A Deep Learning Approach for Predicting Antidepressant Response in Major Depression Using Clinical and Genetic Biomarkers

Bibliographic Data

ID15519987
AuthorsEugene Lin (0000-0001-6984-2159, China Medical University, corresponding author), Po-Hsiu Kuo (0000-0003-0365-3587, National Taiwan University), Yu-Li Liu (0000-0002-7852-4678, National Health Research Institutes), Younger W-Y Yu, Albert C Yang (0000-0003-2794-9649, National Yang Ming Chiao Tung University), Shih‐Jen Tsai (0000-0002-9987-022X, National Yang Ming Chiao Tung University, corresponding author)
Year2018
Volume9
Pages290-290
Publication date2018-07-06
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueFrontiers in Psychiatry (JOURNAL)
Journal identifiersISSN: 1664-0640 • E-ISSN: 1664-0640
PublisherFrontiers Media (PUBLISHER • CH)
DOI10.3389/fpsyt.2018.00290
PMID30034349
OpenAlexW2807780860
LanguageEN
Citations received3
References cited55

In the wake of recent advances in scientific research, personalized medicine using deep learning techniques represents a new paradigm. In this work, our goal was to establish deep learning models which distinguish responders from non-responders, and also to predict possible antidepressant treatment outcomes in major depressive disorder (MDD). To uncover relationships between the responsiveness of antidepressant treatment and biomarkers, we developed a deep learning prediction approach resulting from the analysis of genetic and clinical factors such as single nucleotide polymorphisms (SNPs), age, sex, baseline Hamilton Rating Scale for Depression score, depressive episodes, marital status, and suicide attempt status of MDD patients. The cohort consisted of 455 patients who were treated with selective serotonin reuptake inhibitors (treatment-response rate = 61.0%; remission rate = 33.0%). By using the SNP dataset that was original to a genome-wide association study, we selected 10 SNPs (including ABCA13 rs4917029, BNIP3 rs9419139, CACNA1E rs704329, EXOC4 rs6978272, GRIN2B rs7954376, LHFPL3 rs4352778, NELL1 rs2139423, NUAK1 rs2956406, PREX1 rs4810894, and SLIT3 rs139863958) which were associated with antidepressant treatment response. Furthermore, we pinpointed 10 SNPs (including ARNTL rs11022778, CAMK1D rs2724812, GABRB3 rs12904459, GRM8 rs35864549, NAALADL2 rs9878985, NCALD rs483986, PLA2G4A rs12046378, PROK2 rs73103153, RBFOX1 rs17134927, and ZNF536 rs77554113) in relation to remission. Then, we employed multilayer feedforward neural networks (MFNNs) containing 1-3 hidden layers and compared MFNN models with logistic regression models. Our analysis results revealed that the MFNN model with 2 hidden layers (area under the receiver operating characteristic curve (AUC) = 0.8228 ± 0.0571; sensitivity = 0.7546 ± 0.0619; specificity = 0.6922 ± 0.0765) performed maximally among predictive models to infer the complex relationship between antidepressant treatment response and biomarkers. In addition, the MFNN model with 3 hidden layers (AUC = 0.8060 ± 0.0722; sensitivity = 0.7732 ± 0.0583; specificity = 0.6623 ± 0.0853) achieved best among predictive models to predict remission. Our study indicates that the deep MFNN framework may provide a suitable method to establish a tool for distinguishing treatment responders from non-responders prior to antidepressant therapy

Antidepressant · Biology · Depression (economics · Gene · Genome-wide association study · Genotype · Logistic regression · Machine learning · Major depressive disorder · Psychiatry · Receiver operating characteristic · Single-nucleotide polymorphism · Bioinformatics and Genomic Networks · Computational Drug Discovery Methods · Computer Science · Genetic Associations and Epidemiology · Medicine · Psychology · Artificial Intelligence · Genetics · Internal Medicine · Oncology

Tools

Open DOISci-HubOpen Access