Low predictive power of clinical features for relapse prediction after antidepressant discontinuation in a naturalistic setting

Abstract

Background: The risk of relapse after antidepressant medication (ADM) discontinuation is high. Predictors of relapse could guide clinical decision-making, but are yet to be established. Method:We assessed demographic and clinical variables in a longitudinal observational study before antidepressant discontinuation. State-dependent variables were re-assessed either after discontinuation or before discontinuation after a waiting period. Relapse was assessed during six months after discontinuation. We applied logistic general linear models in combination with least absolute shrinkage and selection operator and elastic nets to avoid overfitting in order to identify predictors of relapse and estimated their generalisability using cross-validation. Results:The final sample included 104 patients (age: 34.86 (11.1), 77% female) and 57 healthy controls (age: 34.12 (10.6), 70% female). 36% of the patients experienced a relapse. Treatment by a general practitioner increased the risk of relapse. Although within-sample statistical analyses suggested reasonable sensitivity and specificity, out-of-sample prediction of relapse was at chance level. Residual symptoms increased with discontinuation, but did not relate to relapse. Conclusion and Relevance:Demographic and standard clinical variables appear to carry little predictive power and therefore are of limited use for patients and clinicians in guiding clinical decision-making.Huys QJM, Maia TV, Frank MJ (2016). Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci 19(3), 404-413.Joliat MJ, Schmidt ME, Fava M, Zhang S, Michelson D, Trapp NJ, Miner CM (2004). Long-term treatment outcomes of depression with associated anxiety: efficacy of continuation treatment with fluoxetine. J Clin Psychiatry 65(3), 373-8.Kaymaz N, van Os J, Loonen AJM, Nolen WA (2008). Evidence that patients with single versus recurrent depressive episodes are differentially sensitive to treatment discontinuation: a meta-analysis of placebo-controlled randomized trials. J Clin Psychiatry 69(9), 1423-36. KellerMB, Klerman GL, Lavori PW, Coryell W, Endicott J, Taylor J (1984). Long-term outcome of episodes of major depression: Clinical and public health significance. J Am Med Ass 252, 788-92. Keller MB, Lavori PW, Lewis CE, Klerman GL (1983). Predictors of relapse in major depressive disorder. JAMA 250(24), 3299-3304. Kessler RC, Berglund P, Demler O, Jin R, Koretz D, Merikangas KR, Rush AJ, Walters EE, Wang PS, National Comorbidity Survey Replication (2003). The epidemiology of major depressive disorder: results from the national comorbidity survey replication (NCS-R). JAMA 289(23), 3095-105. Lehr S (2005). Mehrfachwahl-Wortschatz-Intelligenztest MWT-B. Spitta, Balingen, DE. Lépine JP, Briley M (2011). The increasing burden of depression. Neuropsychiatr Dis Treat 7(Suppl 1), 3-7. Lo A, Chernoff H, Zheng T, Lo SH (2015). Why significant variables aren't automatically good predictors. Proc Natl Acad Sci U S A 112(45), 13892-7. McGrath PJ, Stewart JW, Petkova E, Q...

Judging Mental Health Disorders Using Decision Tree Models

“…But just 36.9% of such patients get therapy for it [1]. If we accumulate further reports then we shall notice that the number of folks who are admitted in hospitals every year due to the ailments created by psychological issues, is six times more inclined than the number of folks not getting affected by the ailments created by worry, are three to five times more inclined to visit the physicians than to get admitted in hospitals [2]. If we keep an eye at the report of 2017, we can see that197ꞏ3 million (95% UI 178ꞏ4-216ꞏ4) citizens were affected by psychological ailments in India, counting 45ꞏ7 million (42ꞏ4-49ꞏ8) in the midst of ailments created by dejection and 44ꞏ9 million (41ꞏ2-48ꞏ9) in the midst of ailments created by worry [3,4].…”