New Research Finds Specific Learning Strategies can Enhance AI Model Effectiveness in Hospitals

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. A new study out today from York University found proactive, continual and transfer learning strategies for AI models to be key in mitigating data shifts and subsequent harms.

To determine the effect of data shifts, the team built and evaluated an early warning system to predict the risk of in-hospital patient mortality and enhance the triaging of patients at seven large hospitals in the Greater Toronto Area.

The study used GEMINI, Canada’s largest hospital data sharing network, to assess the impact of data shifts and biases on clinical diagnoses, demographics, sex, age, hospital type, where patients were transferred from, such as an acute care institution or nursing home, and time of admittance. It included 143,049 patient encounters, such as lab results, transfusions, imaging reports and administrative features.

"As the use of AI in hospitals increases to predict anything from mortality and length of stay to sepsis and the occurrence of disease diagnoses, there is a greater need to ensure they work as predicted and don't cause harm," says senior author York University Assistant Professor Elham Dolatabadi of York’s School of Health Policy and Management, Faculty of Health. "Building reliable and robust machine learning models, however, has proven difficult as data changes over time creating system unreliability."

The data to train clinical AI models for hospitals and other health-care settings need to accurately reflect the variability of patients, diseases and medical practices, she adds. Without that, the model could develop irrelevant or harmful predictions, and even inaccurate diagnoses. Differences in patient subpopulations, staffing, resources, as well as unforeseen changes to policy or behaviour, differing health-care practices between hospitals or an unexpected pandemic, can also cause these potential data shifts.

"We found significant shifts in data between model training and real-life applications, including changes in demographics, hospital types, admission sources, and critical laboratory assays," says first author Vallijah Subasri, AI scientist at University Health Network. "We also found harmful data shifts when models trained on community hospital patient visits were transferred to academic hospitals, but not the reverse."

To mitigate these potentially harmful data shifts, the researchers used a transfer learning strategies, which allowed the model to store knowledge gained from learning one domain and apply it to a different but related domain and continual learning strategies where the AI model is updated using a continual stream of data in a sequential manner in response to drift-triggered alarms.

Although machine learning models usually remain locked once approved for use, the researchers found models specific to hospital type which leverage transfer learning, performed better than models that use all available hospitals.

Using drift-triggered continual learning helped prevent harmful data shifts due to the COVID-19 pandemic and improved model performance over time.

Depending on the data it was trained on, the AI model could also have a propensity for certain biases leading to unfair or discriminatory outcomes for some patient groups.

"We demonstrate how to detect these data shifts, assess whether they negatively impact AI model performance, and propose strategies to mitigate their effects. We show there is a practical pathway from promise to practice, bridging the gap between the potential of AI in health and the realities of deploying and sustaining it in real-world clinical environments," says Dolatabadi.

The study is a crucial step towards the deployment of clinical AI models as it provides strategies and workflows to ensure the safety and efficacy of these models in real-world settings.

"These findings indicate that a proactive, label-agnostic monitoring pipeline incorporating transfer and continual learning can detect and mitigate harmful data shifts in Toronto's general internal medicine population, ensuring robust and equitable clinical AI deployment," says Subasri.

Subasri V, Krishnan A, Kore A, Dhalla A, Pandya D, Wang B, Malkin D, Razak F, Verma AA, Goldenberg A, Dolatabadi E.
Detecting and Remediating Harmful Data Shifts for the Responsible Deployment of Clinical AI Models.
JAMA Netw Open. 2025 Jun 2;8(6):e2513685. doi: 10.1001/jamanetworkopen.2025.13685

Most Popular Now

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...

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...

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...

Using Data and AI to Create Better Healt…

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...

AI Tool Set to Transform Characterisatio…

A multinational team of researchers, co-led by the Garvan Institute of Medical Research, has developed and tested a new AI tool to better characterise the diversity of individual cells within...

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...

Human-AI Collectives Make the Most Accur…

Diagnostic errors are among the most serious problems in everyday medical practice. AI systems - especially large language models (LLMs) like ChatGPT-4, Gemini, or Claude 3 - offer new ways...

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...

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...

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...

Groundbreaking TACIT Algorithm Offers Ne…

Researchers at VCU Massey Comprehensive Cancer Center have developed a novel algorithm that could provide a revolutionary tool for determining the best options for patients - both in the treatment...

The Many Ways that AI Enters Rheumatolog…

High-resolution computed tomography (HRCT) is the standard to diagnose and assess progression in interstitial lung disease (ILD), a key feature in systemic sclerosis (SSc). But AI-assisted interpretation has the potential...