Başaran Fatma, Duru Pınar
Department of Midwifery, Faculty of Health Sciences, Ağrı İbrahim Çeçen University, Ağrı, Turkey.
Department of Public Health Nursing, Faculty of Health Sciences, Eskisehir Osmangazi University, Eskisehir, Turkey.
J Eval Clin Pract. 2025 Apr;31(3):e14180. doi: 10.1111/jep.14180. Epub 2024 Oct 13.
Domestic violence against women is a pervasive issue globally, representing a severe violation of human rights and a significant public health concern. The hidden nature of such violence and its frequent underreporting make it a critical area for research. Recent advancements in artificial intelligence offer new avenues for identifying and predicting instances of domestic violence through machine learning (ML) algorithms.
This study aimed to determine the frequency and risk factors of domestic violence against women using ML methods.
With a cross-sectional design, this research was conducted with 630 married women between December 2023 and February 2024. Data were obtained using the 'Demographic Information Form' and the 'HITS Domestic Violence Scale'. Data analysis used six ML algorithms (decision tree, random forest, support vector machine [SVM], logistic regression [LR], Naive Bayes and k-nearest neighbour).
In our study, the rate of women experiencing violence was determined to be 11%, while the duration of marriage, number of children and level of education were identified as significant risk factors. Threat, insult and injury were common risk factors in all algorithms. SVM and LR algorithms were effective models in predicting violence with a 100% accuracy rate. All ML algorithms' sensitivity ranged from 91.12% to 100%, while specificity ranged from 85% to 100%.
The findings of our study demonstrate that ML algorithms have high accuracy rates in determining the frequency and risk factors of domestic violence against women, indicating that they can be used safely.
针对妇女的家庭暴力是全球普遍存在的问题，严重侵犯人权，也是重大的公共卫生问题。此类暴力的隐蔽性及其经常未被报告的情况使其成为一个关键的研究领域。人工智能的最新进展为通过机器学习（ML）算法识别和预测家庭暴力事件提供了新途径。
本研究旨在使用ML方法确定针对妇女的家庭暴力的发生率和风险因素。
采用横断面设计，于2023年12月至2024年2月对630名已婚妇女进行了研究。使用“人口信息表”和“家庭暴力量表”获取数据。数据分析使用了六种ML算法（决策树、随机森林、支持向量机[SVM]、逻辑回归[LR]、朴素贝叶斯和k近邻）。
在我们的研究中，确定遭受暴力的妇女比例为11%，而婚姻持续时间、子女数量和教育程度被确定为重要风险因素。威胁、侮辱和伤害是所有算法中常见的风险因素。SVM和LR算法是预测暴力的有效模型，准确率为100%。所有ML算法的灵敏度范围为91.12%至100%，特异性范围为85%至100%。
我们研究的结果表明，ML算法在确定针对妇女的家庭暴力的发生率和风险因素方面具有很高的准确率，表明它们可以安全使用。
