Hierarchical Machine Learning Classification of Parkinsonian Disorders using Saccadic Eye Movements: A Development and Validation Study

TL;DR

This study introduces a novel hierarchical machine learning approach analyzing raw saccadic eye movement waveforms to accurately distinguish Parkinson's Disease, PSP, and healthy controls, outperforming traditional methods and enabling improved clinical diagnosis.

Contribution

The paper presents a new calibration-free waveform analysis combined with hierarchical machine learning for individual-level classification of Parkinsonian disorders, surpassing conventional metrics.

Findings

High AUROCs (0.92-0.97) for PD vs PSP discrimination

Effective classification of de novo PD, established PD, PSP, and controls

Outperforms conventional saccade analysis methods

Abstract

Discriminating between Parkinson's Disease (PD) and Progressive Supranuclear Palsy (PSP) is difficult due to overlapping symptoms, especially early on. Saccades (rapid conjugate eye movements between fixation points) are affected by both diseases but conventional saccade analyses exhibit group level differences only. We hypothesized analyzing entire saccade raw time series waveforms would permit superior individual level discrimination between PD, PSP, and healthy controls (HC). 13,309 saccadic eye movements from 127 participants were analyzed using a novel, calibration-free waveform analysis and hierarchical machine learning framework. Individual saccades were classified based on which trained model could reconstruct each waveform with minimum error, indicating the most likely condition. A hierarchical classifier then predicted overall status (recently diagnosed and medication-naive 'de novo' PD, 'established' PD on antiparkinsonian medication, PSP, and healthy controls) by combining each participant's saccade results. This approach substantially outperformed conventional metrics, achieving high AUROCs distinguishing de novo PD from PSP (0.92-0.97), de novo PD from HC (0.72-0.89), and PSP from HC (0.90-0.95), while the conventional model showed limited performance (AUROC range: 0.45-0.75). This calibration-free waveform analysis sets a new standard for precise saccadic classification of PD, PSP, and HC, increasing potential for clinical adoption, remote monitoring, and screening.