Show simple item record

dc.contributor.authorChandler, Chelsea
dc.contributor.authorFoltz, Peter W.
dc.contributor.authorElvevåg, Brita
dc.date.accessioned2022-11-25T11:41:46Z
dc.date.available2022-11-25T11:41:46Z
dc.date.issued2022-05-26
dc.description.abstractObjectives: Machine learning (ML) and natural language processing have great potential to improve effciency and accuracy in diagnosis, treatment recommendations, predictive interventions, and scarce resource allocation within psychiatry. Researchers often conceptualize such an approach as operating in isolation without much need for human involvement, yet it remains crucial to harness human-inthe-loop practices when developing and implementing such techniques as their absence may be catastrophic. We advocate for building ML-based technologies that collaborate with experts within psychiatry in all stages of implementation and use to increase model performance while simultaneously increasing the practicality, robustness, and reliability of the process.<p> <p>Methods: We showcase pitfalls of the traditional ML framework and explain how it can be improved with human-inthe-loop techniques. Specifcally, we applied active learning strategies to the automatic scoring of a story recall task and compared the results to a traditional approach. <p>Results: Human-in-the-loop methodologies supplied a greater understanding of where the model was least confdent or had knowledge gaps during training. As compared to the traditional framework, less than half of the training data were needed to reach a given accuracy. <p>Conclusions: Human-in-the-loop ML is an approach to data collection and model creation that harnesses active learning to select the most critical data needed to increase a model’s accuracy and generalizability more effciently than classic random sampling would otherwise allow. Such techniques may additionally operate as safeguards from spurious predictions and can aid in decreasing disparities that artifcial intelligence systems otherwise propagate.en_US
dc.identifier.citationChandler, Foltz, Elvevåg. Improving the Applicability of AI for Psychiatric Applications through Human-in-the-loop Methodologies. Schizophrenia Bulletin. 2022;48(5):949-957en_US
dc.identifier.cristinIDFRIDAID 2057244
dc.identifier.doi10.1093/schbul/sbac038
dc.identifier.issn0586-7614
dc.identifier.issn1745-1701
dc.identifier.urihttps://hdl.handle.net/10037/27546
dc.language.isoengen_US
dc.publisherOxford University Pressen_US
dc.relation.journalSchizophrenia Bulletin
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2022 The Author(s)en_US
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0en_US
dc.rightsAttribution-NonCommercial 4.0 International (CC BY-NC 4.0)en_US
dc.titleImproving the Applicability of AI for Psychiatric Applications through Human-in-the-loop Methodologiesen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record

Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
Except where otherwise noted, this item's license is described as Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)