• Home
  • Search
  • Incremental learning and granular computing from evolving data streams: An application to speech-based bipolar disorder diagnosis
  • Cite Icon3
  • https://doi.org/10.1016/j.fss.2024.109205Copy DOI Icon

Incremental learning and granular computing from evolving data streams: An application to speech-based bipolar disorder diagnosis

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We apply an evolving granular-computing modeling approach, called evolving Optimal Granular System (eOGS), to bipolar mood disorder (BD) diagnosis based on speech data streams. The eOGS online learning algorithm reveals information granules in the flow and design the structure and parameters of a granular rule-based model with a certain degree of interpretability based on acoustic attributes obtained from phone calls made over 7 months to the Psychiatry department of a hospital. A multi-objective programming problem that trades-off information specificity, model compactness, and numerical and granular error indices is presented. Spectral and prosodic attributes are ranked and selected based on a hybrid Pearson-Spearman correlation coefficient. Low attribute-class correlation, ranging from 0.03 to 0.07, is observed, as well as high class overlap, which is typical in the psychiatric field. eOGS models for BD recognition overcome alternative computational-intelligence models, namely, Dynamic Evolving Neural-Fuzzy Inference System (DENFIS) and Fuzzy-set-Based evolving Modeling (FBeM-Gauss), by a small margin in both best and average cases; followed by eXtended Takagi-Sugeno (xTS) and evolving Takagi Sugeno (eTS) types of models. The proposed eOGS model using only 8 of the original acoustic attributes, and about 15 ‘If-Then’ inference rules, has exhibited the best root mean square error, 0.1361, and 91.8% accuracy in sharp BD class estimates. Granules associated to linguistic labels and a granular input-output map offer human understandability with relation to the inherent process of generating class estimates. Linguistically readable eOGS rules may assist physicians in explaining symptoms and making a diagnosis.

Similar Papers
  • Research Article
  • Citations26

Mental Health Treatment Received by Youths in the Year Before and After a New Diagnosis of Bipolar Disorder

  • Aug 01, 2009
  • Psychiatric Services
  • Mark Olfson +4
  • Research Article
  • Citations135

Subjective and Objective Indicators of Recovery in Severe Mental Illness: a Cross-Sectional Study

  • Jul 10, 2009
  • International Journal of Social Psychiatry
  • Chris Lloyd +2
  • Research Article
  • Citations11

Cohort profile: the Swedish National Quality Register for bipolar disorder(BipoläR)

  • Dec 01, 2022
  • BMJ Open
  • Erik Pålsson +8
  • PDF
  • Research Article
  • Citations1

Identification of the role of immune-related genes in the diagnosis of bipolar disorder with metabolic syndrome through machine learning and comprehensive bioinformatics analysis

  • Oct 04, 2023
  • Frontiers in Psychiatry
  • Jing Shen +4
  • Research Article
  • Citations1

Differentiating Recurrent Unipolar Depressive Disorder from Bipolar Affective Disorder as a diagnostic code within the Coventry IPU 3-8 (Affective Disorders).

  • Jan 01, 2017
  • Frontiers in Psychiatry
  • Sazgar Hamad
  • Research Article
  • Citations37

Using Electronic Health Record-Based Tools To Screen for Bipolar Disorder in Primary Care Patients With Depression

  • May 01, 2012
  • The Journal of the American Board of Family Medicine
  • J M Gill +3
  • Research Article
  • Citations1

Bipolar Disorder Often Misdiagnosed In Children, Expert Says

  • Jul 05, 2002
  • Psychiatric News
  • Jim Rosack
  • Research Article
  • Citations2

Special Report: Bipolar Disorder II—Frequently Neglected, Misdiagnosed

  • Mar 01, 2023
  • Psychiatric News
  • Trisha Suppes +2
  • Research Article

Bipolar affective disorder occurring with psychopharmacotherapy-induced manic phases

  • Apr 23, 2024
  • Zhurnal nevrologii i psikhiatrii imeni S.S. Korsakova
  • A.S Shteinberg +3
  • PDF
  • Research Article
  • Citations22

Affective lability as a prospective predictor of subsequent bipolar disorder diagnosis: a systematic review

  • Nov 01, 2021
  • International Journal of Bipolar Disorders
  • Rosie H Taylor +3
  • PDF
  • Research Article

Difficulties associated with the diagnosis of bipolar affective disorder in a 16-year-old boy treated in the past for ADHD and ODD – case study

  • Mar 01, 2020
  • Current Problems of Psychiatry
  • Izabela Chojnowska-Ćwiąkała +3
  • Research Article
  • Citations33

Mortality trends in external causes of death in people with mental health disorders in Sweden, 1987-2010.

  • Mar 01, 2018
  • Scandinavian Journal of Public Health
  • Jonas Hällgren +3
  • Research Article
  • Citations21

Thwarted interpersonal needs and suicide ideation: Comparing psychiatric inpatients with bipolar and non-bipolar mood disorders.

  • Sep 19, 2016
  • Psychiatry Research
  • Nathanael J Taylor +5
  • Research Article

A Study of Instrumental Activities of Daily Living of Patients having Bipolar Affective Disorder and Its Relationship with their Subjective Well Being and Self Efficacy

  • Jan 01, 2018
  • Bipolar Disorder: Open Access
  • Laxmi Kumari +1
  • Research Article
  • Citations472

"Cade's disease" and beyond: misdiagnosis, antidepressant use, and a proposed definition for bipolar spectrum disorder.

  • Mar 01, 2002
  • The Canadian Journal of Psychiatry
  • S Nassir Ghaemi +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.