A validation study has shown that a new artificial intelligence (AI)-based image analysis tool, iQ-Solutions MS Report (IQ-MS; SNAC, Camperdown, Australia), significantly outperforms standard radiology reports in detecting multiple sclerosis (MS) disease activity in real-world clinical settings.

The study involved 397 magnetic resonance imaging (MRI) scan pairs of 282 unique MS patients with a mean disease duration of 13.1 years and a median Expanded Disability Status Scale (EDSS) of 1.5. The majority of study scans were performed on 1 of 3 different scanners at different MRI centers.

Investigators found that IQ-MS more sensitively detected new or enlarging brain lesions associated with MS (93.3%) compared to standard clinical radiology reports (58.3%), with only a minor drop in specificity (97.6% vs. 98.8%). The AI tool also showed equivalence with a core clinical trial imaging lab in measuring lesion activity and brain volume loss (93.3% vs. 85.0%).

The validation of AI-based image quantitation that can enhance the accuracy of qualitative radiology reports may lead to more precise treatment management for MS patients.

Source: Barnett M, Wang D, Beadnall H, et al. A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis. NPJ Digit Med. 2023;6(196). doi:10.1038/s41746-023-00940-6