Journal of Medical Internet Research

Health portraits powered by big data integrate diverse health-related data into actionable insights, thereby facilitating precise risk prediction and personalized management of noncommunicable diseases (NCDs). Despite their promise, the adoption and application of health portraits remain fragmented, primarily due to the lack of a standardized conceptual and methodological framework necessary to fully harness their capabilities.

Wasp stings are a significant public health concern in many parts of the world, particularly in tropical and subtropical regions. The venom of wasps contains a variety of bioactive compounds that can lead to a wide range of clinical effects, from mild localized pain and swelling to severe, life-threatening allergic reactions, such as anaphylaxis. With the rapid development of artificial intelligence (AI) technologies, large language models (LLMs) are increasingly being used in health care, including emergency medicine and toxicology. These models have the potential to assist health care professionals in making fast and informed clinical decisions. This study aimed to assess the performance of 4 leading LLMs—ERNIE Bot 3.5 (Baidu), ERNIE Bot 4.0 (Baidu), Claude Pro (Anthropic), and ChatGPT 4.0—in managing wasp sting cases, with a focus on their accuracy, comprehensiveness, and decision-making abilities.

Emotional well-being interventions lead to better mental and physical health. However, most of these interventions have been tested on relatively homogeneous samples, with few interventions large enough to examine whether key sociodemographic factors impact outcomes. In addition, barriers to engagement include access and high participant burden. We developed a brief web-based intervention to address these barriers and tested the effects across sociodemographic groups.

A significant gap exists in the knowledge and procedural skills of medical graduates when it comes to managing emergencies. In response, highly immersive virtual-reality (VR)-based learning environments have been developed to train clinical competencies. However, robust evidence on how VR-based methods affect both short- and long-term learning outcomes, as well as physiological and perceived stress, remains limited.

Online accessible patient education materials (PEMs) are essential for patient empowerment. However, studies have shown that these materials often exceed the recommended sixth-grade reading level, making them difficult for many patients to understand. Large language models (LLMs) have the potential to simplify PEMs into more readable educational content.

Parkinson disease (PD) presents motor and nonmotor challenges that significantly affect quality of life. Telemedicine has emerged as a promising approach to deliver interventions, including exercise performed through remote equipment (e-Exercise), cognitive behavioral training sessions conducted remotely (e-Cognitive), and consultations conducted through remote devices (e-Visits), yet their comparative effectiveness remains unclear.

WeChat mini program-based interventions grounded in behavioral theories show promise in promoting and maintaining healthy lifestyles among patients with cardiovascular diseases (CVDs) after hospital discharge. However, limited randomized controlled trials (RCTs) have evaluated the effectiveness of such interventions among Chinese patients with CVDs in a home-based rehabilitation context.

Accurately assessing perioperative risk is critical for informed surgical planning and patient safety. However, current prediction models often rely on structured data and overlook the nuanced clinical reasoning embedded in free-text preoperative notes. Recent advances in large language models (LLMs) have opened opportunities for harnessing unstructured clinical data, yet their application in perioperative prediction remains limited by concerns about factual accuracy. Retrieval-augmented generation (RAG) offers a promising solution—enhancing LLM performance by grounding outputs in domain-specific knowledge sources, potentially improving both predictive accuracy and clinical interpretability.

N/A

Digital patient portals (PPs) are platforms that enhance patient engagement and promote active involvement in health care by providing remote access to personal health data. Although many hospitals are legally required to offer these portals, adoption varies widely among patients, often influenced by sociodemographic and socioeconomic determinants. Evidence suggests that higher income, education, employment status, and specific age groups correlate with increased portal usage, highlighting a digital divide. This study aims to analyze sociodemographic and socioeconomic determinants affecting digital PP usage, addressing inconsistencies in existing research and contributing to strategies for reducing digital health disparities.

Preconception health is essential for preventing premature birth, yet engagement in preconception care remains low. Internet-based interventions offer scalable solutions, but their effectiveness in this context is underexplored.

Recent advances in digital health technology offer the potential to overcome established access barriers to mental health support, such as stigma and geographical location. The World Health Organization recommends integrating digital technologies into mental health care, underscoring the need for countries to develop national digital mental health (DMH) strategies to guide efforts. The rate of development and availability of DMH tools currently outpaces the existing policy or regulatory guidance required to guide their use. In Ireland, a key requirement of the national mental health strategy, Sharing the Vision, was the development of a national DMH strategy. Key stakeholders in DMH research, policy, practice, and lived experience were brought together as part of a focused stakeholder engagement event to develop a shared vision for digital mental health in Ireland.