Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach
Koutsouleris N, Kahn R, Chekroud A, Leucht S, Falkai P, Wobrock T, Derks E, Fleischhacker W, Hasan A. Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach. The Lancet Psychiatry 2016, 3: 935-946. PMID: 27569526, DOI: 10.1016/s2215-0366(16)30171-7.Peer-Reviewed Original ResearchConceptsFirst-episode psychosisTreatment outcomesEuropean First Episode Schizophrenia TrialKaplan-Meier log-rank analysisLog-rank analysisReal-world careWeeks of treatmentPrevious depressive episodesCommencement of treatmentPoor treatment outcomesFirst-episode sampleBetter treatment outcomesClinical trial designQuality of lifeMeaningful outcome indicatorsHospital eventsMale sexOutcome predictorsDepressive episodeTreatment adherenceFunctional deficitsSchizophrenia trialsSuperior efficacyNew patientsSymptom persistence