“…The broad majority of them used changes in scores of psychotic symptom severity scales, such as the Positive and Negative Syndrome Scale (PANSS) and the Brief Psychiatric Rating Scale (BPRS), as measures of clinical improvement [28-31, 33-35, 39, 41, 43, 44, 46, 48-50, 53, 54]. In many of these studies, ML methods were applied to predict binary outcomes ("response" versus "no response", or "remission" versus "no remission") to antipsychotic treatment [28,29,32,35,39,41,43,44,46,48,49,51,54] while several studies used ML techniques for predicting continuous values such as reduction rates of PANSS and BPRS. Additionally, as the definition of treatment outcome is not merely defined by the symptomatic response, but might base on complex clinical and social domains, other measures and scales assessing specific symptoms and functioning criteria were used as labels in many studies [23, 36-38, 40, 42, 45, 47, 51, 52].…”