Construction and Evaluation of Intimate Partner Homicide Prediction Model
ObjectiveTo analyze the independent influencing factors of intimate partner homicide （IPH） cases, construct an IPH prediction model, and provide a basis for criminal profiling.MethodsA total of 476 convicted homicide cases in Guangdong Province from January 1, 2014, to December 31, 2020, were collec...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Forensic Medicine
2024-12-01
|
| Series: | Fayixue Zazhi |
| Subjects: | |
| Online Access: | http://www.fyxzz.cn/CN/10.12116/j.issn.1004-5619.2023.431005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850222212880007168 |
|---|---|
| author | LÜ Wei-ping LIAO Xin-biao REN Li-ju KONG Xiao-ping CHEN Yan-chang CHANG Ya-fei LUO Bin |
| author_facet | LÜ Wei-ping LIAO Xin-biao REN Li-ju KONG Xiao-ping CHEN Yan-chang CHANG Ya-fei LUO Bin |
| author_sort | LÜ Wei-ping |
| collection | DOAJ |
| description | ObjectiveTo analyze the independent influencing factors of intimate partner homicide （IPH） cases, construct an IPH prediction model, and provide a basis for criminal profiling.MethodsA 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.ResultsThrough 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 was χ2=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.ConclusionThe 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. |
| format | Article |
| id | doaj-art-6de1e0950e874535a92bf2e1b83ccdf5 |
| institution | OA Journals |
| issn | 1004-5619 |
| language | zho |
| publishDate | 2024-12-01 |
| publisher | Editorial Office of Journal of Forensic Medicine |
| record_format | Article |
| series | Fayixue Zazhi |
| spelling | doaj-art-6de1e0950e874535a92bf2e1b83ccdf52025-08-20T02:06:26ZzhoEditorial Office of Journal of Forensic MedicineFayixue Zazhi1004-56192024-12-0140658258810.12116/j.issn.1004-5619.2023.4310051004-5619（2024）06-0582-07Construction and Evaluation of Intimate Partner Homicide Prediction ModelLÜ Wei-ping0LIAO Xin-biao1REN Li-ju2KONG Xiao-ping3CHEN Yan-chang4CHANG Ya-fei5LUO Bin6Xinxing Public Security Bureau, Xinxing 527400, Guangdong Province, ChinaKey Laboratory of Forensic Pathology, Ministry of Public Security, PRC, Guangdong Forensic Science Institute, Guangzhou 510000, ChinaPanyu Branch of Guangzhou Public Security Bureau, Guangzhou 510080, ChinaPanyu Branch of Guangzhou Public Security Bureau, Guangzhou 510080, ChinaForensic Medicine Center, Sun Yat-sen University, Guangzhou 510080, ChinaForensic Medicine Center, Sun Yat-sen University, Guangzhou 510080, ChinaForensic Medicine Center, Sun Yat-sen University, Guangzhou 510080, ChinaObjectiveTo analyze the independent influencing factors of intimate partner homicide （IPH） cases, construct an IPH prediction model, and provide a basis for criminal profiling.MethodsA 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.ResultsThrough 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 was χ2=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.ConclusionThe 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.http://www.fyxzz.cn/CN/10.12116/j.issn.1004-5619.2023.431005forensic pathologyintimate partner homicideprediction modelcriminal profiling |
| spellingShingle | LÜ Wei-ping LIAO Xin-biao REN Li-ju KONG Xiao-ping CHEN Yan-chang CHANG Ya-fei LUO Bin Construction and Evaluation of Intimate Partner Homicide Prediction Model Fayixue Zazhi forensic pathology intimate partner homicide prediction model criminal profiling |
| title | Construction and Evaluation of Intimate Partner Homicide Prediction Model |
| title_full | Construction and Evaluation of Intimate Partner Homicide Prediction Model |
| title_fullStr | Construction and Evaluation of Intimate Partner Homicide Prediction Model |
| title_full_unstemmed | Construction and Evaluation of Intimate Partner Homicide Prediction Model |
| title_short | Construction and Evaluation of Intimate Partner Homicide Prediction Model |
| title_sort | construction and evaluation of intimate partner homicide prediction model |
| topic | forensic pathology intimate partner homicide prediction model criminal profiling |
| url | http://www.fyxzz.cn/CN/10.12116/j.issn.1004-5619.2023.431005 |
| work_keys_str_mv | AT luweiping constructionandevaluationofintimatepartnerhomicidepredictionmodel AT liaoxinbiao constructionandevaluationofintimatepartnerhomicidepredictionmodel AT renliju constructionandevaluationofintimatepartnerhomicidepredictionmodel AT kongxiaoping constructionandevaluationofintimatepartnerhomicidepredictionmodel AT chenyanchang constructionandevaluationofintimatepartnerhomicidepredictionmodel AT changyafei constructionandevaluationofintimatepartnerhomicidepredictionmodel AT luobin constructionandevaluationofintimatepartnerhomicidepredictionmodel |