PhoneMD: Learning to Diagnose Parkinson's Disease from Smartphone Data

TL;DR

This paper introduces a machine learning approach using long-term smartphone data to improve Parkinson's disease diagnosis, potentially serving as a digital biomarker and reducing misdiagnosis.

Contribution

The study develops attentive deep-learning models that leverage smartphone data for Parkinson's diagnosis, achieving high predictive accuracy and identifying meaningful features.

Findings

Achieved AUC of 0.85 in distinguishing Parkinson's from controls

Long-term smartphone data improves diagnostic performance

Models identify relevant features in walking, voice, tapping, and memory data

Abstract

Parkinson's disease is a neurodegenerative disease that can affect a person's movement, speech, dexterity, and cognition. Clinicians primarily diagnose Parkinson's disease by performing a clinical assessment of symptoms. However, misdiagnoses are common. One factor that contributes to misdiagnoses is that the symptoms of Parkinson's disease may not be prominent at the time the clinical assessment is performed. Here, we present a machine-learning approach towards distinguishing between people with and without Parkinson's disease using long-term data from smartphone-based walking, voice, tapping and memory tests. We demonstrate that our attentive deep-learning models achieve significant improvements in predictive performance over strong baselines (area under the receiver operating characteristic curve = 0.85) in data from a cohort of 1853 participants. We also show that our models identify meaningful features in the input data. Our results confirm that smartphone data collected over extended periods of time could in the future potentially be used as a digital biomarker for the diagnosis of Parkinson's disease.