Editorials in 2026

As digital medicine expands, the growing volume of unused (or underutilized) data are creating a hidden epidemic of technological waste. For example, the concept of a digital twin has gained rapid traction. A virtual replica to mirror an organ, physiological system or a patient to explore predictive simulation, real-time monitoring and/or “what-if” scenarios. Yet, a digital twin generates big data e.g., sensor streams, metadata, audit logs, simulations, and backups. Over time, much of that data may become dormant, but require storage. That is the burden of going digital, invisible waste with the accumulation of unused files, logs, archives, and dormant applications/apps especially in Cloud and institutional infrastructures. The environmental, financial, and operational costs of digital waste are rarely discussed in medicine (or health), yet it matters as data ecosystems scale. In contrast (physical) electronic/e-waste is broadly discussed. Here, we discuss why digital medicine researchers and institutions must take digital waste seriously. We highlight Digital Cleanup Day (21 March 2026) and raise awareness to embed data sustainability metrics into digital medicine.

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.