亲密伴侣杀人案预测模型构建与评价  

Construction and Evaluation of Intimate Partner Homicide Prediction Model

作　　者：吕伟平 廖信彪[2] 任李聚 孔小平[3] 陈燕嫦 常亚斐 罗斌[4] LÜWei-ping;LIAO Xin-biao;REN Li-ju;KONG Xiao-ping;CHEN Yan-chang;CHANG Ya-fei;LUO Bin(Xinxing Public Security Bureau,Xinxing 527400,Guangdong Province,China;Key Laboratory of Fo-rensic Pathology,Ministry of Public Security,PRC,Guangdong Forensic Science Institute,Guangzhou 510000,China;Panyu Branch of Guangzhou Public Security Bureau,Guangzhou 510080,China;Fo-rensic Medicine Center,Sun Yat-sen University,Guangzhou 510080,China)

机构地区：[1]新兴县公安局,广东新兴527400 [2]广东省公安厅刑事技术中心法医病理学公安部重点实验室,广东广州510000 [3]广州市公安局番禺分局,广东广州510080 [4]中山大学法医鉴定中心,广东广州510080

出　　处：《法医学杂志》2024年第6期582-588,共7页Journal of Forensic Medicine

基　　金：广东省刑事技术“双十计划”资助项目(2022GDSSGG05);国家自然科学基金资助项目(81671866);广东省自然科学基金资助项目(2016A030313223,2017A0313469)。

摘　　要：目的分析亲密伴侣杀人(intimate partner homicide,IPH)案的独立影响因素,构建IPH预测模型,为案犯刻画提供依据。方法收集广东省2014年1月1日—2020年12月31日法院已判决命案资料共476例作为建模数据,根据案犯与被害人是否为亲密伴侣将案例分为IPH组(n=180)和非亲密伴侣杀人(nonintimate partner homicide,N-IPH)组(n=296)。采用Logistic回归构建模型,通过受试者操作特征(receiver operating characteristic,ROC)曲线分析对模型进行评价并绘制列线图。采用十折交叉验证法进行内部验证。随机收集国内非广东省2011年1月1日—2020年12月31日的法院判决书126例进行外部验证。结果通过多因素Logistic回归分析,最终筛选出7个变量纳入模型。模型Hosmer-Lemeshow拟合优度检验结果为χ^(2)=13.158,P=0.068。ROC曲线下面积(area under the curve,AUC)为0.939(95%CI:0.919~0.959),cutoff值为0.292,敏感度为0.900,特异度为0.865,校准曲线在理想曲线附近。十折交叉验证结果显示准确率为0.863,Kappa值为0.708,外部验证结果显示AUC为0.922(95%CI:0.872~0.971),cut-off值为0.292,敏感度为0.890,特异度为0.886,校准曲线趋于理想曲线。结论基于法医现场学指标构建的IPH模型预测能力良好,准确性和稳定性可靠,可为案犯刻画提供科学方法。Objective To analyze the independent influencing factors of intimate partner homicide(IPH)cases,construct an IPH prediction model,and provide a basis for criminal profiling.Methods A total of 476 convicted homicide cases in Guangdong Province from January 1,2014,to December 31,2020,were collected as modeling dataset.They were divided into the IPH group(n=180)and the non-intimate partner homicide(N-IPH)group(n=296)based on whether the offender and victim were intimate partners.Logistic regression was used to build the model,the model was evaluated through the receiver operating characteristic(ROC)curve analysis and a nomogram was drawn.Internal validation was conducted using ten-fold cross-validation method.A total of 126 court judgments from outside Guangdong Province from January 1,2011,to December 31,2020,were randomly collected for external validation.Results Through multi-factor Logistic regression analysis,7 variables were ultimately selected for inclusion in the model.The Hosmer-Lemeshow goodness of fit test result of the model wasχ^(2)=13.158,P=0.068.The ROC area under the curve(AUC)of the model was 0.939(95%CI:0.919-0.959),the cut-off value was 0.292,the sensitivity was 0.900,and the specificity was 0.865.The calibration curve was close to the ideal curve.The ten-fold cross-validation showed the accuracy of 0.863 and a Kappa value of 0.708.The external validation results showed an AUC of 0.922(95%CI:0.872-0.971),a cut-off value of 0.292,a sensitivity of 0.890,and a specificity of 0.886.The calibration curve tended to the ideal curve.Conclusion The IPH prediction model based on forensic field indicators has good predictive ability,reliable accuracy and stability,and can provide a scientific method for criminal profiling.

关 键 词：法医病理学 亲密伴侣杀人 预测模型 案犯刻画 

分 类 号：R89[医药卫生—法医学] DF795.1[医药卫生—临床医学] D919.1[政治法律—诉讼法学]