Machine Learning and Risk Assessment: Random Forest Does Not Outperform Logistic Regression in the Prediction of Sexual Recidivism.

Although many studies supported the use of actuarial risk assessment instruments (ARAIs) because they outperformed unstructured judgments, it remains an ongoing challenge to seek potentials for improvement of their predictive performance. Machine learning (ML) algorithms, like random forests, are able to detect patterns in data useful for prediction purposes without explicitly programming them (e.g., by considering nonlinear effects between risk factors and the criterion). Therefore, the current study aims to compare conventional logistic regression analyses with the random forest algorithm on a sample of N = 511 adult male individuals convicted of sexual offenses. Data were collected at the Federal Evaluation Center for Violent and Sexual Offenders in Austria within a prospective-longitudinal research design and participants were followed-up for an average of M = 8.2 years. The Static-99, containing static risk factors, and the Stable-2007, containing stable dynamic risk factors, were included as predictors. The results demonstrated no superior predictive performance of the random forest compared with logistic regression; furthermore, methods of interpretable ML did not point to any robust nonlinear effects. Altogether, results supported the statistical use of logistic regression for the development and clinical application of ARAIs.

Eleven strategies for making reproducible research and open science training the norm at research institutions.

Reproducible research and open science practices have the potential to accelerate scientific progress by allowing others to reuse research outputs, and by promoting rigorous research that is more likely to yield trustworthy results. However, these practices are uncommon in many fields, so there is a clear need for training that helps and encourages researchers to integrate reproducible research and open science practices into their daily work. Here, we outline eleven strategies for making training in these practices the norm at research institutions. The strategies, which emerged from a virtual brainstorming event organized in collaboration with the German Reproducibility Network, are concentrated in three areas: (i) adapting research assessment criteria and program requirements; (ii) training; (iii) building communities. We provide a brief overview of each strategy, offer tips for implementation, and provide links to resources. We also highlight the importance of allocating resources and monitoring impact. Our goal is to encourage researchers - in their roles as scientists, supervisors, mentors, instructors, and members of curriculum, hiring or evaluation committees - to think creatively about the many ways they can promote reproducible research and open science practices in their institutions.

Everything has its price: Foundations of cost-sensitive machine learning and its application in psychology.

Psychology has seen an increase in the use of machine learning (ML) methods. In many applications, observations are classified into one of two groups (binary classification). Off-the-shelf classification algorithms assume that the costs of a misclassification (false positive or false negative) are equal. Because this is often not reasonable (e.g., in clinical psychology), cost-sensitive machine learning (CSL) methods can take different cost ratios into account. We present the mathematical foundations and introduce a taxonomy of the most commonly used CSL methods, before demonstrating their application and usefulness on psychological data, that is, the drug consumption data set (N = 1, 885) from the University of California Irvine ML Repository. In our example, all demonstrated CSL methods noticeably reduced mean misclassification costs compared to regular ML algorithms. We discuss the necessity for researchers to perform small benchmarks of CSL methods for their own practical application. Thus, our open materials provide R code, demonstrating how CSL methods can be applied within the mlr3 framework (https://osf.io/cvks7/). (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Evaluation of the German Version of the Adult Attention-Deficit/Hyperactivity Disorder Self-Report Screening Scale for DSM-5 as a Screening Tool for Adult Attention-Deficit/Hyperactivity Disorder in Primary Care.

Adult attention-deficit/hyperactivity disorder (ADHD) is common, but often undiagnosed. A valid and time-efficient screening tool for primary care is needed. Objective of this study is to evaluate the German version of the Adult ADHD Self-Report Scale for DSM-5 (ASRS-5) and its feasibility, acceptability, and reliability as a screening tool for adult ADHD in primary care. A multi-centered prospective, diagnostic study was performed. We recruited 262 patients in primary care practices and at an ADHD Outpatient Service of a department of psychiatry in Germany. Patients from 18 to 65 years with suspected or diagnosed ADHD were included by medical doctors, as well as non-ADHD patients as "negative controls." Participants filled in the ASRS-5 and a sociodemographic questionnaire. The Integrated Diagnosis of Adult ADHD, revised version (IDA-R) performed by trained interviewers was used for validation. Feasibility, acceptability, and credibility in primary care practices were examined through a semi-structured interview. The German version of the ASRS-5 showed comparable psychometric properties to the English original version (sensitivity 95.6% and specificity 72.3%). For factor structure, a parallel analysis suggested one latent dimension. Performing confirmatory factor analysis, the best fit was achieved for a general factor with one correlated error. Internal consistency results in Raykovs Omega = 0.86 and Cronbach's α = 0.88. The ASRS-5 was assessed positively in terms of feasibility, acceptability, and credibility by interviewed general practitioners. Potential problems were raised for "treatment options," "stigmatization," and "knowledge gaps." In conclusion, the German version of the ASRS-5 offers a promising tool to improve adult ADHD patients' diagnosis and healthcare.

Cognitive reserve in young and old healthy subjects: differences and similarities in a testing-the-limits paradigm with DSST.

Cognitive reserve (CR) is understood as capacity to cope with challenging conditions, e.g. after brain injury or in states of brain dysfunction, or age-related cognitive decline. CR in elderly subjects has attracted much research interest, but differences between healthy older and younger subjects have not been addressed in detail hitherto. Usually, one-time standard individual assessments are used to characterise CR. Here we observe CR as individual improvement in cognitive performance (gain) in a complex testing-the-limits paradigm, the digit symbol substitution test (DSST), with 10 repeated measurements, in 140 younger (20-30 yrs) and 140 older (57-74 yrs) healthy subjects. In addition, we assessed attention, memory and executive function, and mood and personality traits as potential influence factors for CR. We found that both, younger and older subjects showed significant gains, which were significantly correlated with speed of information processing, verbal short-term memory and visual problem solving in the older group only. Gender, personality traits and mood did not significantly influence gains in either group. Surprisingly about half of the older subjects performed at the level of the younger group, suggesting that interindividual differences in CR are possibly age-independent. We propose that these findings may also be understood as indication that one-time standard individual measurements do not allow assessment of CR, and that the use of DSST in a testing-the-limits paradigm is a valuable assessment method for CR in young and elderly subjects.