Photo Credit: DC Studio
The Following is a summary of “Automated Imaging Differentation for Parkinsonism,” Published in the March 2025 Issue of Jama Neurology by Váillancourt et al.
Mri with Disease-Specific Machine Learning May Help Differentiate PD, MSA, and PSP. The Prospective Study is Needed to Confirm Its Diagnostic Value.
Researchers Drived the Retrospective Study to Evaluate the Accuracy of Automated Imaging Differentiation for Parkinsonism (AIDP) Using 3-T Diffusion Mri and Support Vector Machine (SVM) Learning.
They conducted a prospective multicenter cohort study across 21 sites from July 2021 to January 2024. Patients with pd, msa, and psp meta stablished Criteria, and their diagnoses were confirmed by 3 blinded neurologists. Participants Were Assigned to the Training or Independent Testing Set.
The Results Showed That 316 Patients Were Screened, and 249 (Mean Age 67.8 (7.7) Years; 155 ills (62.2%)) Met Inclusion Criteria – 99 Had PD, 53 Had MSA, and 97 Had PSP. The Retrospective Cohort of 396 Patients (Mean Age 65.8 (8.9) Years; 234 ills (59.1%)) Included 211 with PD, 98 with msa, and 87 with psp. PATIES WERE ASSIGNED TO TRAINING SET (78%; 104 PROSPECTIVE, 396 RETROSPTIVE) OR AN INDEPENDENT TESTING SET (22%; 145 PROSPECTIVE: 60 PD, 27 MSA, 58 PSP; MEAN AGE 67.4 (7.7) YEARS; 95 evils (65.5%)). The Model Differentiated PD vs Athpical Parkinsonism (Auroc 0.96; Positive Predictive Value (PPV) 0.91; Negative Predictive Value (NPV), 0.83), MSA VS PSP (AUROC 0.98; PPV 0.98; NPV 0.81), PD VS MSA (AUROC 0.98; PPV 0.97; NPV 0.97), and PD VS PSP (AUROC 0.98; ppv 0.92; NPV 0.98). AIDP Predictions Were Neuropatholically Confirmed in 46 of 49 Brains (93.9%).
Investigators met the primary endpoints, confirm Aidp’s Diagnostic Value. Results Supported its use in diagnosis Common Parkinsonian Syndromes.
Source: jamanetwork.com/journals/jamaneurology/fullarticle/2831631
