Using text mining and machine learning for detection of child abuse

TL;DR

This paper presents a machine learning and text mining approach to analyze unstructured child health data for detecting potential child abuse, aiding public health efforts in the Netherlands.

Contribution

It introduces a novel application of text mining and machine learning techniques to identify abuse patterns in unstructured medical notes for child protection.

Findings

High classification accuracy in detecting abuse cases

Effective implementation of decision support API in a Dutch municipality

Demonstrates potential for improving child abuse detection processes

Abstract

Abuse in any form is a grave threat to a child's health. Public health institutions in the Netherlands try to identify and prevent different kinds of abuse, and building a decision support system can help such institutions achieve this goal. Such decision support relies on the analysis of relevant child health data. A significant part of the medical data that the institutions have on children is unstructured, and in the form of free text notes. In this research, we employ machine learning and text mining techniques to detect patterns of possible child abuse in the data. The resulting model achieves a high score in classifying cases of possible abuse. We then describe our implementation of the decision support API at a municipality in the Netherlands.