IJPDS International Journal of Population Data Science

Loughborough University researchers have developed an artificial intelligence (AI) tool that identifies the key human factors influencing maternity care outcomes, supporting ongoing efforts to improve safety for mothers and babies.

Developed by AI and data scientist Professor Georgina Cosma and Professor Patrick Waterson, an expert in human factors and complex systems, the new ‘I-SIRch’ tool analyses maternity incident reports to highlight human factors – such as communication, teamwork, and decision-making – that may have influenced care outcomes.

When an adverse maternity incident occurs in England, detailed investigation reports are produced to identify opportunities for learning and enhancing safety.

These reports provide valuable insights into clinical aspects that impacted care, such as health conditions, procedures, and tests. However, identifying the human factors involved is often more challenging, as they tend to be complex and nuanced.

To extract human factor insights from incident reports, experts must carry out manual reviews. This process is resource-intensive, time-consuming, and relies on individual interpretation and expertise, which can lead to varying conclusions.

The I-SIRch tool addresses these challenges by automatically identifying and categorising human factors within an incident report.

The AI model was trained and tested on data from 188 real maternity incident reports. It successfully identified human factors in each report and analysed them collectively to highlight specific areas where additional support could be beneficial.

"AI has transformed our analysis of maternity safety reports. We've uncovered crucial insights far quicker than manual methods," said Professor Cosma.

“This has enabled us to gather a comprehensive understanding of where there are areas for improvement in maternity care, and these insights will help identify ways to enhance patient safety and improve outcomes for mothers and babies."

Insights from the reports

Teamwork and communication emerged as the most frequently identified human factors across all the analysed reports, underscoring the importance of effective collaboration and clear information exchange among healthcare professionals and patients in promoting safety and quality in maternity care.

The analysis also emphasised the importance of thorough patient evaluations – including assessments, investigations, and screenings – as well as the impact of individual patient characteristics, such as birth history and conditions like pre-eclampsia, on care outcomes.

I-SIRch identified challenges related to medical technology use and staff performance, indicating that ongoing training and support could improve care outcomes. The tool also provided insights into how COVID-19 affected maternity services, underscoring the need for adaptability in practices.

Additionally, the AI tool indicated that certain human factors might have a greater impact on mothers from minority ethnic backgrounds. However, due to the limited number of reports that included ethnicity data, further research is required to reach definitive conclusions.

Professor Waterson said: “Our work opens up new possibilities for understanding the complex interplay between social, technical, and organisational factors influencing maternal safety and population health outcomes. 

“The need for such research was highlighted in the Ockenden Review, which examined maternity care and set to improve safety and care quality in maternity services.

“We hope to build on this research by testing I-SIRch on a larger, more diverse dataset, specifically focusing on reports involving mothers from ethnic minority backgrounds. 

“This expanded testing is essential to validate the tool’s effectiveness and further understand the challenges faced by mothers from ethnic minority backgrounds in maternity care.

“By taking a more comprehensive view of maternal healthcare delivery, we can develop targeted interventions to improve maternal outcomes for all mothers and babies.”  

The Health Services Safety Investigations Body (HSSIB) investigates patient safety concerns across England to improve NHS and independent healthcare at a national level.

When asked about the research, Dr Jonathan Back, a safety insights analyst at HSSIB, said: "I-SIRch could help analysts working in health and care to identify where there are inequalities, maximising learning by bringing together findings from multiple investigations.”

The findings of the I-SIRch project have been published in the International Journal of Population Data Science. The paper can be read in its entirety on the journal’s website.  

The I-SIRch project was jointly funded by the Health Foundation and the NHS AI Lab at the NHS Transformation Directorate and supported by the National Institute for Health and Care Research.

 

Click here to view the full article

Georgina Cosma, Department of Computer Science, School of Science, Loughborough University, Loughborough, United Kingdom and Patrick Waterson, Professor of Human Factors and Complex Systems, School of Design and Creative Arts, Loughborough University, Loughborough, United Kingdom

Singh, M. K., Cosma, G., Waterson, P., Back, J. and Jun, G. T. (2024) “I-SIRch: AI-powered concept annotation tool for equitable extraction and analysis of safety insights from maternity investigations”, International Journal of Population Data Science, 9(2). doi: 10.23889/ijpds.v9i2.2439.