Laboratory performance prediction using virtual reality behaviometrics

Abstract

In this study, we show that virtual reality (VR) behaviometrics can be used for the assessment of compliance and physical laboratory skills. Drawing on approaches from machine learning and classical statistics, significant behavioral predictors were deduced from a logistic regression model that classified students and biopharma company employees as experts or novices on pH meter handling with 77% accuracy. Specifically, the game score and number of interactions in VR tasks requiring practical skills were found to be performance predictors. The study provides biopharma companies and academic institutions the possibility of assessing performance using an automatic, reliable, and simple alternative to traditional in-person assessment methods. Integrating the assessment into the training tool renders such laborious post-training assessments unnecessary.