Machine learning for the diagnosis accuracy of bipolar disorder: a systematic review and meta-analysis

Yi Pan, Pushi Wang, Bowen Xue, Yanbin Liu, Xinhua Shen, Shiliang Wang, Xing Wang · 2025

Read Machine learning for the diagnosis accuracy of bipolar disorder: a systematic review and meta-analysis by Yi Pan, Pushi Wang, Bowen Xue, Yanbin Liu, Xinhua Shen, Shiliang Wang, Xing Wang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11810903.txt.

Description

Yi Pan and six co-authors pooled evidence on whether machine learning can diagnose bipolar disorder from patient data. Clinical diagnosis is slow and often mistaken for depression at first. They searched four databases to April 2023 and kept eighteen studies covering 3,152 people and twenty-eight models, grading each study's quality with a standard tool.

Against healthy controls, the models caught bipolar disorder with sensitivity near eighty-eight percent and specificity near eighty-nine percent. The harder task, telling bipolar disorder from depression, scored slightly lower, near eighty-four and eighty-two percent. The authors, in a paper whose head is dated 2024, say the numbers support machine learning as a diagnostic aid. They note a limit: nearly all models answer yes-or-no questions, while practice must sort among several conditions at once. Multi-way classifiers, they argue, are what would make these tools clinically useful.

Catalog record

CREATORYi Pan, Pushi Wang, Bowen Xue, Yanbin Liu, Xinhua Shen, Shiliang Wang, Xing Wang
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE27 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11810903

Browse the full library · About the Tower of Babel