Machine Learning Models of Voxel-Level [F] Fluorodeoxyglucose Positron Emission Tomography Data Excel at Predicting Progressive Supranuclear Palsy Pathology.

OBJECTIVE

To determine whether a machine learning model of voxel level [f]fluorodeoxyglucose positron emission tomography (PET) data could predict progressive supranuclear palsy (PSP) pathology, as well as outperform currently available biomarkers.

METHODS

One hundred and thirty-seven autopsied patients with PSP (n = 42) and other neurodegenerative diseases (n = 95) who underwent antemortem [f]fluorodeoxyglucose PET and 3.0 Tesla magnetic resonance imaging (MRI) scans were analyzed. A linear support vector machine was applied to differentiate pathological groups with sensitivity analyses performed to assess the influence of voxel size and region removal. A radial basis function was also prepared to create a secondary model using the most important voxels. The models were optimized on the main dataset (n = 104), and their performance was compared with the magnetic resonance parkinsonism index measured on MRI in the independent test dataset (n = 33).

RESULTS

The model had the highest accuracy (0.91) and F-score (0.86) when voxel size was 6mm. In this optimized model, important voxels for differentiating the groups were observed in the thalamus, midbrain, and cerebellar dentate. The secondary models found the combination of thalamus and dentate to have the highest accuracy (0.89) and F-score (0.81). The optimized secondary model showed the highest accuracy (0.91) and F-scores (0.86) in the test dataset and outperformed the magnetic resonance parkinsonism index (0.81 and 0.70, respectively).

INTERPRETATION

The results suggest that glucose hypometabolism in the thalamus and cerebellar dentate have the highest potential for predicting PSP pathology. Our optimized machine learning model outperformed the best currently available biomarker to predict PSP pathology. ANN NEUROL 2025;98:410-420.