npj Health Systems

Author notes These authors contributed equally: Timothy R. Huerta, Christopher W. Bartlett. Authors and Affiliations College of Medicine, The Ohio State University, Columbus, OH, USA Timothy R. Huerta, Gabriel Alain, Carol R. Bradford, John FP Bridges, Arnab Chakravarti, Julie A. Johnson, Nina V. Kraguljac, Lang Li, Qin Ma, Puneet Mathur, Marcy Mays, Ann Scheck McAlearney, Sayoko E. Moroi, Xia Ni…

Abstract Health technology faces rising costs, system complexities, and gaps between development and coverage policies, limiting translation into practice. Traditional health technology assessment (HTA) evaluates technologies at late stages, providing little support if a technology fails to secure reimbursement. Early HTA addresses this by assessing technologies during research and development st…

Abstract Cross-state deployment of Medicaid risk prediction models is challenged by demographic, policy, and care-delivery differences that create domain shift. We evaluated transfer learning methods for predicting acute care utilisation between Washington (source; n = 20,744) and Virginia (target; n = 28,901) Medicaid populations enrolled in high-risk care management, where outcome prevalence di…

Disease phenotype onset is critical for timely and accurate diagnosis and clinical decision-making, yet it remains poorly characterized in the literature. Estimating phenotype onset using electronic health record (EHR) data holds promise but remains challenging. Researchers often resort to EHR documentation timestamps as proxies for phenotype onset, which can be inaccurate. Conventional natural l…

Abstract Using artificial intelligence (AI) to prescribe drugs has advanced slowly. Whether a “doctor-in-the-loop” design would increase acceptance of drug-prescribing AI is unknown, as are settings where physicians envision AI-driven drug prescription most likely to be implemented. We surveyed a stratified sample of 2708 physicians throughout China to interrogate their opinions on drug-prescribi…

Abstract We analyzed 19,123 natural language processing-related studies to explore the differences in task distributions and application contexts between large language models (LLMs) and non-LLM methods in health care. Through topic modeling analysis, we found that LLMs demonstrate advantages in open-ended tasks, while non-LLM methods dominate in information extraction tasks. These findings highl…

Abstract Data-driven medical devices promise significant enhancements to diagnostic accuracy, personalised treatments, real-time patient monitoring, and clinical decision support. However, these innovations present regulatory challenges. This study maps the current European Union Medical Device Regulation requirements against international data safety and quality assurance standards, identifying …

Abstract Rapid nurse decision-making is needed to detect patient deterioration and prevent mortality. Current approaches to support nurses’ decisions involve diagnostic data processing and providing a decision with little explanation. Our team aimed to demonstrate the utility of attention architecture to model sequential nurse–patient care actions. Experienced nurses and students completed patien…

Abstract We tested state-of-the-art LLMs under clinical-scale workloads using two designs: a single agent handling all tasks and a multi-agent orchestrator assigning each task to a dedicated worker. Across retrieval, extraction, and dosing tasks, batch sizes ranged from 5–80. Multi-agent accuracy remained high (90.6% at 5 tasks; 65.3% at 80), while single-agent accuracy collapsed (73.1% to 16.6%;…

It is essential to align the perspectives of healthcare professionals on recovery priorities for the targeted population to promote health and well-being. This study aimed to identify the functional recovery priorities of individuals with spinal cord injury (SCI) and to assess gaps in recovery priorities between individuals with SCI and healthcare professionals. A web-based survey was conducted w…

Alzheimer's Disease¹ (AD) necessitates accelerated treatment discovery, positioning drug repurposing as a vital strategy. While computational approaches such as knowledge graph reasoning and transcriptomics show promise, they often yield divergent results, complicating the selection of candidates for experimental follow-up^2,3. To bridge the gap between computational predicti…

Abstract Accurate segmentation of knee cartilage and meniscus in magnetic resonance imaging (MRI) is essential for the early detection and monitoring of complications such as cartilage erosion and osteoarthritis. Yet, manual annotation remains time-consuming, subjective, and inefficient for routine clinical use. In this study, we introduced KneeXNet-2.5D , a clinically oriented and explainable de…

Abstract Africa is experiencing the impacts of climate change. While global epidemiological studies using traditional analytical methods to study the relations between climate change and health exist, studies using data science to tackle these topics are increasing. The aim of this study was to identify how data science is being used to understand climate change impacts on health in Africa. We ca…

Artificial intelligence (AI) holds promise for healthcare, but real-world implementation remains difficult. The Mayo clinic platform (MCP) addresses this by providing scalable, multi-institutional, de-identified data and analytical tools. Through four research projects, we demonstrate MCP's ability to support efficient cohort identification, AI model development, and real-world evidence generatio…

Abstract Electronic health record (EHR) systems are critical to modern healthcare delivery, yet the dynamic workflows that govern electronic order processing remain underexplored. Inefficiencies in these digital pathways can cause delays in care, repetitive workloads, and even patient harm. This study presents a discrete-event simulation framework used to reconstruct and evaluate EHR-based order …

Abstract Large language model (LLM) chat tools have the potential to transform healthcare workflows by improving efficiency and reducing administrative burdens. While prior research has predominantly focused on clinicians, non-clinician healthcare staff constitute the majority of the workforce, and their real-world chat tool use remains uncharacterized. This retrospective, cross-sectional study a…

Rising healthcare costs and a shortage of primary care providers in the United States create substantial strain on the healthcare system, underscoring the need for efficient allocation of limited resources. Accurate prediction of high primary care utilization can enable proactive care planning, targeted interventions, and workload optimization. We developed and evaluated the Friedman Score, a mac…

Abstract Digital Twins hold great potential to personalize clinical patient care, provided the concept is translated to meet specific requirements emerging from established clinical workflows. We present a general and unspecialized Digital Twin design combining knowledge graphs and ensemble learning to reflect the entire patient’s clinical journey and assist clinicians in their decision-making. S…

Intensive care units (ICU) produce numerous progress notes that may contain stigmatizing language that perpetuate negative biases and punitive approaches against patients. Patients with substance use disorders are particularly vulnerable to stigma. This study examined the performance of Large Language Models (LLMs) in the identification of stigmatizing language. We annotated a dataset with over 7…