English

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

Machine Learning 2022-04-07 v3 Artificial Intelligence Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2107.00710,
  title  = {Long-Short Ensemble Network for Bipolar Manic-Euthymic State Recognition Based on Wrist-worn Sensors},
  author = {Ulysse Côté-Allard and Petter Jakobsen and Andrea Stautland and Tine Nordgreen and Ole Bernt Fasmer and Ketil Joachim Oedegaard and Jim Torresen},
  journal= {arXiv preprint arXiv:2107.00710},
  year   = {2022}
}

Comments

Published in IEEE Pervasive Computing in 2022. 12 pages + 2. 2 Figures and 3 tables

R2 v1 2026-06-24T03:49:20.442Z