Clinical psychoinformatics: a novel approach to behavioral states and mental health care driven by machine learning

Tetsuya Yamamoto, Junichiro Yoshimoto, Jocelyne Alcaraz-Silva, Eric Murillo-Rodríguez, Claudio Imperatori, Sérgio Machado, Henning Budde

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Machine learning (ML) is a branch of artificial intelligence technology that has received considerable attention in recent years. It is a computational strategy to discover the regularities inherent in multidimensional data sets, allowing us to build predictive models focused on individual states. Therefore, it may help increase the efficiency and sophistication of assessment and aid the selection of optimal intervention methods in clinical practice, including cognitive behavioral therapy. In this paper, we first review the framework of the ML approach, its differences from statistics, and its features. Subsequently, we summarize the main research topics where ML approaches have been applied in the field of mental health and introduce some examples of their applications that may contribute to research in clinical psychology and cognitive behavioral therapy. Finally, the limitations of the ML approach are discussed, as well as its potential for future applications.

Original languageEnglish
Title of host publicationMethodological Approaches for Sleep and Vigilance Research
PublisherElsevier
Pages255-279
Number of pages25
ISBN (Electronic)9780323852357
ISBN (Print)9780323903349
DOIs
Publication statusPublished - 01-01-2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Medicine(all)
  • Neuroscience(all)

Fingerprint

Dive into the research topics of 'Clinical psychoinformatics: a novel approach to behavioral states and mental health care driven by machine learning'. Together they form a unique fingerprint.

Cite this