Learning neuroimaging models from health system-scale data

TL;DR

A new AI model called Prima is developed using a large health system dataset to improve neuroimaging diagnosis and reduce healthcare system strain.

Contribution

Prima is the first vision language model for neuroimaging trained on health system-scale data and tested in real-world clinical settings.

Findings

Prima achieved a mean diagnostic area under the ROC curve of 90.1 ± 5.0% across 52 radiologic diagnoses.

Prima outperformed existing general and medical AI models in neuroimaging tasks.

Prima provides explainable diagnoses, worklist prioritization, and referral recommendations while demonstrating algorithmic fairness.

Abstract

Neuroimaging is a ubiquitous tool for evaluating patients with neurological diseases. The global demand for magnetic resonance imaging (MRI) studies has risen steadily, placing significant strain on health systems, prolonging turnaround times, and intensifying physician burnout [1, 2]. These challenges disproportionately impact patients in low-resource and rural settings [3]. Here, we utilized a large academic health system as a data engine to develop Prima, the first vision language model (VLM) serving as an AI foundation for neuroimaging that supports real-world, clinical MRI studies as input. Trained on over 220,000 MRI studies, Prima uses a hierarchical vision architecture that provides general and transferable MRI features. Prima was tested in a 1-year, prospective, health system-wide study that included 30K MRI studies. Across 52 radiologic diagnoses from the major neurologic disorders, including neoplastic, inflammatory, infectious, and developmental lesions, Prima achieved a mean diagnostic area under the ROC curve of 90.1 ± 5.0%, outperforming other state-of-the-art general and medical AI models by a large margin [4–6]. Prima offers explainable differential diagnoses, worklist priority for radiologists, and clinical referral recommendations across diverse patient demographics and MRI systems. Prima demonstrates algorithmic fairness across sensitive groups and can help mitigate health system biases, such as prolonged turnaround times for low-resource populations. These findings highlight the transformative potential of health system-scale VLMs and Prima’s role in advancing AI-driven healthcare.

Figures