A machine learning approach to predict quality of life changes in patients with Parkinson's Disease

Abstract

Objective: Parkinson disease (PD) is a progressive neurodegenerative disorder with an annual incidence of approximately 0.1%. While primarily considered a motor disorder, increasing emphasis is being placed on its non-motor features. Both manifestations of the disease affect quality of life (QoL), which is captured in part II of the Unified Parkinson's Disease Rating Scale (UPDRS-II). While useful in the management of patients, it remains challenging to predict how QoL will change over time in PD. The goal of this work is to explore the feasibility of a machine learning algorithm to predict QoL changes in PD patients. Methods: In this retrospective cohort study, patients with at least 12 months of follow-up were identified from the Parkinson's Progression Markers Initiative database (N = 630) and divided into two groups: those with and without clinically significant worsening in UPDRS-II (n = 404 and n = 226, respectively). We developed an artificial neural network using only UPDRS-II scores, to predict whether a patient would clinically worsen or not at 12 months from follow-up. Results: Using UPDRS-II at baseline, at 2 months, and at 4 months, the algorithm achieved 90% specificity and 56% sensitivity. Interpretation: A learning model has the potential to rule in patients who may exhibit clinically significant worsening in QoL at 12 months. These patients may require further testing and increased focus.

Artificial intelligence of imaging and clinical neurological data for predictive, preventive and personalized (P3) medicine for Parkinson Disease: The NeuroArtP3 protocol for a multi-center research study

“…Machine learning approaches are computer-based statistical approaches that can help clinicians in classifying patients according to several variables at the same time and to predict outcomes through AI algorithms. Despite the difficulties of implementing such approaches because of the need for big amounts of homogenous data, the use of machine learning might represent a key cornerstone in developing and applying P3 approaches for complex diseases such as PD [ 20 ], as well as personalized medicine in general [ 18 ].…”

“…Through the use of mathematical models, Artificial Intelligence (AI) and machine learning, on a large and common set of data, the project’s goal is to identify patterns of clinical and neuropsychological variables as predictors of the trajectories of PD patients [ 20 ]. In particular, the study consists of an initial retrospective phase, aimed at generating preventive, predictive and personalized algorithms, whose value and accuracy will be verified in the subsequent prospective phase, analyzing the correspondence between the mathematical predictions and the actual clinical course of the patients.…”

“…In this perspective the adoption of a P3 (predictive, preventive and personalized) medicine approach seems to be pivotal, as recent literature highlights [18][19][20].…”