Editorials

Han et al. show that deep learning applied to simple smartphone videos can match specialist ratings of gait impairment, detect medication effects, and surface novel movement features as candidate biomarkers in Parkinson’s disease. These steps toward remote, objective gait assessment complement advances in wearable-powered symptom tracking and promise extended access to care alongside enriched clinical trial metrics. To realize these benefits, implementation research focused on validating care models is needed.

As healthcare systems are becoming increasingly overwhelmed by mounting demands for care and declining capacity, digitally enabled interventions are being adopted to relieve system pressure. To ensure digital healthcare interventions are appropriate and beneficial, co-design should be central to their development. Co-design approaches will be increasingly instrumental in shaping future digital medicine interventions to address the needs of populations and individuals, thereby reducing the risk of wasting resources on unwanted, inoperable, and ineffective interventions. There is a growing body of literature reporting how end-users have been involved in informing the development of digital healthcare interventions. However, there are consistent omissions and discrepancies in key details of the co-design process, as well as inconsistent terminology, contributing to a convoluted evidence base.

While physicians routinely consider uncertainty during patient diagnosis, large language models (LLMs) often fail to recognize that real-world clinical data can be too limited for a definitive diagnosis. Zhou et al. address this problem by training a LLM, ConfiDx, to recognize medical cases with limited clinical data. This approach improves the utility of LLMs in the clinic and enables physicians to more effectively recognize and explain uncertainty in their patient care.

Chen et al. demonstrate that large language models (LLMs) frequently prioritize agreement over accuracy when responding to illogical medical prompts, a behavior known as sycophancy. By reinforcing user assumptions, this tendency may amplify misinformation and bias in clinical contexts. The authors find that simple prompting strategies and LLM fine-tuning can markedly reduce sycophancy without impairing performance, highlighting a path toward safer, more trustworthy applications of LLMs in medicine.

In “A Randomized Controlled Trial of Mobile Intervention Using Health Support Bubbles to Prevent Social Frailty”, Hayashi et al. investigated the effects of using a mobile health app with family or individually. Greater improvements in social behavior and frailty were noted in participants who used the app with family. In an era of remote healthcare and app-based health interventions, Hayashi et al.’s study reminds of the importance of human connection.

Integrating large language models (LLMs) into oncology holds promise for clinical decision support. Woollie is an LLM recently developed by Zhu et al., fine-tuned using radiology impression notes from Memorial Sloan Kettering Cancer Center and externally validated on UCSF oncology datasets. This methodology prioritizes data accuracy, preempts catastrophic forgetting, and demonstrates unparalleled rigor in predicting the progression of various cancer types. This work establishes a foundation for reliable, scalable, and equitable applications of LLMs in oncology.

Return-to-work (RTW) after long-term absence due to ill health (or other factors) can be fraught with psychological, physical, and organisational challenges which may require continuous management to ensure successful employee reintegration. While digital interventions have emerged to support reintegration, a recent systematic review revealed that few explicitly address RTW needs, despite growing interest in e-mental health. Early online interventions demonstrate promise in improving psychological outcomes, yet face limitations in scalability, personalisation, and integration into workplace systems. Smartphone-based interventions via applications/apps offer a scalable alternative, leveraging ubiquitous technology to deliver support beyond bespoke settings through self-monitoring, continuous learning, and communication tools. However, existing RTW-focused apps remain narrowly tailored to specific conditions, with limited adaptation to individual needs and insufficient evaluation of long-term effectiveness. Future developments must prioritise personalisation, rigorous evaluation in diverse populations, and integration within occupational health and real-world employer systems with organisational support. Addressing these gaps is essential to fully realise the potential of digital solutions in supporting sustainable work reintegration that is respectful and compassionate.

Wu et al.’s recent article, “Noninvasive early prediction of preeclampsia in pregnancy using retinal vascular features,” documents significant differences in retinal vascular features among women who develop preeclampsia and those with normotensive pregnancies. These findings provide evidence that retinal screening has the potential to be used as a low-cost, non-invasive screening strategy to support the earlier detection, prevention, and treatment of preeclampsia.

Winter et al.’s recent investigation, “A Comparison of Self-Reported COVID-19 Symptoms Between Android and iOS CoronaCheck App Users,” reveals differences in the demographics and COVID-19 symptoms reported by users of Android and iOS systems. These findings not only provide more information about the varied experiences of individuals during the COVID-19 pandemic but also suggest that conclusions reached in studies using one operating platform may not be generalizable to users of other platforms.

Deep vein thrombosis (DVT) causes significant morbidity/mortality and timely diagnosis often via ultrasound is critical. However, the shortage of trained ultrasound providers has been an ongoing challenge. Recently, Speranza and colleagues (2025) demonstrated that an artificial intelligence (AI) guided ultrasound system used by non-ultrasound-trained nurses with remote clinician review can achieve sensitivities of 90–98% and specificities of 74–100% for diagnosing DVT. This study highlights the potential for AI guided imaging to address important gaps in health care delivery.

Collaborative use of population-level health data and artificial intelligence is essential for achieving precision health through a learning health system. Two groundbreaking initiatives—the European Health Data Space (EHDS), covering 449 million EU citizens, and Germany’s forthcoming Health Data Lab, providing access to data from 75 million insured individuals (90% of the country’s population)—offer unprecedented opportunities to advance digital health innovation and research with global impact.

Digital health tools have the potential to support patients in managing their chronic diseases. Recently, Ullrich and colleagues (2025) introduced PreventiPlaque, a mobile health application that provides patients with up-to-date ultrasound images of their carotid plaques and tracks their lifestyle habits. Through a randomized controlled trial, the authors provide evidence of PreventiPlaque’s efficacy in improving patients’ cardiovascular risk profiles. This study highlights the potential for digital health interventions to provide personalized health information to patients and empower them to take actionable steps to improve their cardiovascular health.

Cardiovascular disease is underdiagnosed and undertreated in women compared to men. Wearable technologies (wearables) help shed light on women’s cardiovascular by collecting continuous cardiovascular data and correlating it with hormonal fluctuations across the menstrual cycle. In this context, Jasinski et al. propose that the new metric, cardiovascular amplitude, enables non-invasive monitoring of female physiology and health across the menstrual cycle.

Liu et al.’s recent study reveals that telemedicine expanded access to cardiovascular care in China, enabling patients in poorer areas of the country to access care in cities with more resources. While these findings may support the global expansion of telemedicine, implementation often proves challenging. This article examines the potential and limitations of adopting similar telemedicine efforts within the U.S. to advance geographic health equity.

Alzheimer’s disease is the fifth-leading cause of death for adults over the age of 65. Retinal imaging has emerged to find more accurate diagnostic tool for Alzheimer’s Disease. This paper highlights Hao et al.’s development of a new deep learning tool, EyeAD, which studies Optical Coherence Tomography Angiography (OCT-A) of patients with Alzheimer’s. Integrating this model into clinical workflows may offer novel insights into the progression of this disease.

Qiao et al. recently investigated the ability of dual-energy X-ray absorptiometry (DXA) scans and a smartphone app to provide detailed body composition and shape data. In a healthcare system that continues to rely on crude and stigmatizing measurements like body-mass index (BMI), their findings point to the potential of newer technologies to capture markers (i.e., visceral adiposity and fat distribution patterns) that provide clearer insights into metabolic health.

Radin et al.’s recent study on patients with long COVID demonstrates that personal wearable data can provide critical insight into complex conditions. This editorial argues that research insights gained through personal wearables support the integration of personal wearables into healthcare. Challenges in incorporating wearable data in the clinic point towards AI data sorting, data sharing, device interoperability, FDA oversight, and expanded insurance coverage as first steps towards addressing these challenges.

This piece critiques the exclusion of healthcare practitioners (HCPs) from the digital health innovation process. Drawing on “Sync fast and solve things—best practices for responsible digital health” by Landers et al., the editorial argues for the importance of inclusive co-creation, in which clinicians play an active role in developing digital health solutions. It emphasizes that without the meaningful involvement of HCPs, digital health tools risk being clinically irrelevant.

There is a need for digital health innovation focused on bettering the health of marginalized populations. These communities, often insured by Medicaid and Medicare, face complex healthcare barriers that technology can address—emphasizing the role of the Center for Medicaid and Medicare Services (CMS) in fostering innovation. Dasari et al. identify four areas of CMS collaboration with startups: enhancing consumer awareness, leveraging telehealth, streamlining cross-state licensing and billing, and adopting technology-enabled tools.

Large language models (LLMs) have shown promise in reducing time, costs, and errors associated with manual data extraction. A recent study demonstrated that LLMs outperformed natural language processing approaches in abstracting pathology report information. However, challenges include the risks of weakening critical thinking, propagating biases, and hallucinations, which may undermine the scientific method and disseminate inaccurate information. Incorporating suitable guidelines (e.g., CANGARU), should be encouraged to ensure responsible LLM use.