Maternity Incident Investigation
Maternity incident investigation aims to improve maternal safety and equity by analyzing reports of adverse events to identify systemic issues and contributing factors. Current research utilizes natural language processing (NLP) techniques, such as topic modeling and intelligent multi-document summarization, often incorporating machine learning models like BART and k-means clustering, to analyze large volumes of unstructured data and reveal disparities in care across different ethnic groups. This work highlights the importance of considering human factors alongside biomedical data in understanding and addressing these disparities, ultimately leading to more effective interventions and improved maternal health outcomes.
Papers
Unveiling Disparities in Maternity Care: A Topic Modelling Approach to Analysing Maternity Incident Investigation Reports
Georgina Cosma, Mohit Kumar Singh, Patrick Waterson, Gyuchan Thomas Jun, Jonathan Back
Intelligent Multi-Document Summarisation for Extracting Insights on Racial Inequalities from Maternity Incident Investigation Reports
Georgina Cosma, Mohit Kumar Singh, Patrick Waterson, Gyuchan Thomas Jun, Jonathan Back