Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings.

Autor: Athreya AP; Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA., Brückl T; Department of Translational Research Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany., Binder EB; Department of Translational Research Psychiatry, Max Planck Institute of Psychiatry, Munich, Germany., John Rush A; Duke-National University of Singapore, Singapore, Singapore.; Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, NC, USA.; Department of Psychiatry, Texas Tech University-Health Sciences Center, Midland, TX, USA., Biernacka J; Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA., Frye MA; Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, USA., Neavin D; Garvan Institute of Medical Research, Sydney, NSW, Australia., Skime M; Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, USA., Monrad D; Department of Statistics, University of Illinois at Urbana-Champaign, Champaign, IL, USA., Iyer RK; Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, IL, USA., Mayes T; Department of Psychiatry, University of Texas Southwestern Medical Center, Dallas, TX, USA., Trivedi M; Department of Psychiatry, University of Texas Southwestern Medical Center, Dallas, TX, USA., Carter RE; Department of Health Sciences Research, Mayo Clinic, Jacksonville, FL, USA., Wang L; Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA., Weinshilboum RM; Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA., Croarkin PE; Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, USA., Bobo WV; Department of Psychiatry and Psychology, Mayo Clinic, Jacksonville, FL, USA. Bobo.william@mayo.edu.
Jazyk: angličtina
Zdroj: Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology [Neuropsychopharmacology] 2021 Jun; Vol. 46 (7), pp. 1272-1282. Date of Electronic Publication: 2021 Jan 15.
DOI: 10.1038/s41386-020-00943-x
Abstrakt: Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians' ability to accurately predict a specific patient's eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% (p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% (p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.
Databáze: MEDLINE
Externí odkaz: