLUSIONS: Our internal usability testing highlights the potential of the CHIA as a viable tool for delivering MI-aligned counseling in English and Spanish to promote HIV prevention and support PrEP uptake, though its Spanish language performance requires further improvement.

PMID:41632955 | DOI:10.2196/79671

JMIR Res Protoc. 2026 Feb 3;15:e79875. doi: 10.2196/79875.

ABSTRACT

BACKGROUND: Therapeutic emesis (TE), known as vamana karma, is a classical method of detoxification performed to eliminate vitiated kapha (bio-humor governing fluid regulation and structural cohesion of the body in normalcy) ailments from the body. The assessment of this complete process depends on physicians’ visual assessments of vomitus features and patient responses, introducing subjectivity and interobserver variability. Moreover, this method requires more than continuous monitoring; thus, it can sometimes lead to human error, resulting in missed expelled content or complications. We propose an artificial intelligence (AI) model to monitor TE to observe visual changes (ie, patient vomitus content and gestures) to provide better clinical outcomes. This approach is being explored for the first time in the traditional system of medicine.

OBJECTIVE: This study aims to develop and validate an AI-assisted digital framework for the objective evaluation of TE via (1) automatic vomitus detection, (2) content classification, (3) number of bouts expelled, (4) facial expressions and individual gestures, (5) determination of detoxification type, and (6) provision of a postpurificatory dietary regimen after completion.

METHODS: The study will be conducted in 3 phases. The first is the preparation of standard operating procedure for TE data collection. The second is data annotation of detected vomiting events. All analyses will be conducted using Python libraries, including scikit-learn (version 1.3.2; developed by the scikit-learn contributors, Python Software Foundation), TensorFlow (version 2.14.0; Google Brain Team, Google LLC), and tools supported under Google Summer of Code 2023 (Google LLC), along with SPSS Statistics (version 26.0; IBM Corp) for statistical analysis. In the third phase, model performance will be evaluated using standard machine learning metrics, and agreement with expert assessments will be measured using the Fleiss κ statistic. This study is exploratory in nature. Thus, 50 volunteers will be targeted.

RESULTS: This is the first study of its kind, so to create the dataset, we prepared a standard operating procedure for TE event data collection. Data collection was completed in December 2025. Data annotation and preliminary model preparation are ongoing, with final testing and validation expected to be completed by December 2025. External testing in the health care setting is expected to be completed by February 2026.

CONCLUSIONS: This work presents one of the first attempts to apply deep learning for objective analysis of the TE process in Ayurveda. By combining YOLOv9 for vomit detection and residual neural network for classification, the framework achieves promising accuracy in automated vomit identification. The results will demonstrate the potential of AI-assisted analysis in traditional medicine, although further clinical validation and expansion across multiple centers will be necessary before deployment in real-world settings.

PMID:41632954 | DOI:10.2196/79875

Perfusion. 2026 Feb 3:2676591261423026. doi: 10.1177/02676591261423026. Online ahead of print.

ABSTRACT

BackgroundEffective myocardial protection is essential for successful outcomes in open-heart surgery. Although both del Nido and St. Thomas cardioplegia solutions are widely used, comparative evidence in adult rheumatic mitral valve replacement remains limited. This study aimed to compare their myocardial protective efficacy and clinical outcomes.MethodsA prospective comparative study was conducted between May 2022 and October 2024. Total 50 adult patients undergoing mitral valve replacement-20 with severe mitral regurgitation (MR) and 30 with severe mitral stenosis (MS) were included. Patients were divided into two groups based on cardioplegia type (del Nido or St. Thomas). Intraoperative parameters, postoperative left ventricular ejection fraction (LVEF), troponin I levels, inotropic and ventilatory support, and ICU/hospital stay were analysed.ResultsBaseline characteristics were comparable across groups. The mean number of cardioplegia doses was significantly lower in the del Nido group (1.6 ± 0.5 vs 3.2 ± 0.8; p < 0.001). Postoperative LVEF was better preserved with del Nido cardioplegia (MS: 53.3 ± 7.2% vs 45.3 ± 10.6%; p = 0.023). Troponin I levels at 6, 24, and 48 h were lower in the del Nido group, though not statistically significant. Patients receiving del Nido required less inotropic and ventilatory support, with shorter ICU and hospital stays. One in-hospital death occurred in the del Nido group due to sepsis.ConclusionDel Nido cardioplegia offers comparable or superior myocardial protection to St. Thomas solution in adult mitral valve replacement, with fewer interruptions, reduced dosing, and faster postoperative recovery.

PMID:41632949 | DOI:10.1177/02676591261423026

Liver Transpl. 2026 Jan 20. doi: 10.1097/LVT.0000000000000811. Online ahead of print.

ABSTRACT

BACKGROUND: Early reoperation for bleeding after liver transplantation (ERBALT) is associated with increased morbidity and mortality. However, no reliable predictive tool is currently available. The primary aim was to evaluate the predictive ability of conventional coagulation tests (CCT) and viscoelastic assays (VEA), for identifying patients at risk of ERBALT within the first seven days following liver transplantation (LT).

METHODS: A total of 275 patients who underwent LT at a tertiary center were screened in this prospective observational study. CCT and VEA were obtained at four time points: (1) post-induction; (2) end of the an-hepatic phase; (3) 10 minutes after reperfusion (R10); and (4) 60 minutes after reperfusion (R60). Other recognized perioperative risk factors for ERBALT were recorded. A predictive score was developed based on the weighted coefficients from multivariable logistic regression.

RESULTS: The final analysis included 222 patients of whom 25 (11.26%) required ERBALT. These patients had more advanced liver disease (Child-Pugh score: 10 (8-11) vs. 8 (6-9), p=0.002) and required significantly higher volumes of fluids (4000 (3000-5750) mL vs. 3000 (2500-4000) mL, p=0.002) and blood products intraoperatively (80% vs. 51.3%, p=0.005). The score included R60-CTINTEM ≥230 seconds (4 points), R60-CTEXTEM ≥85 seconds (2 points); and intraoperative transfusion of ≥4 units of red blood cells (1 point) yielding a total score ranging from 0 to 7. Only 1% of patients with a score ≤3 required ERBALT, compared to 47.8% of those with a score of 7.

CONCLUSION: VEA demonstrated strong predictive value for early reoperation for bleeding after LT. The proposed risk score could facilitate the timely correction of coagulation and potentially improve clinical outcomes after LT.

PMID:41632943 | DOI:10.1097/LVT.0000000000000811

JCO Clin Cancer Inform. 2026 Feb;10:e2500234. doi: 10.1200/CCI-25-00234. Epub 2026 Feb 3.

ABSTRACT

PURPOSE: This trial aims to investigate the effectiveness of online digital intervention in patients with non-small cell lung cancer (NSCLC) in terms of adverse events (AEs) and quality of life (QoL).

METHODS: This randomized trial recruited 200 patients with advanced NSCLC (March 2022-October 2023). All patients received standard-of-care precise treatment, predominantly immunochemotherapy. The study was designed to assess AEs and QoL improvement. Through the CareAcross online platform, all patients received information about their disease and treatment and reported any of the 22 predefined AEs at any time. Patients were randomly assigned 1:1 in the intervention (A) and control (B) arm; patients in arm A automatically received, additionally, evidence-based guidance for the reported AEs. EuroQol 5-dimension 5-level responses were collected at baseline and at each treatment cycle. Resulting scores were compared between baseline and after the sixth cycle. In addition, patient case-level hospitalization data were collected and costs were estimated based on reimbursed costs as defined by the Ministry of Health, enabling a post hoc analysis.

RESULTS: Clinical characteristics were well-balanced. More AEs were reported by patients online versus to their clinicians (P < .01). Among the 22 AEs, 17 improved more in arm A, with the improvement in rash and stomatitis being statistically significant. In QoL, there was no improvement in any of the five EuroQol 5-Dimension dimensions. Digital intervention was cost-saving with lower mean costs for hospitalization (P < .001). Overall response rate, progression-free survival, and overall survival were not statistically different between the two arms, ensuring comparable clinical outcome.

CONCLUSION: Digital oncology tends to improve selected AEs and is cost saving. Patients report, digitally, more informative AEs. Digital oncology can be a complementary tool to the oncology team and warrants further exploration.

PMID:41632937 | DOI:10.1200/CCI-25-00234

J Am Acad Orthop Surg Glob Res Rev. 2026 Feb 2;10(2). doi: 10.5435/JAAOSGlobal-D-25-00422. eCollection 2026 Feb 1.

ABSTRACT

INTRODUCTION: Periprosthetic distal femur fractures (PDFFs) are increasing with rising arthroplasty volumes. An optimal fixation strategy remains debated. This study evaluated outcomes of single lateral locking plate constructs (sLLPs), retrograde intramedullary nails (IMNs), and dual constructs (nail-plate or dual plating).

METHODS: A retrospective cohort study was done at a level I trauma center (2012 to 2024). Adults with PDFF (AO/Orthopaedic Trauma Association 33) treated with sLLP, IMN, or dual constructs were included. All patients were assessed for postoperative weight-bearing status, while clinical outcomes required ≥6-month follow-up or earlier documented complications. Outcomes included revision surgery, infection, implant failure, hardware removal, wound dehiscence, and time to weight bearing as tolerated (WBAT).

RESULTS: Of 99 identified patients, 64 met criteria (IMN: n = 20; sLLP: n = 19; dual: n = 25). Mean age was 69.0 years; 75.0% female, 59.4% Black; mean follow-up 391.5 days. Immediate WBAT was ore common in dual (70.7%) and IMN (52.8%) groups than sLLP (9.1%; P < 0.001). Mean time to WBAT was shortest with dual constructs (13.8 days), followed by IMN (26.0) and sLLP (42.8; P = 0.020). On multivariable analysis, sLLP fixation was associated with increased odds of unplanned revision surgery (OR 6.27, 95% confidence interval, 1.29 to 30.50, P = 0.023), while neither IMN (P = 0.157) nor dual constructs (P = 0.071) demonstrated a significant association.

CONCLUSION: Single lateral locking plate fixation in PDFF was associated with higher odds of unplanned revision surgery. Dual construct patients had the shortest time to postoperative weight bearing and were more frequently permitted WBAT immediately after surgery.

PMID:41632935 | DOI:10.5435/JAAOSGlobal-D-25-00422