Relative importance of symptoms, cognition, and other multilevel variables for psychiatric disease classifications by machine learning. (August 2019)

• Record Type: Journal Article
• Authors: Walsh-Messinger, Julie; Jiang, Haoran; Lee, Hyejoo; Rothman, Karen; Ahn, Hongshik; Malaspina, Dolores
• Is Part Of: Psychiatry research. Volume 278(2019)
• Page Start: 27
• Page End: 34
• Publication Date: 2019-08
• Subjects: Machine learning -- Nosology -- Schizophrenia -- Schizoaffective disorder -- Major depressive disorder, Bipolar disorder; Psychiatry -- Periodicals; Psychiatry -- periodicals; Psychiatrie -- Périodiques; 616.89
• DOI: 10.1016/j.psychres.2019.03.048
• Languages: English
• ISSNs: 0165-1781

Abstract

Highlights: Machine-learning algorithms estimated importance of multilevel data for diagnostic classification. Symptoms were most influential for differentiating psychiatric cases from healthy controls. Function was most important for separating the schizophrenias from affective disorder cases. Function and paternal age were equally important for separating schizophrenia from all other cases. Misclassified controls had mild symptoms, lower cognition, and/or younger mothers/older fathers. Abstract: This study used machine-learning algorithms to make unbiased estimates of the relative importance of various multilevel data for classifying cases with schizophrenia ( n = 60), schizoaffective disorder ( n = 19), bipolar disorder ( n = 20), unipolar depression ( n = 14), and healthy controls ( n = 51) into psychiatric diagnostic categories. The Random Forest machine learning algorithm, which showed best efficacy (92.9% SD: 0.06), was used to generate variable importance ranking of positive, negative, and general psychopathology symptoms, cognitive indexes, global assessment of function (GAF), and parental ages at birth for sorting participants into diagnostic categories. Symptoms were ranked most influential for separating cases from healthy controls, followed by cognition and maternal age. To separate schizophrenia/schizoaffective disorder from bipolar/unipolar depression, GAF was most influential, followed by cognition and paternal age. For classifying schizophrenia from all other psychiatric disorders, low GAF and paternal age were similarly important, followed by cognition, psychopathology and maternal age. Controls misclassified as schizophrenia cases showed lower nonverbal abilities, mild negative and general psychopathology symptoms, and younger maternal or older paternal age. The importance of symptoms for classification of cases and lower GAF for diagnosing schizophrenia, notably more important and distinct from cognition and symptoms, concurs with current practices. The high importance of parental ages is noteworthy and merits further study.