@article{ref1,
title="A deep learning approach for predicting antidepressant response in major depression using clinical and genetic biomarkers",
journal="Frontiers in psychiatry",
year="2018",
author="Lin, Eugene and Kuo, Po-Hsiu and Liu, Yu-Li and Yu, Younger W-Y and Yang, Albert C. and Tsai, Shih-Jen",
volume="9",
number="",
pages="e290-e290",
abstract="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 <i>ABCA13</i> rs4917029, <i>BNIP3</i> rs9419139, <i>CACNA1E</i> rs704329, <i>EXOC4</i> rs6978272, <i>GRIN2B</i> rs7954376, <i>LHFPL3</i> rs4352778, <i>NELL1</i> rs2139423, <i>NUAK1</i> rs2956406, <i>PREX1</i> rs4810894, and <i>SLIT3</i> rs139863958) which were associated with antidepressant treatment response. Furthermore, we pinpointed 10 SNPs (including <i>ARNTL</i> rs11022778, <i>CAMK1D</i> rs2724812, <i>GABRB3</i> rs12904459, <i>GRM8</i> rs35864549, <i>NAALADL2</i> rs9878985, <i>NCALD</i> rs483986, <i>PLA2G4A</i> rs12046378, <i>PROK2</i> rs73103153, <i>RBFOX1</i> rs17134927, and <i>ZNF536</i> 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.<p /> <p>Language: en</p>",
language="en",
issn="1664-0640",
doi="10.3389/fpsyt.2018.00290",
url="http://dx.doi.org/10.3389/fpsyt.2018.00290"
}