BACKGROUND
Despite the implementation of prevention strategies, family violence continues to be a prevalent issue worldwide. Current strategies have demonstrated mixed success and innovative approaches are needed urgently to prevent the occurrence of family violence and the adverse psychological and physical impacts caused by it. Incorporating artificial intelligence (AI) into prevention strategies is a novel approach that is gaining research attention, particularly in detecting individuals at risk of perpetrating family violence using textual or voice signal data. However, no review to date has collated the extant research regarding how accurate AI is at identifying individuals who are at risk of perpetrating family violence.
OBJECTIVE
The primary aim of this systematic review and meta-analysis is to assess the accuracy of AI models in differentiating between individuals at risk of engaging in family violence versus those who are not using textual or voice signal data.
METHODS
The following databases will be searched from conception to the search date: IEEEexplore, Pubmed, PsycINFO, EBSCOhost (Psychology and Behavioural Sciences collection) and Computers and Applied Sciences Complete. ProQuest Dissertations and Theses A&I will also be used to search the grey literature. In both the data screening and full-text review phases, two researchers will review the returned results and discrepancies in decisions will be resolved through discussion with involvement of a third researcher, if required. Results will be reported in a narrative review. Additionally, a random effects meta-analysis will be conducted using the AUC reported in the included studies.
RESULTS
Systematic searches have not yet begun. The study will document the state of the research concerning the accuracy of AI models in detecting the risk of family violence perpetration using textual or voice signal data. Results will be presented in narrative form. The results of the meta-analysis will be summarised in tabular form and using a forest-plot.
CONCLUSIONS
To the authors knowledge, this will be the first systematic review and meta-analysis to examine the accuracy of AI models in detecting individuals at risk of perpetrating family violence.
CLINICALTRIAL
PROSPERO Registration: CRD42023481174