US Edition
Generalizability Assessment of AI Models Across Hospitals in a Low-Middle and High Income Country
- Researchers at York University conducted a study published in JAMA Network Open that evaluated the performance of AI models across seven major medical centers within the Greater Toronto region.
- The study investigated the impact of differences between the data used to develop AI models and the actual clinical data encountered in practice, revealing how such mismatches can result in unsafe AI predictions and increased risks to patients.
- The researchers used GEMINI's data of over 143,000 patient encounters and applied proactive, continual, and transfer learning to detect and mitigate data shifts.
- Lead author Vallijah Subasri explained that their work identifies changes in data over time, evaluates how these changes can harm the effectiveness of AI models, and offers approaches to address and reduce such negative consequences.
- The study offers practical methods for maintaining AI robustness and fairness in clinical settings, enabling safer deployment of AI models across diverse hospitals.
11 Articles
11 Articles
Generalizability assessment of AI models across hospitals in a low-middle and high income country
The integration of artificial intelligence (AI) into healthcare systems within low-middle income countries (LMICs) has emerged as a central focus for various initiatives aiming to improve healthcare access and delivery quality. In contrast to high-income countries (HICs), which often possess the resources and infrastructure to adopt innovative healthcare technologies, LMICs confront resource limitations such as insufficient funding, outdated inf…
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 published today in JAMA Network Open from York University found proactive, continual and transfer learning strategies for AI models to be key in mitigating data shifts and subsequent harms.
Study Finds Learning Strategies Can Improve AI Model Adaptability in Greater Toronto Area Hospitals
A study published in *JAMA Network Open* identifies spe […] The post Study Finds Learning Strategies Can Improve AI Model Adaptability in Greater Toronto Area Hospitals first appeared on GeneOnline News. The post Study Finds Learning Strategies Can Improve AI Model Adaptability in Greater Toronto Area Hospitals appeared first on GeneOnline News.
New Study Reveals Targeted Learning Strategies Boost AI Model Performance
In the rapidly evolving landscape of healthcare technology, the integration of artificial intelligence (AI) models into clinical settings promises transformative improvements in patient outcomes and hospital efficiency. However, a critical challenge arises when the data used to train these AI algorithms does not accurately represent the dynamic realities of clinical environments. Researchers from York University have unveiled pivotal findings th…
Local Opinions on Artificial Intelligence in Healthcare: A Scoping Rev
Applying artificial intelligence (AI) in healthcare presents a significant opportunity to improve public health in low- and middle-income countries (LMICs). However, the successful implementation of such technologies depends not only on these countries’...
Coverage Details
Bias Distribution
- 50% of the sources are Center
To view factuality data please Upgrade to Premium
Ownership
To view ownership data please Upgrade to Vantage
