When an ‘adverse maternity incident’ occurs in England, investigation reports are produced to identify opportunities to improve safety. These detailed reports provide insights into clinical aspects that impacted care, such as health conditions, procedures, and tests.
Related content
Identifying where human factors played a role in these incidents can be difficult, as these are generally complex and nuanced. Currently, this labour-intensive process is carried out manually and is, by its nature, subjective.
By contrast, the AI tool identifies and categorises human factors in reports rapidly. According to the researchers, the AI can analyse multiple reports and spot recurring factors, flagging areas likely to benefit most from additional support.
The AI model was trained and tested on data from 188 real maternity incident reports, successfully identifying human factors in each report. The work is published in the International Journal of Population Data Science (IJPDS).
"AI has transformed our analysis of maternity safety reports. We've uncovered crucial insights far quicker than manual methods," said Georgina Cosma, Professor of AI and Data Science and one of the research leads.
“This has enabled us to gather a comprehensive understanding of where there are areas for improvement in maternity care, and these insights can help identify ways to enhance patient safety and improve outcomes for mothers and babies."
The study found that teamwork and communication were the most frequently identified human factors across all the analysed reports. Analysis also highlighted the importance of thorough patient evaluations – including assessments, investigations, and screenings – as well as staff challenges related to medical technology. The Loughborough team now hopes to secure funding to refine the AI model using a larger, more diverse dataset.
"We are seeking to collaborate with hospitals, healthcare organisations, and investigation bodies to further refine and apply our AI tool to reports,” said Professor Cosma. “These partnerships will help us extract vital intelligence to prevent adverse incidents and ensure the safety of all mothers and babies.
“We also hope to adapt the tool for use with other types of reports, such as adverse police incident reports, where understanding the human factors involved can help prevent future incidents and improve response strategies.”
Heat network to set bar for decarbonising heat
The report is somewhat outdated and seems to give emphasis to hydrogen and carbon capture. Thermal energy sources do not include those for electricity...