Individual risk prediction: Comparing random forests with Cox proportional-hazards model by a simulation study.

With big data becoming widely available in healthcare, machine learning algorithms such as random forest (RF) that ignores time-to-event information and random survival forest (RSF) that handles right-censored data are used for individual risk prediction alternatively to the Cox proportional hazards (Cox-PH) model. We aimed to systematically compare RF and RSF with Cox-PH. RSF with three split criteria [log-rank (RSF-LR), log-rank score (RSF-LRS), maximally selected rank statistics (RSF-MSR)]; RF, Cox-PH, and Cox-PH with splines (Cox-S) were evaluated through a simulation study based on real data.

Validation of the Patient Health Questionnaire-4 (PHQ-4) to screen for depression and anxiety in the Greek general population.

Objective: The Patient Health Questionnaire-4 (PHQ-4) is an ultra-brief self-report screening scale for depression and anxiety with promising psychometric properties; however, its reliability and validity have not been investigated in Greece yet. The objective of the current study was to investigate the reliability and validity of the PHQ-4 and to establish a cut-off score to identify depression and anxiety in the Greek general population.

Methods: The reliability of the PHQ-4 was assessed using a random sample of 204 students from Athens, Greece.