eprintid: 19831
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/98/31
datestamp: 2024-06-04 14:19:34
lastmod: 2024-06-04 14:19:34
status_changed: 2024-06-04 14:15:59
type: article
metadata_visibility: show
creators_name: Ho, C.S.H.
creators_name: Tan, T.W.K.
creators_name: Khoe, H.C.H.
creators_name: Chan, Y.L.
creators_name: Tay, G.W.N.
creators_name: Tang, T.B.
title: Using an Interpretable Amino Acid-Based Machine Learning Method to Enhance the Diagnosis of Major Depressive Disorder
ispublished: pub
keywords: 3 hydroxykynurenine; alanine; amino acid; antidepressant agent; arginine; aspartic acid; biological marker; citrulline; glutamic acid; glycine; histidine; isoleucine; kynurenine; leucine; methionine; ornithine; phenylalanine; proline; serine; tryptophan; tyrosine; valine; xanthurenic acid, adult; amino acid blood level; Article; binary classification; classification algorithm; controlled study; cross validation; diagnostic accuracy; diagnostic test accuracy study; diagnostic value; feature selection; female; human; liquid chromatography-mass spectrometry; major clinical study; major depression; male; molecular diagnosis; nested cross validation; psychiatric diagnosis; psychopharmacotherapy; receiver operating characteristic; social support; suicide attempt
note: cited By 0
abstract: Background: Major depressive disorder (MDD) is a leading cause of disability worldwide. At present, however, there are no established biomarkers that have been validated for diagnosing and treating MDD. This study sought to assess the diagnostic and predictive potential of the differences in serum amino acid concentration levels between MDD patients and healthy controls (HCs), integrating them into interpretable machine learning models. Methods: In total, 70 MDD patients and 70 HCs matched in age, gender, and ethnicity were recruited for the study. Serum amino acid profiling was conducted by means of chromatography-mass spectrometry. A total of 21 metabolites were analysed, with 17 from a preset amino acid panel and the remaining 4 from a preset kynurenine panel. Logistic regression was applied to differentiate MDD patients from HCs. Results: The best-performing model utilised both feature selection and hyperparameter optimisation and yielded a moderate area under the receiver operating curve (AUC) classification value of 0.76 on the testing data. The top five metabolites identified as potential biomarkers for MDD were 3-hydroxy-kynurenine, valine, kynurenine, glutamic acid, and xanthurenic acid. Conclusions: Our study highlights the potential of using an interpretable machine learning analysis model based on amino acids to aid and increase the diagnostic accuracy of MDD in clinical practice. © 2024 by the authors.
date: 2024
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85187485219&doi=10.3390%2fjcm13051222&partnerID=40&md5=27bb9f95bae79949e5e880127824d1df
id_number: 10.3390/jcm13051222
full_text_status: none
publication: Journal of Clinical Medicine
volume: 13
number: 5
refereed: TRUE
citation:   Ho, C.S.H. and Tan, T.W.K. and Khoe, H.C.H. and Chan, Y.L. and Tay, G.W.N. and Tang, T.B.  (2024) Using an Interpretable Amino Acid-Based Machine Learning Method to Enhance the Diagnosis of Major Depressive Disorder.  Journal of Clinical Medicine, 13 (5).