News & Views

Diagnostics play a crucial role in screening, detecting, and stratifying patients, yet can account for only 2–3% of healthcare spending. With advancements in wearable technology and direct-to-consumer testing, the market for consumer health continues to rise. The potential benefits of more holistic and continuous measurement offer a promising opportunity for earlier disease detection and proactive health management. Many health systems are in a parallel transition from legacy analogue approaches to digitally enabled infrastructures. The evolving role of the clinical workforce, including medical ethics, regulation, will be closely coupled and a critical lever in success. This includes on a patient and clinician level, balancing the benefits and risks of interventions, and care pathway level, promoting responsible data utilisation with greater contextualisation based on the latest evidence of clinical efficacy. Moving forward a balance may need to be struck between increased data capture, analysis and reuse, with proportionate ethics, regulation, trust and governance.

Reliably processing and interlinking medical information has been recognized as a critical foundation to the digital transformation of medical workflows, and despite the development of medical ontologies, the optimization of these has been a major bottleneck to digital medicine. The advent of large language models has brought great excitement, and maybe a solution to the medicines’ ‘communication problem’ is in sight, but how can the known weaknesses of these models, such as hallucination and non-determinism, be tempered? Retrieval Augmented Generation, particularly through knowledge graphs, is an automated approach that can deliver structured reasoning and a model of truth alongside LLMs, relevant to information structuring and therefore also to decision support.

The hospital at home concept integrates key digital medicine technologies and concepts in a single platform approach, with telemedicine, wearables, and sensors. It could bring benefits to patients, who face lower risks from hospital infections and who want to be at home with their loved ones. Moreover, it may lead to efficiency savings, through its seamless integration of data flows, and therefore is likely to be an increasingly implemented model. But what happens when the platform succumbs to exploited platform/infrastructure vulnerabilities or cyber attacks like ransomware that have been weaponized to bring networked systems crashing down? Exploring the attack modes and their consequences could help prioritize adequate safeguards.

Smartphones, smartwatches, linked wearables, and associated wellness apps have had rapid uptake. These tools become ever ‘smarter’ in sensing intimate aspects of our surroundings and physiology over time, including activity, metabolites, electrical signals, blood pressure and oxygenation. Proposed EU law stipulates the ‘involuntary donation’ of depersonalized health and wellness data. There has been pushback against the ever-increasing gathering and sharing of wellness data in this context, increasing with every app purchased or updated. Is the potential of this data now lost to research? Consent-led COVID-19 data donation projects signpost a participative, standardized, and scalable approach to data sharing.

The path to market and to a meaningful impact on care delivery for medical extended reality (MXR) is challenging, due to limitations with current display technologies and as the MXR approach is far away from the traditional practice of medicine and the daily experience of most patients or healthcare providers. Focused conferences, which bring together all stakeholders for free communication and the brainstorming of optimal approaches to design, validation, and regulatory approval are important and are being organized by the clinician-enthusiast and developer community. These conferences and the community spirit they inspire are models for other digital health subdomains.