Brown School, Washington University in St. Louis, 1 Brookings Dr, St. Louis, MO 63130, United States of America.
Brown School, Washington University in St. Louis, 1 Brookings Dr, St. Louis, MO 63130, United States of America.
Child Abuse Negl. 2024 May;151:106706. doi: 10.1016/j.chiabu.2024.106706. Epub 2024 Feb 29.
Early identification of children and families who may benefit from support is crucial for implementing strategies that can prevent the onset of child maltreatment. Predictive risk modeling (PRM) may offer valuable and efficient enhancements to existing risk assessment techniques.
To evaluate the PRM's effectiveness against the existing assessment tool in identifying children and families needing home visiting services.
Children born in hospitals affiliated with the Bridges Maternal Child Health Network in Orange County, California, from 2011 to 2016 (N = 132,216).
We developed a PRM tool by integrating a machine learning algorithm with a linked dataset of birth records and child protection system (CPS) records. To align with the existing assessment tool (baseline model), we limited the predicting features to the information used by the existing tool. The need for home visiting services was measured by substantiated maltreatment allegation reported during the first three years of the child's life.
Of the children born in Bridges Network hospitals between 2011 and 2016, 2.7 % experienced substantiated maltreatment allegations by the age of three. Within the top 30 % of children with high-risk scores, the PRM tool outperformed the baseline model, accurately identifying 75.3 %-84.1 % of all children who would experience maltreatment substantiation, surpassing the baseline model's performance of 46.2 %.
Our study underscores the potential of PRM in enhancing the risk assessment tool used by a prevention program in a child welfare center in California. The findings provide valuable insights to practitioners interested in utilizing data for PRM development, highlighting the potential of machine learning algorithms to generate accurate predictions and inform targeted preventive services.
早期识别可能受益于支持的儿童和家庭对于实施可以预防虐待儿童发生的策略至关重要。预测风险建模（PRM）可能为现有风险评估技术提供有价值且高效的增强。
评估 PRM 在识别需要家庭访问服务的儿童和家庭方面相对于现有评估工具的有效性。
2011 年至 2016 年期间，加利福尼亚州橙县 Bridges 母婴健康网络附属医院出生的儿童（N=132216）。
我们通过将机器学习算法与出生记录和儿童保护系统（CPS）记录的链接数据集集成，开发了 PRM 工具。为了与现有评估工具（基线模型）保持一致，我们将预测特征限制为现有工具使用的信息。家庭访问服务的需求通过孩子生命的头三年报告的经证实的虐待指控来衡量。
在 2011 年至 2016 年期间在 Bridges 网络医院出生的儿童中，有 2.7%的儿童在三岁之前经历过经证实的虐待指控。在高风险评分的前 30%的儿童中，PRM 工具的表现优于基线模型，准确识别了所有经历虐待证实的儿童的 75.3%-84.1%，超过了基线模型的 46.2%的表现。
我们的研究强调了 PRM 在增强加利福尼亚州儿童福利中心预防计划使用的风险评估工具方面的潜力。研究结果为有兴趣利用数据进行 PRM 开发的从业者提供了有价值的见解，突出了机器学习算法生成准确预测和提供有针对性的预防服务的潜力。
