Journal of Medical Internet Research

Telemedicine is expanding rapidly, with public direct-to-consumer (DTC) telemedicine representing 70% of the market. A key priority is establishing clear quality distinctions between the public and private sectors. No studies have directly compared the quality of DTC telemedicine in the public and private sectors using objective evaluation methods.

Large language models (LLMs) continue to exhibit noteworthy capabilities across a spectrum of areas, including emerging proficiencies across the health care continuum. Successful LLM implementation and adoption depend on digital readiness, modern infrastructure, a trained workforce, privacy, and an ethical regulatory landscape. These factors can vary significantly across health care ecosystems, dictating the choice of a particular LLM implementation pathway. This perspective discusses 3 LLM implementation pathways—training from scratch pathway (TSP), fine-tuned pathway (FTP), and out-of-the-box pathway (OBP)—as potential onboarding points for health systems while facilitating equitable adoption. The choice of a particular pathway is governed by needs as well as affordability. Therefore, the risks, benefits, and economics of these pathways across 4 major cloud service providers (Amazon, Microsoft, Google, and Oracle) are presented. While cost comparisons, such as on-demand and spot pricing across the cloud service providers for the 3 pathways, are presented for completeness, the usefulness of managed services and cloud enterprise tools is elucidated. Managed services can complement the traditional workforce and expertise, while enterprise tools, such as federated learning, can overcome sample size challenges when implementing LLMs using health care data. Of the 3 pathways, TSP is expected to be the most resource-intensive regarding infrastructure and workforce while providing maximum customization, enhanced transparency, and performance. Because TSP trains the LLM using enterprise health care data, it is expected to harness the digital signatures of the population served by the health care system with the potential to impact outcomes. The use of pretrained models in FTP is a limitation. It may impact its performance because the training data used in the pretrained model may have hidden bias and may not necessarily be health care–related. However, FTP provides a balance between customization, cost, and performance. While OBP can be rapidly deployed, it provides minimal customization and transparency without guaranteeing long-term availability. OBP may also present challenges in interfacing seamlessly with downstream applications in health care settings with variations in pricing and use over time. Lack of customization in OBP can significantly limit its ability to impact outcomes. Finally, potential applications of LLMs in health care, including conversational artificial intelligence, chatbots, summarization, and machine translation, are highlighted. While the 3 implementation pathways discussed in this perspective have the potential to facilitate equitable adoption and democratization of LLMs, transitions between them may be necessary as the needs of health systems evolve. Understanding the economics and trade-offs of these onboarding pathways can guide their strategic adoption and demonstrate value while impacting health care outcomes favorably.

Artificial intelligence (AI) chatbots such as ChatGPT are expected to impact vision health care significantly. Their potential to optimize the consultation process and diagnostic capabilities across range of ophthalmic subspecialties have yet to be fully explored.

Assessing the complex and multifaceted symptoms of patients with acute psychiatric disorders proves to be significantly challenging for clinicians. Moreover, the staff in acute psychiatric wards face high work intensity and risk of burnout, yet research on the introduction of digital technologies in this field remains limited. The combination of continuous and objective wearable sensor data acquired from patients with deep learning techniques holds the potential to overcome the limitations of traditional psychiatric assessments and support clinical decision-making.

The adoption of patient portals, such as the National Health Service (NHS) App in England, may improve patient engagement in health care. However, concerns remain regarding differences across sociodemographic groups in the uptake and use of various patient portal features, which have not been fully explored. Understanding the use of various functions across diverse populations is essential to ensure any benefits are equally distributed across the population.

Evaluating the clinical status of concussions using virtual platforms has become increasingly common. While virtual approaches to care are useful, there is limited information regarding the barriers and facilitators associated with a virtual concussion assessment.

Although personalization and tailoring have been identified as alternatives to a “one-size-fits-all” approach for eHealth technologies, there is no common understanding of these two concepts and how they should be applied.

The concept of digital twins, widely adopted in industry, is entering health care. However, there is a lack of consensus on what constitutes the digital twin of a patient.

Effective fall prevention interventions in hospitals require appropriate allocation of resources early in admission. To address this, fall risk prediction tools and models have been developed with the aim to provide fall prevention strategies to patients at high risk. However, fall risk assessment tools have typically been inaccurate for prediction, ineffective in prevention, and time-consuming to complete. Accurate, dynamic, individualized estimates of fall risk for admitted patients using routinely recorded data may assist in prioritizing fall prevention efforts.

Co-use of alcohol and e-cigarettes (often called vaping) has been linked with long-term health outcomes, including increased risk for substance use disorder. Co-use may have been exacerbated by the COVID-19 pandemic. Social networking sites may offer insights into current perspectives on polysubstance use.

The COVID-19 pandemic impacted patients with substance use disorder (SUD) more than the general population and resulted in substantially increased emergency department admissions. Routine care of patients attending drug health services during the pandemic transitioned, with telehealth being important in delivering appropriate care. However, telehealth introduces unique risks such as privacy, confidentiality, and data safety. Providing health care through telehealth may fail if the legal impacts are not fully identified and acted on by health professionals. It also poses unintended risks for patients and can result in ineffectiveness, damages, medical negligence, and detracts from the best intentions of governments and health professionals. Understanding the legal framework ensures that medical professionals operate health care through telehealth within the law. Providing health care successfully through telehealth depends on the balance between innovation and legal compliance. By considering these aspects, clinicians and practitioners can provide effective and safe telehealth services during pandemics or any other natural disaster.

Intrinsic capacity (IC), as a comprehensive measure of an individual’s functional ability, has gained prominence in the framework for healthy aging introduced by the World Health Organization (WHO). As internet usage continues to integrate into daily life, it is imperative to scrutinize the association between internet use and IC to effectively promote healthy aging among the middle-aged and older population.