Show simple item record

Pharmacogenomics-Driven Prediction of Antidepressant Treatment Outcomes: A Machine-Learning Approach With Multi-trial Replication.

dc.contributor.author Athreya, Arjun P
dc.contributor.author Neavin, Drew
dc.contributor.author Carrillo-Roa, Tania
dc.contributor.author Skime, Michelle
dc.contributor.author Biernacka, Joanna
dc.contributor.author Frye, Mark A
dc.contributor.author Rush, A John
dc.contributor.author Wang, Liewei
dc.contributor.author Binder, Elisabeth B
dc.contributor.author Iyer, Ravishankar K
dc.contributor.author Weinshilboum, Richard M
dc.contributor.author Bobo, William V
dc.date.accessioned 2022-04-13T23:29:46Z
dc.date.available 2022-04-13T23:29:46Z
dc.date.issued 2019-10
dc.identifier.issn 0009-9236
dc.identifier.issn 1532-6535
dc.identifier.uri https://hdl.handle.net/10161/24806
dc.description.abstract We set out to determine whether machine learning-based algorithms that included functionally validated pharmacogenomic biomarkers joined with clinical measures could predict selective serotonin reuptake inhibitor (SSRI) remission/response in patients with major depressive disorder (MDD). We studied 1,030 white outpatients with MDD treated with citalopram/escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS; n = 398), Sequenced Treatment Alternatives to Relieve Depression (STAR*D; n = 467), and International SSRI Pharmacogenomics Consortium (ISPC; n = 165) trials. A genomewide association study for PGRN-AMPS plasma metabolites associated with SSRI response (serotonin) and baseline MDD severity (kynurenine) identified single nucleotide polymorphisms (SNPs) in DEFB1, ERICH3, AHR, and TSPAN5 that we tested as predictors. Supervised machine-learning methods trained using SNPs and total baseline depression scores predicted remission and response at 8 weeks with area under the receiver operating curve (AUC) > 0.7 (P < 0.04) in PGRN-AMPS patients, with comparable prediction accuracies > 69% (P ≤ 0.07) in STAR*D and ISPC. These results demonstrate that machine learning can achieve accurate and, importantly, replicable prediction of SSRI therapy response using total baseline depression severity combined with pharmacogenomic biomarkers.
dc.language eng
dc.publisher Wiley
dc.relation.ispartof Clinical pharmacology and therapeutics
dc.relation.isversionof 10.1002/cpt.1482
dc.subject Humans
dc.subject Citalopram
dc.subject Serotonin Uptake Inhibitors
dc.subject Genetic Markers
dc.subject Remission Induction
dc.subject Depressive Disorder, Major
dc.subject Polymorphism, Single Nucleotide
dc.subject Algorithms
dc.subject Adult
dc.subject Female
dc.subject Male
dc.subject Biomarkers, Pharmacological
dc.subject Genome-Wide Association Study
dc.subject Machine Learning
dc.subject Pharmacogenomic Variants
dc.subject Pharmacogenomic Testing
dc.subject Clinical Decision Rules
dc.title Pharmacogenomics-Driven Prediction of Antidepressant Treatment Outcomes: A Machine-Learning Approach With Multi-trial Replication.
dc.type Journal article
duke.contributor.id Rush, A John|0491499
dc.date.updated 2022-04-13T23:29:45Z
pubs.begin-page 855
pubs.end-page 865
pubs.issue 4
pubs.organisational-group Duke
pubs.organisational-group School of Medicine
pubs.publication-status Published
pubs.volume 106
duke.contributor.orcid Rush, A John|0000-0003-2004-2382


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record