Cited 0 times in Scipus Cited Count

Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing

DC Field Value Language
dc.contributor.authorLee, DY-
dc.contributor.authorKim, N-
dc.contributor.authorPark, C-
dc.contributor.authorGan, S-
dc.contributor.authorSon, SJ-
dc.contributor.authorPark, RW-
dc.contributor.authorPark, B-
dc.date.accessioned2024-04-04T06:27:34Z-
dc.date.available2024-04-04T06:27:34Z-
dc.date.issued2024-
dc.identifier.issn0165-1781-
dc.identifier.urihttp://repository.ajou.ac.kr/handle/201003/32462-
dc.description.abstractAlthough 20 % of patients with depression receiving treatment do not achieve remission, predicting treatment-resistant depression (TRD) remains challenging. In this study, we aimed to develop an explainable multimodal prediction model for TRD using structured electronic medical record data, brain morphometry, and natural language processing. In total, 247 patients with a new depressive episode were included. TRD-predictive models were developed based on the combination of following parameters: selected tabular dataset features, independent components-map weightings from brain T1-weighted magnetic resonance imaging (MRI), and topic probabilities from clinical notes. All models applied the extreme gradient boosting (XGBoost) algorithm via five-fold cross-validation. The model using all data sources showed the highest area under the receiver operating characteristic of 0.794, followed by models that used combined brain MRI and structured data, brain MRI and clinical notes, clinical notes and structured data, brain MRI only, structured data only, and clinical notes only (0.770, 0.762, 0.728, 0.703, 0.684, and 0.569, respectively). Classifications of TRD were driven by several predictors, such as previous exposure to antidepressants and antihypertensive medications, sensorimotor network, default mode network, and somatic symptoms. Our findings suggest that a combination of clinical data with neuroimaging and natural language processing variables improves the prediction of TRD.-
dc.language.isoen-
dc.subject.MESHAntidepressive Agents-
dc.subject.MESHBrain-
dc.subject.MESHDepression-
dc.subject.MESHHumans-
dc.subject.MESHMagnetic Resonance Imaging-
dc.subject.MESHNatural Language Processing-
dc.titleExplainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing-
dc.typeArticle-
dc.identifier.pmid38430816-
dc.subject.keywordBrain imaging-
dc.subject.keywordMachine learning-
dc.subject.keywordNatural language processing-
dc.subject.keywordTreatment-resistant depression-
dc.contributor.affiliatedAuthorSon, SJ-
dc.contributor.affiliatedAuthorPark, RW-
dc.contributor.affiliatedAuthorPark, B-
dc.type.localJournal Papers-
dc.identifier.doi10.1016/j.psychres.2024.115817-
dc.citation.titlePsychiatry research-
dc.citation.volume334-
dc.citation.date2024-
dc.citation.startPage115817-
dc.citation.endPage115817-
dc.identifier.bibliographicCitationPsychiatry research, 334. : 115817-115817, 2024-
dc.identifier.eissn1872-7123-
dc.relation.journalidJ001651781-
Appears in Collections:
Journal Papers > School of Medicine / Graduate School of Medicine > Psychiatry & Behavioural Sciences
Journal Papers > School of Medicine / Graduate School of Medicine > Biomedical Informatics
Files in This Item:
38430816.pdfDownload

qrcode

해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse