Long-Short Ensemble Network for Bipolar Manic-Euthymic State Recognition Based on Wrist-worn Sensors

TL;DR

This paper introduces a deep learning ensemble approach using wrist sensor data to accurately distinguish between manic and euthymic states in bipolar disorder patients, aiding early detection.

Contribution

It presents a novel ensemble method combining long and short-term data analysis for automatic mood-state detection from wrist-worn sensors.

Findings

Achieved 91.59% accuracy in mood-state classification

Utilized actigraphy and electrodermal activity data

Demonstrated effectiveness on 47 bipolar patients

Abstract

Manic episodes of bipolar disorder can lead to uncritical behaviour and delusional psychosis, often with destructive consequences for those affected and their surroundings. Early detection and intervention of a manic episode are crucial to prevent escalation, hospital admission and premature death. However, people with bipolar disorder may not recognize that they are experiencing a manic episode and symptoms such as euphoria and increased productivity can also deter affected individuals from seeking help. This work proposes to perform user-independent, automatic mood-state detection based on actigraphy and electrodermal activity acquired from a wrist-worn device during mania and after recovery (euthymia). This paper proposes a new deep learning-based ensemble method leveraging long (20h) and short (5 minutes) time-intervals to discriminate between the mood-states. When tested on 47 bipolar patients, the proposed classification scheme achieves an average accuracy of 91.59% in euthymic/manic mood-state recognition.