Supervised machine learning to predict reduced depression severity in people with epilepsy through epilepsy self-management intervention.

Autor: Camp EJ; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States. Electronic address: Edward.j.camp.18@dartmouth.edu., Quon RJ; Geisel School of Medicine, Dartmouth College, Hanover, NH 03755, United States. Electronic address: Robert.j.Quon.GR@Dartmouth.edu., Sajatovic M; Case Western Reserve University School of Medicine, Cleveland, OH 44106, United States. Electronic address: Martha.Sajatovic@UHhospitals.org., Briggs F; Case Western Reserve University School of Medicine, Cleveland, OH 44106, United States. Electronic address: farren.briggs@case.edu., Brownrigg B; Case Western Reserve University School of Medicine, Cleveland, OH 44106, United States. Electronic address: Brittany.Brownrigg@UHhospitals.org., Janevic MR; Center for Managing Chronic Disease, University of Michigan, Ann Arbor, MI 48109, United States. Electronic address: mjanevic@umich.edu., Meisenhelter S; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States. Electronic address: stephen.meisenhelter.gr@dartmouth.edu., Steimel SA; Geisel School of Medicine, Dartmouth College, Hanover, NH 03755, United States. Electronic address: sarah.a.steimel.gr@dartmouth.edu., Testorf ME; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States; Thayer School of Engineering, Dartmouth College, Hanover, NH 03755, United States. Electronic address: Markus.E.Testorf@Dartmouth.EDU., Kiriakopoulos E; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States. Electronic address: Elaine.T.kiriakopoulos@dartmouth.edu., Mazanec MT; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States. Electronic address: Morgan.T.Mazanec@hitchcock.org., Fraser RT; Department of Rehabilitation Medicine, University of Washington, Seattle, WA 98104, United States. Electronic address: rfraser@uw.edu., Johnson EK; Health Promotion Research Center, University of Washington, Seattle, WA 98105, United States. Electronic address: ericajohnsonphd@uwalumni.com., Jobst BC; Department of Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, NH 03756, United States; Geisel School of Medicine, Dartmouth College, Hanover, NH 03755, United States. Electronic address: Barbara.C.jobst@hitchcock.org.
Jazyk: angličtina
Zdroj: Epilepsy & behavior : E&B [Epilepsy Behav] 2022 Feb; Vol. 127, pp. 108548. Date of Electronic Publication: 2022 Jan 15.
DOI: 10.1016/j.yebeh.2021.108548
Abstrakt: Objective: To develop a classifier that predicts reductions in depression severity in people with epilepsy after participation in an epilepsy self-management intervention.
Methods: Ninety-three people with epilepsy from three epilepsy self-management randomized controlled trials from the Managing Epilepsy Well (MWE) Network integrated research database met the inclusion criteria. Supervised machine learning algorithms were utilized to develop prediction models for changes in self-reported depression symptom severity. Features considered by the machine learning classifiers include age, gender, race, ethnicity, education, study type, baseline quality of life, and baseline depression symptom severity. The models were trained and evaluated on their ability to predict clinically meaningful improvement (i.e., a reduction of greater than three points on the nine-item Patient Health Questionnaire (PHQ-9)) between baseline and follow-up (<=12 weeks) depression scores. Models tested were a Multilayer Perceptron (ML), Random Forest (RF), Support Vector Machine (SVM), Logistic Regression with Stochastic Gradient Descent (SGD), K-nearest Neighbors (KNN), and Gradient Boosting (GB). A separate, outside dataset of 41 people with epilepsy was used in a validation exercise to examine the top-performing model's generalizability and performance with external data.
Results: All six classifiers performed better than our baseline mode classifier. Support Vector Machine had the best overall performance (average area under the curve [AUC] = 0.754, highest subpopulation AUC = 0.963). Our analysis of the SVM features revealed that higher baseline depression symptom severity, study type (i.e., intervention program goals), higher baseline quality of life, and race had the strongest influence on increasing the likelihood that a subject would experience a clinically meaningful improvement in depression scores. From the validation exercise, our top-performing SVM model performed similarly or better than the average SVM model with the outside dataset (average AUC = 0.887).
Significance: We trained an SVM classifier that offers novel insight into subject-specific features that are important for predicting a clinically meaningful improvement in subjective depression scores after enrollment in a self-management program. We provide evidence for machine learning to select subjects that may benefit most from a self-management program and indicate important factors that self-management programs should collect to develop improved digital tools.
Competing Interests: Declaration of interests M.S. has received research grants from the following entities in the past 3 years: Nuromate, Otsuka, Alkermes, International Society for Bipolar Disorders (ISBD), National Institutes of Health (NIH), Centers for Disease Control and Prevention (CDC), and Patient-Centered Outcomes Research Institute (PCORI). She has consulted for: Alkermes, Otsuka, Janssen, Myriad, Health Analytics, and Frontline Medical Communications. She has royalties with: Springer Press, Johns Hopkins University Press, Oxford Press, and UpToDate. She also has CME activities in: American Physician’s Institute, MCM Education, CMEology, Potomac Center for Medical Education, Global Medical Education, Creative Educational Concepts, and Psychopharmacology Institute. B.C.J. has received research funding from the following entities: NIH, National Science Foundation, DARPA, Centers for Disease Control and Prevention, Neuropace, Inc., Harvard-Pilgrim, Inc., and the Diamond Foundation. She serves as Associate Editor for the journal Neurology. She also has received travel support for activities in her roles as Committee Chair and Vice Chair of the Council of Education of the American Epilepsy Society. All other authors have no conflicts of interest to report. We confirm that we have read the Journal’s position on issues involved in ethnical publication and affirm that this report is consistent with those guidelines.
(Copyright © 2022 Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: