High Accuracy but Low Explainability: The Challenge of Explainable Artificial Intelligence in Multiple Sclerosis Assessment From Magnetic Resonance Imaging Radiology Reports

Key Points

• High accuracy in artificial intelligence assessments demonstrates diagnostic potential for multiple sclerosis, but explainability challenges remain.
• A notable finding showed AI algorithms maintain over 90% accuracy in interpreting MRI reports for multiple sclerosis.
• Assessment analyzed multiple sclerosis cases using advanced artificial intelligence techniques paired with radiology reports.
• Highlights the necessity for tools that provide greater transparency in AI decision-making, as current models struggle with explainability.