이동윤 (아주대학교 의과대학) | 한빛사논문 > 한빛사

한빛사논문

조회492

아주대학교 의과대학

CV File 104 kb

Psychiatry Res., online 25 February 2024, 115817 | https://doi.org/10.1016/j.psychres.2024.115817 Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing

Dong Yun Lee ^a,b#, Narae Kim ^a,c#, ChulHyoung Park^a,b, Sujin Gan ^c, Sang Joon Son ^d, Rae Woong Park ^{a,c ‡}, Bumhee Park ^{a,e ‡}

^aDepartment of Biomedical Informatics, Ajou University School of Medicine, Suwon, South Korea

^bDepartment of Medical Sciences, Graduate School of Ajou University, Suwon, Republic of Korea

^cDepartment of Biomedical Sciences, Graduate School of Ajou University, Suwon, Republic of Korea

^dDepartment of Psychiatry, Ajou University School of Medicine, Suwon, South Korea

^eOffice of Biostatistics, Medical Research Collaborating Center, Ajou Research Institute for innovative medicine, Ajou University Medical Center, Suwon, Republic of Korea

^#Those authors contributed equally as co-first author.

^‡Those authors contributed equally as co-corresponding author.

Abstract

Although 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.

논문정보

형식Research article
게재일2024년 02월 (BRIC 등록일 2024-02-29)
연구진국내 연구진
분야 의약학 > 응용의학

댓글 작성 로그인

CV 열람하기

연락처 보기