📄 Category

health informatics

256 papers

Health informatics sits at the vibrant intersection of medicine, data science, and technology, transforming how we store, analyze, and utilize health information. This rapidly evolving field empowers clinicians and researchers to uncover patterns in patient data, improve diagnostic accuracy, and personalize treatment plans without getting lost in complex databases. By turning raw medical records into actionable insights, these innovations are reshaping the future of healthcare delivery and population health management.

At Gist.Science, we bridge the gap between cutting-edge research and public understanding by curating the latest preprints from medRxiv specifically within this domain. Our team processes every new submission in this category, providing both accessible plain-language explanations and detailed technical summaries to ensure the science is clear for everyone, from policymakers to curious readers. Below are the latest papers in health informatics, freshly distilled and ready for you to explore.

📄 health informatics

A ReAct Agentic AI System for Natural Language Querying and Statistical Analysis of The Cancer Genome Atlas Clinical Data

This paper presents TCGA-Agent, a ReAct-based agentic AI system that autonomously queries and analyzes complex TCGA clinical data using a suite of eight computational tools, achieving 93.4% accuracy and demonstrating that tool design and reasoning loops are more critical than model scale for extracting clinically valuable insights beyond existing curated resources.

Korutla, R., Amal, S.2026-09-28
📄 health informatics

PhysioFusion: A Multi-Modal Ensemble using Static Preoperative Variables and Time Series Intraoperative Data to Predict Adverse Events Following Cardiothoracic Surgery

The PhysioFusion study demonstrates that a multi-modal ensemble model integrating static preoperative variables and intraoperative time-series data achieves high accuracy (AUC 0.87) in predicting post-cardiothoracic surgery adverse events, revealing that while the two data modalities act as substitutes rather than complements, their fusion optimizes the sensitivity-specificity trade-off to provide a high-negative-predictive-value screening tool for high-risk patients.

Korutla, R., Hicks, A., Milosevic, M., Kulkarni, D., Mazhude, F., Kelting, T., Rabb, J. B., Jin, Q., Kramer, R., Sawyer (…)2026-09-28
📄 health informatics

Automated, Component-Level Assessment of a National Inpatient Diabetes Guideline: Adherence and Its Association with Hospitalization Complications Across Six Hospitals

This retrospective multicenter study of nearly 48,000 inpatient admissions demonstrates that automated, component-level assessment of a national diabetes guideline revealed modest overall adherence improvements but significant gaps in insulin management, with higher adherence strongly associated with reduced mortality and hyperglycemia despite a slight increase in hypoglycemia risk.

Oded, S., Shahar, Y., Shalom, E., Bashkin, A., Saiegh, L., Cantrell, D., Wirsansky, I., Badarne, M., Barash, I., Cahn, A (…)2026-09-28
📄 health informatics

Exposure Records Preserved by Two Users of Japan's COVID-19 Contact-Confirming Application During the Seventh Wave: A Descriptive Study

This descriptive study analyzes exposure records preserved by two Japanese users of the COCOA app during the seventh wave of COVID-19, revealing that while recorded exposure windows generally tracked the epidemic's rise and fall, a subsequent policy revision coincided with a sharp decline in data that cannot be solely attributed to the policy change due to confounding factors like app usage and software updates.

Nakagawa, S., Kumagai, S., Yamamoto, A.2026-09-25
📄 health informatics

Quality of physicians responses using a conversational artificial intelligence system: a randomized vignette experiment in Latin America

In a randomized vignette experiment involving physicians in Latin America, an evidence-traceable conversational AI system significantly improved the composite validity of clinical responses compared to usual search practices, though findings are considered exploratory due to the volunteer-based sample.

Castano-Villegas, N., Monsalve, K., Villa, M. C., Quiros Gomez, O. I., Velasquez, L., Zea, J.2026-09-25
📄 health informatics

Collecting health narratives at scale: A multi-study evaluation of speech-to-text in health surveys

This multi-study evaluation demonstrates that while speech-to-text technology can significantly enrich the length and content of patient health narratives at scale, its adoption varies widely across populations and depends heavily on contextual factors such as privacy, interface design, and individual preferences.

Baumer, A. M., Naoumis, P., Fabian, J., Strukova, S., Wolf, M., Ballouz, T., Farnham, A., Hofmann, V. X. C., Spitale, G. (…)2026-09-25
📄 health informatics

Evaluation of linkage between health, education and social care administrative data for 21 million children in England

This study evaluates the linkage of health, education, and social care data for 21 million children in England, revealing that while over 90% of recent cohorts are successfully linked, significant under-representation persists among children from deprived areas, London residents, and minoritised ethnic groups, highlighting the critical need for researchers to account for these demographic biases in their analyses.

Nguyen, V. G., Lam, J., Stone, T., Blackburn, R., Gilbert, R., Ruiz Nishiki, M., Harron, K.2026-09-22