A signature-based machine learning model for bipolar disorder and borderline personality disorder

TL;DR

This study uses a signature-based machine learning approach on smartphone mood data to accurately distinguish bipolar disorder, borderline personality disorder, and healthy controls, and predict future mood states with high accuracy.

Contribution

It introduces a novel signature-based machine learning method for analyzing complex mood time series in psychiatry, improving classification and prediction accuracy.

Findings

75% correct classification of participant groups

Over 70% accuracy in mood prediction across groups

Highest prediction accuracy in healthy volunteers (89-98%)

Abstract

Mobile technologies offer opportunities for higher resolution monitoring of health conditions. This opportunity seems of particular promise in psychiatry where diagnoses often rely on retrospective and subjective recall of mood states. However, getting actionable information from these rather complex time series is challenging, and at present the implications for clinical care are largely hypothetical. This research demonstrates that, with well chosen cohorts (of bipolar disorder, borderline personality disorder, and control) and modern methods, it is possible to objectively learn to identify distinctive behaviour over short periods (20 reports) that effectively separate the cohorts. Participants with bipolar disorder or borderline personality disorder and healthy volunteers completed daily mood ratings using a bespoke smartphone app for up to a year. A signature-based machine learning model was used to classify participants on the basis of the interrelationship between the different mood items assessed and to predict subsequent mood. The signature methodology was significantly superior to earlier statistical approaches applied to this data in distinguishing the participant three groups, clearly placing 75% into their original groups on the basis of their reports. Subsequent mood ratings were correctly predicted with greater than 70% accuracy in all groups. Prediction of mood was most accurate in healthy volunteers (89-98%) compared to bipolar disorder (82-90%) and borderline personality disorder (70-78%).