Health services articles from across Nature Portfolio

Evaluation of a clinical summarization method based on GPT-4 suggests that such models might reduce the documentation burden on clinicians — but prospective evaluation with high-priority tasks will be the true test of its potential.

Tailored to detect and prevent potential medication direction errors in a digital pharmacy data processing pipeline, a large language model is shown to increase efficiency and decrease burden for technicians and pharmacists in a prospective application.

Allgaier et al. scrutinize the performance of machine learning (ML) models applied to 7 longitudinal mHealth datasets. Their study advocates for considering simple heuristics over complex ML models, underscoring the need for robust validation and expert consultation to address hidden groups in data.

Evaluation of a clinical summarization method based on GPT-4 suggests that such models might reduce the documentation burden on clinicians — but prospective evaluation with high-priority tasks will be the true test of its potential.

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.