Using Data and AI to Create Better Health Care Systems

Academic medical centers could transform patient care by adopting principles from learning health systems principles, according to researchers from Weill Cornell Medicine and the University of California, San Diego. In this approach, information from electronic health records, clinical trials and day-to-day hospital operations is analyzed in real-time to uncover insights that continuously improve patient care.

The perspective, published in npj Health Systems, reasons that a smarter, more efficient and more equitable model of care can be created by harnessing existing data to support system-wide learning. Yet, adoption of this model remains limited.

"Integrating diverse databases is part of creating a dynamic health care system," said lead author Dr. Peter Steel, associate professor of clinical emergency medicine at Weill Cornell Medicine and an emergency medicine physician at NewYork-Presbyterian/Weill Cornell Medical Center. "Practitioners will be able to more easily and quickly see what’s working and what’s not; and what’s driving up unnecessary costs."

Also, contributing to the perspective are Dr. Robert Harrington, the Stephen and Suzanne Weiss Dean of Weill Cornell Medicine, and Dr. Christopher Longhurst and Dr. Gabriel Wardi, both from the University of California, San Diego.

The authors say establishing a learning health system is especially important now as academic institutions are facing financial strain caused by rising research costs, declining margins and growing patient expectations. The perspective is a call to action for academic health centers to make systemic changes by rethinking how they generate and apply knowledge.

The idea behind this approach is not new - medical researchers first envisioned learning health systems when hospitals transitioned from paper to electronic health records. However, electronic health records were designed primarily for the convenience of clinicians and patients, rather than for researchers and quality improvement initiatives. Data siloes further complicate establishing learning health systems. Information - patient histories, lab results, imaging or billing records - is stored in separate, disconnected systems that don’t communicate with each other.

Consequently, it can often take years to gather and analyze data needed to improve patient care, the authors noted. A functioning learning health system could shrink this time frame to weeks while maintaining ethical, patient-centric research and using strong security systems to ensure patient privacy. Those insights can then be used to revise treatment guidelines, enhance patient safety and spur innovations.

Part of the issue, the authors argue, is insufficient integration between the people focused on clinical care, research and education. Ideally, future doctors could be taught how to use data to efficiently ask and answer clinical questions that will bring together different stakeholders to collaborate.

"A learning health system, powered by AI, has the potential to elevate clinical care and outcomes," said Dr. Harrington. "When we enable future clinicians to learn from every clinical encounter, we can improve quality and effectiveness in ways we couldn't before."

Beyond data organization and analysis, the cost of implementing a learning health system may reach tens of millions of dollars. But the long-term return may be strategic: Years after implementation, health care organizations that successfully utilize this approach could become significantly more competitive than those that do not, the authors said.

Despite the challenges, the recent advances in artificial intelligence make learning health systems adoption more critical. Patients are starting to expect doctors to leverage AI to deliver personalized, proactive care, but AI depends on clean, well-structured, real-world data. "AI can only fulfill its promise if it’s built on a foundation of learning infrastructure," Dr. Steel said.

AI tools can analyze huge volumes of medical data quickly, helping doctors spot early warning signs of illness, streamline operations and make faster, more individualized decisions. A learning health system enables essential quality control, ensuring AI tools are continuously monitored for safety, bias and effectiveness.

"Academic medical centers face a rapidly changing funding landscape, even as the costs of technological transformation and administration in health care continue to rise," Dr. Steel said. "Implementing the learning health system is no longer a theoretical goal, but a strategic imperative."

Steel PA, Wardi G, Harrington RA, Longhurst CA.
Learning health system strategies in the AI era.
npj Health Systems. 2025. doi: 10.1038/s44401-025-00029-0

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...

AI Medical Receptionist Modernizing Doct…

A virtual medical receptionist named "Cassie," developed through research at Texas A&M University, is transforming the way patients interact with health care providers. Cassie is a digital-human assistant created by Humanate...

Highland Marketing Announced as Official…

Highland Marketing has been named, for the second year running, the official communications partner for HETT Show 2025, the UK's leading digital health conference and exhibition. Taking place 7-8 October...

AI Detects Hidden Heart Disease Using Ex…

Mass General Brigham researchers have developed a new AI tool in collaboration with the United States Department of Veterans Affairs (VA) to probe through previously collected CT scans and identify...

MHP-Net: A Revolutionary AI Model for Ac…

Liver cancer is the sixth most common cancer globally and a leading cause of cancer-related deaths. Accurate segmentation of liver tumors is a crucial step for the management of the...

Northern Ireland Completes Nationwide Ro…

Go-lives at Western and Southern health and social care trusts mean every pathology service is using the same laboratory information management system; improving efficiency and quality. An ambitious technology project to...