Objective:

To examine the role of AI in identifying, recording, conveying, and responding to indicators of escalation in intimate partner violence (IPV) and femicide prevention across various institutional contexts.

Approach:

Key Findings:

• 4,099 entries were identified; 125 publications were included in the evidence map.
• AI techniques were primarily used for detection, classification, record linkage, risk stratification, and decision support across various institutional contexts.
• The literature showed limited representation of femicide, lethality, and severe escalation topics.
• Few studies investigated implementation, human oversight, and ethical considerations such as privacy and fairness.

Interpretation:

AI may assist in recognizing and coordinating risk indicators but cannot replace human judgment or survivor-focused practices.

Limitations:

• The review highlighted a lack of comprehensive studies on the implementation of AI in IPV contexts, particularly regarding ethical concerns such as privacy and fairness.

Conclusion:

AI should be viewed as a supportive tool within human-driven frameworks for risk recognition rather than a standalone solution.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.