IBM uses AI to predict progress of Huntington's disease symptoms

It could help with patient care and, hopefully, treatment.

IBM is using its AI-based health prediction skills to help tackle the challenge of Huntington's disease. The tech firm has teamed up with CHDI Foundation on an artificial intelligence model that can predict when patients will experience Huntington's symptoms and, crucially, determine how rapidly those symptoms will progress. The team used MRI brain scans to train the AI, using signals from white matter (relatively untapped in brain studies) to help the system gauge how cognitive and motor performance will change over time.

The existing understanding of the disease only indicates that symptoms tend to materialize between the ages of 30 and 50, not which symptoms and how they'll evolve.

The researchers are "optimistic" that a single MRI scan could produce more accurate estimates of functional decline across multiple categories. It wouldn't result in better treatment by itself, but it could help Huntington's disease patients prepare for changes. It could also help scientists choose candidates for clinical trials based on the states of their disease. That, in turn, could lead to long-term solutions.