JMIR Formative Research最新文献

Background: Conversational artificial intelligence (AI) systems offer potential solutions to traditional constraints in medical consultation skills training, including high costs, scheduling difficulties, and varied standardization. There is limited evidence evaluating medical professionals' perceptions of AI-generated patient interactions across multiple fidelity dimensions and assessing the educational value of conversational AI for consultation skills training.

Objective: This study aimed to evaluate perceptions of conversational AI patient simulations in primary care consultation training, examining functional fidelity, conversational realism, educational value, and implementation readiness.

Methods: A cross-sectional evaluation study at a UK medical school (medical students and general practitioners) yielded 47 grouped and individual responses. Participants completed standardized clinical scenarios using the SimFlow conversational AI system, a conversational AI system, followed by a multidomain questionnaire evaluating AI realism, medical content, educational value, feedback, and usability. Data were analyzed using the Wilcoxon signed rank test, Spearman correlation, and Firth logistic regression to assess domain performance and participant characteristics.

Results: Medical content received the highest ratings (median 4.5, IQR 4.0-5.0), with 97.8% (45/46) rating clinical plausibility highly. Educational value was rated positively (median 4.0, IQR 3.0-4.0), although AI realism received moderate scores (median 3.0, IQR 2.0-4.0). Participants with prior AI experience gave significantly higher ratings for AI realism than those without prior experience (mean 3.81, SD 0.63 vs 3.07, SD 0.72; P=.03). Concordance analysis demonstrated moderate-to-strong agreement between individual- and group-level domain rankings (mean Spearman ρ=0.685), supporting consistency between collaborative and individual survey evaluations. Qualitative analysis revealed 4 themes: clinical authenticity, interactional limitations, educational potential, and implementation considerations.

Conclusions: Conversational AI demonstrates strong capabilities in functional fidelity (clinical accuracy) despite limitations in conversational fidelity (realism). The technology shows promise as a supplementary tool for clinical skills training rather than higher-stakes assessment, with future development needed in dialogue naturalness and feedback capabilities.

Background: Despite the rapid expansion of internet infrastructure and digital health initiatives in China, there remains a lack of longitudinal, nationally representative analyses that track the concurrent development of general internet access and the specific adoption of online health services over the past decade. Understanding these parallel trends is crucial for evaluating the reach and equity of the ongoing digital health transformation.

Objective: The aim of this study was to describe decade-long trends in internet infrastructure development and online health service adoption in China through a comprehensive secondary analysis of nationally representative, publicly available survey data from 2014 to 2025.

Methods: Data were retrieved from the official website of the China Internet Network Information Center for the period from June 2014 to June 2025. The study was conducted in 31 provinces, autonomous regions, and municipalities, excluding Hong Kong, Macau, and Taiwan. The participants were citizens aged 6 years and older who had a telephone or mobile phone. The China Internet Network Information Center conducted a stratified 2-stage sampling survey using a computer-aided telephone access system.

Results: From 2014 to 2025, an increasing trend was observed in the number of internet users and the internet penetration rate in China. It also showed an upward trend in the number of internet users, both in urban and rural areas. A consistent increasing trend was detected in the number of mobile internet users. In contrast, desktops and laptops showed a declining trend. The number of online health users in China showed a V-shaped change from 2020 to 2025. In June 2025, the total number of online medical users reached approximately 393 million, representing 35% of all internet users.

Conclusions: This decade-long observational study demonstrates sustained and significant growth in internet access across China, accompanied by a substantial rise in online health service adoption. A notable V-shaped trajectory in online health use emerged after 2020, indicative of a rapid COVID-19 pandemic-driven acceleration followed by market consolidation. The converging trends of near-universal smartphone-based access and the massive popularity of mobile-centric services, such as short videos, have fundamentally reshaped the digital landscape. Consequently, the findings suggest that for digital health strategies to achieve broad impact, policymakers and health care providers could consider prioritizing the integration of health promotion and services into existing high-penetration mobile platforms and communication formats that the population already uses daily.

Background: Clinical decision support systems (CDSSs) are widely used in various health care settings. In Japan, pressure ulcers are becoming a major concern in an aging society due to their increasing prevalence. However, management is often handled by nonspecialists in wound care due to regional disparities in specialist availability.

Objective: To provide support for nonspecialists in wound care, we developed a prototype smartphone-based CDSS for pressure ulcer management. The system prompts users to answer questions about the wound's condition and recommends appropriate ointments and wound dressings by using a safety-first approach. This study aims to evaluate the utility of this system.

Methods: We conducted a randomized crossover pilot study involving 28 general internal medicine (GIM) physicians. Participants were randomly assigned to group A (intervention-control) or group B (control-intervention). Participants evaluated 10 standardized pressure ulcer photographs and selected the most appropriate ointment and wound dressing for each. The unit of analysis was the individual response to each question (N=280 total observations). We used generalized estimating equations with an exchangeable correlation structure to account for within-subject clustering and adjust for potential period and sequence effects.

Results: The overall correct response rate during the intervention phase was significantly higher than that during the control phase (49.3% vs 4.3%, respectively). After adjusting for clustering and crossover biases, the use of CDSS was associated with a 29.1-fold increase in the odds of a correct response (95% CI 8.2-103; P<.001). Secondary analyses revealed significant improvements in ointment selection (adjusted odds ratio [aOR] 2.4, 95% CI 1.5-3.8; P<.001) and wound dressing selection (aOR 8.9, 95% CI 4.9-16.1; P<.001). However, no significant period (P=.11) or sequence (P=.25) effects were observed for the primary outcome.

Conclusions: The prototype CDSS improved the accuracy of treatment decisions made by GIM physicians in a pilot study that used photographs and fixed options. Within the parameters of this investigation, CDSS effectively guided participants toward standardized, safety-oriented choices as defined by our scoring criteria.

Trial registration: UMIN Clinical Trials Registry UMIN000057294; https://tinyurl.com/36a6vvah.

Incorporating prespecified Google Trends indicators into leakage-controlled stacked-ensemble models improved a 2025 holdout prediction of subjective well-being by using 2022-2025 data from Japan's 47 prefectures, reducing the mean squared error from 0.0050 to 0.0045.

Background: Extracting accurate medication information from Thai hospital records presents challenges due to the narrative style of medical notes, which often combine Thai and English terminology. Named entity recognition (NER) serves as the foundational step for advanced clinical information extraction (IE) tasks, including medical concept normalization and relation extraction. This study aimed to establish a robust NER framework to address these difficulties by leveraging ontology-based annotation and pretrained transformer models.

Objective: The primary objective of this study was to evaluate the performance of 5 fine-tuned pretrained transformer models-BioClinicalBERT, ClinicalBERT, PubMedBERT, MultilingualBERT, and ThaiBERT-based on Bidirectional Encoder Representations from Transformers (BERT) in extracting structured medication information from unstructured Thai hospital discharge summaries.

Methods: Ninety discharge summaries were collected from Maharaj Nakhon Chiang Mai Hospital. These documents were annotated by physicians following the annotation guidelines based on international standards, including Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) and Health Level Seven Fast Healthcare Interoperability Resources (HL7 FHIR). The dataset was divided into fine-tuning (70 records, 78%, 2030 annotated spans), validation (10 records, 11%, 277 annotated spans), and testing sets (10 records, 11%, 358 annotated spans). The 5 transformer models were fine-tuned and evaluated using this annotated data to recognize and classify key medication entities (substance, route of administration, unit of measure, time patterns, and unit of presentation).

Results: We found that all models had good NER performance metrics in both the validation and test datasets. Regarding test performance, ClinicalBERT achieved the highest exact F1-score at 0.973, compared with 0.968 for BioClinicalBERT, 0.925 for PubMedBERT, 0.931 for MultilingualBERT, and 0.969 for ThaiBERT. All models showed strength in accurately identifying "Substance" and "Dosage" entities, whereas "Unit of Measure" proved to be the most challenging entity type due to implicit information in the source text for all models.

Conclusions: The findings suggest that ontology-based medication IE using transformer-based models holds promise for enhancing data standardization and interoperability within the Thai health care system. Future work will need to leverage the granular annotations preserved in the dataset to develop medical concept normalization and relation extraction models to complete the medical IE system.

Background: The COVID-19 pandemic accelerated the adoption of telehealth as a key strategy within Brazil's Unified Health System. In São Paulo State, digital health initiatives have been developed to implement telehealth-based care models across all 3 levels of health care.

Objective: The aim of this study is to describe the implementation process of the telehealth model in public health facilities to a lesser extent.

Methods: This descriptive study reports on the implementation of telehealth services at the primary, secondary, and tertiary levels of health care in São Paulo State. Thirty primary health units, 4 specialty care outpatient clinics, and 18 hospitals were selected by the institutions participating in the project based on technical, health care, and infrastructure criteria. Teleconsultations were conducted through the institutional teleconferencing platform, ensuring data security and privacy. Data were collected through REDCap (Research Electronic Data Capture) between April and December 2024, including operational metrics and satisfaction scores (Net Promoter Score [NPS]). All participating health care facilities signed a term of adherence and data sharing agreement. Patients received care only after being informed and after signing a consent and adherence term for telehealth form.

Results: Telehealth was implemented in 52 health care facilities across 47 municipalities in São Paulo State. A total of 19,053 teleconsultations were conducted in primary health units (NPS 97) and 218 in specialty care outpatient clinics (NPS 74), and 4178 intensive care unit case discussions were held (NPS 86).

Conclusions: The findings suggest that telehealth is a feasible strategy across all levels of health care, even when implemented at a limited scale, contributing to expanded access and service coverage.

Background: The COVID-19 pandemic prompted rapid changes in medical education, accelerating the adoption of online and distance learning methods as alternatives to traditional teaching. While these approaches offered logistical advantages, students worldwide reported significant limitations, particularly in terms of motivation, clinical exposure, and hands-on skill acquisition. Despite increased use of digital teaching during the pandemic, core educational objectives and the mission of medical training remained unchanged, emphasizing the continued importance of practical experience.

Objective: This study investigates the impact of the COVID-19 pandemic on current teaching methods in medical education and explores students' perceptions of online learning, telemedicine, artificial intelligence, and other modern educational alternatives.

Methods: This observational, cross-sectional multicentric study surveyed a cohort of Romanian medical students using a self-developed 48-item online questionnaire distributed via social media. Data were collected over six weeks (February-March), yielding 451 responses, of which eligible participants included students in clinical years or preclinical students interested in surgical or orthopedic careers, with a heavy representation of the Medicine and Pharmacy University of Timisoara. Statistical analysis was performed using Microsoft Excel and Jasp.

Results: A total of 436 responses were analyzed, with students favoring online or hybrid formats for lectures but preferring onsite teaching for practical training. Reduced patient interaction and limited skill acquisition were the main drawbacks of online practical education. Acceptance of hybrid learning correlated with more positive perceptions of teaching methods and a lower perceived desire to cheat.

Conclusions: The COVID-19 pandemic brought significant changes to the way medicine is being taught in Romania, but it also brought a clearer picture for students and medical staff on how they want medical education to be done. Online cheating remains a significant challenge, but it is being tackled at the moment with different algorithms being tested.

Clinicaltrial:

Background: Personalized behavioral recommendations through mobile apps have proven effective in preventing serious chronic diseases such as diabetes. Recent studies have primarily focused on optimizing personalized recommendations using reinforcement learning. However, the main problem with these approaches is that they focus on behavioral changes and overlook clinical outcomes.

Objective: This study aimed to propose a method for online planning of dietary and exercise recommendations to optimize postprandial glucose levels through behavioral changes directly.

Methods: The proposed method is a multiarmed bandit based on a two-stage reward prediction model, where an action is a combination of the total carbohydrate intake and postprandial walking duration, and the reward is the reduction in postprandial glucose levels. We implemented the prediction of the reward for each action based on the predicted behavioral responses to an action, and subsequently, the postprandial glycemic response.

Results: In a simulation experiment, we demonstrated that the proposed online algorithm can significantly improve postprandial glucose levels with personalized recommendations, compared to the randomized policy. Furthermore, we conducted a small real-world experiment with a simplified proposed method involving a single update of the recommendation policy into a personalized one. For 6 participants, compared to the randomized policy, we observed a 23% improvement, on average, in actual glucose responses along with the behavioral adherence to the recommendations concerning carbohydrate intake and postprandial walking.

Conclusions: The preliminary effectiveness of the proposed method was demonstrated from both the simulation experiment and the small real-world experiment. However, further longitudinal real-world experiments in patients with diabetes are needed to validate and generalize the findings.