Explainable artificial intelligence in forensics: Realistic explanations for number of contributor predictions of DNA profiles. (January 2022)

• Record Type: Journal Article
• Authors: Veldhuis, Marthe S.; Ariëns, Simone; Ypma, Rolf J.F.; Abeel, Thomas; Benschop, Corina C.G.
• Is Part Of: Forensic science international. Volume 56(2022)
• Publication Date: 2022-01
• Subjects: Number of contributors -- Explainable artificial intelligence -- DNA mixtures -- Machine learning -- Counterfactual explanations; Forensic genetics -- Periodicals; Génétique légale -- Périodiques; Forensic genetics; Electronic journals; Periodicals; 614.1
• DOI: 10.1016/j.fsigen.2021.102632
• Languages: English
• ISSNs: 1872-4973

Abstract

Abstract: Machine learning obtains good accuracy in determining the number of contributors (NOC) in short tandem repeat (STR) mixture DNA profiles. However, the models used so far are not understandable to users as they only output a prediction without any reasoning for that conclusion. Therefore, we leverage techniques from the field of explainable artificial intelligence (XAI) to help users understand why specific predictions are made. Where previous attempts at explainability for NOC estimation have relied upon using simpler, more understandable models that achieve lower accuracy, we use techniques that can be applied to any machine learning model. Our explanations incorporate SHAP values and counterfactual examples for each prediction into a single visualization. Existing methods for generating counterfactuals focus on uncorrelated features. This makes them inappropriate for the highly correlated features derived from STR data for NOC estimation, as these techniques simulate combinations of features that could not have resulted from an STR profile. For this reason, we have constructed a new counterfactual method, Realistic Counterfactuals (ReCo), which generates realistic counterfactual explanations for correlated data. We show that ReCo outperforms state-of-the-art methods on traditional metrics, as well as on a novel realism score. A user evaluation of the visualization shows positive opinions of end-users, which is ultimately the most appropriate metric in assessing explanations for real-world settings. Highlights: We present explanations that can be used for number of contributors predictions. The explanations visualize SHAP values and counterfactual examples. The method for generating counterfactuals is suitable for correlated data. The method creates realistic counterfactuals based on a new realism metric. DNA-experts gain insight into the model predictions.