Editorials

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.

In recent years the intersection of wearable technologies and machine learning (ML) based deep learning (DL) approaches have highlighted their potential in sleep research. Yet, a recent study published in NPJ Digital Medicine highlights the generalization limitations of DL models in sleep-wake classification using actigraphy data. Here, this article discusses some of the challenges and opportunities presented by domain adaptation and self-supervised learning (SSL), innovative methodologies that use large-scale unlabeled data to bolster the generalizability of DL models in sleep assessment. These approaches not only improve sleep-wake classification but also hold promise for extending to more comprehensive sleep stage classification, potentially advancing the field of automated sleep assessment through efficient and user-friendly wearable monitoring systems.

Generative AI is designed to create new content from trained parameters. Learning from large amounts of data, many of these models aim to simulate human conversation. Generative AI is being applied to many different sectors. Within healthcare there has been innovation specifically towards generative AI models trained on electronic medical record data. A recent review characterizes these models, their strengths, and weaknesses. Inspired by that work, we present our evaluation checklist for generative AI models applied to electronic medical records.

Boussina et al. recently evaluated a deep learning sepsis prediction model (COMPOSER) in a prospective before-and-after quasi-experimental study within two emergency departments at UC San Diego Health, tracking outcomes before and after deployment. Over the five-month implementation period, they reported a 17% relative reduction in in-hospital sepsis mortality and a 10% relative increase in sepsis bundle compliance. This editorial discusses the importance of shifting the focus towards evaluating clinically relevant outcomes, such as mortality reduction or quality-of-life improvements, when adopting artificial intelligence (AI) tools. We also explore the ecosystem vital for AI algorithms to succeed in the clinical setting, from interoperability standards and infrastructure to dashboards and action plans. Finally, we suggest that algorithms may eventually fail due to the human nature of healthcare, advocating for the need for continuous monitoring systems to ensure the adaptability of these tools in the ever-evolving healthcare landscape.

The utilization of artificial intelligence (AI) in diabetes care has focused on early intervention and treatment management. Notably, usage has expanded to predict an individual’s risk for developing type 2 diabetes. A scoping review of 40 studies by Mohsen et al. shows that while most studies used unimodal AI models, multimodal approaches were superior because they integrate multiple types of data. However, creating multimodal models and determining model performance are challenging tasks given the multi-factored nature of diabetes. For both unimodal and multimodal models, there are also concerns of bias with the lack of external validations and representation of race, age, and gender in training data. The barriers in data quality and evaluation standardization are ripe areas for developing new technologies, especially for entrepreneurs and innovators. Collaboration amongst providers, entrepreneurs, and researchers must be prioritized to ensure that AI in diabetes care is providing quality and equitable patient care.

We explore the evolving landscape of diagnostic artificial intelligence (AI) in dermatology, particularly focusing on deep learning models for a wide array of skin diseases beyond skin cancer. We critically analyze the current state of AI in dermatology, its potential in enhancing diagnostic accuracy, and the challenges it faces in terms of bias, applicability, and therapeutic recommendations.