A zero-cost, EHR-integrated AI tool significantly boosts dementia detection in primary care clinics without adding clinician workload.
Key Details
- 1AI tool analyzes EHRs using NLP to identify dementia risk markers.
- 2Combined with a brief patient survey (QDRS), detection rates increased by 31% over standard care in a >5,000 patient RCT.
- 3Led to a 41% increase in follow-up diagnostic assessments (e.g., neuroimaging, cognitive testing).
- 4No additional physician time or licensing fee; open-source, deployable within any EHR system with proper staffing.
- 5Trial conducted at 9 U.S. health centers and results published in JAMA Network Open.
Why It Matters
Demonstrates how scalable, passive digital diagnostics can integrate with standard practice, improving early dementia detection and increasing equitable access, especially with no extra clinician time or cost. While not imaging-based, the approach underlines the growing convergence between AI, digital health records, and automated disease screening relevant to radiology-AI professionals.
Source
EurekAlert
Related News
•EurekAlert
HKUST Releases Misalignment-Resistant GenAI for Virtual Pathology Staining
HKUST researchers created a generative AI tool that enables high-fidelity virtual staining in histopathology even with imperfectly aligned training image pairs.
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.