Mind the past: A systematic review on psychological autopsy

Psychological Autopsy (PA) has become widespread to the point of being applied in many diverse fields. However, it is difficult to identify a standard model. In this systematic review, we focused on PA studies assessing mental illness as a major risk factor for suicide. The research, performed on Scopus, Embase, and Pubmed to cover the last 20 years led to 321 reports of which 15 met the inclusion criteria. Results confirmed mental illness as the main risk factor for suicide, followed by specific socio-demographic factors and life events. The analysis of methodologies depicted a still highly heterogeneous scenario, especially regarding data collection and variables included. However, concerning psychiatric evaluations, an initial standardization process of PA models emerged. In conclusion, the approach is in evolution, and novel guidelines are needed to promote the application of PA as a fundamental tool to inform suicide prevention efforts and to assist forensic examiners in court.

Machine Learning and Criminal Justice: A Systematic Review of Advanced Methodology for Recidivism Risk Prediction

Recent evolution in the field of data science has revealed the potential utility of machine learning (ML) applied to criminal justice. Hence, the literature focused on finding better techniques to predict criminal recidivism risk is rapidly flourishing. However, it is difficult to make a state of the art for the application of ML in recidivism prediction. In this systematic review, out of 79 studies from Scopus and PubMed online databases we selected, 12 studies that guarantee the replicability of the models across different datasets and their applicability to recidivism prediction. The different datasets and ML techniques used in each of the 12 studies have been compared using the two selected metrics. This study shows how each method applied achieves good performance, with an average score of 0.81 for ACC and 0.74 for AUC. This systematic review highlights key points that could allow criminal justice professionals to routinely exploit predictions of recidivism risk based on ML techniques. These include the presence of performance metrics, the use of transparent algorithms or explainable artificial intelligence (XAI) techniques, as well as the high quality of input data.