Identifying Variation in the Newborn Life Support Procedure: An Automated Method

Tan, Alfian; Remenyte-Prescott, Rasa; Egede, Joy; Valstar, Michel; Sharkey, Don

Abstract

This research is conducted for developing an automated method to recognize variations in the Newborn Life Support (NLS) procedure. Compliance with the NLS standard guideline is essential to prevent any adverse consequences for the newborn. Video recordings of resuscitation are frequently used in research to identify types of variations and understand how to minimize the unwanted ones. Despite their benefits, it takes a significant amount of time and human resources to manually evaluate the procedure from videos. Therefore, an automated method could help. In this study, a variation recognition based on action recognition technique is built. In the first step, automatic object segmentation is performed to every NLS action image. In the second stage, a number of features involving proportion of medical objects availability and their movement, as well as association among actions are extracted and fed into machine learning models. The results show that the strategy of considering this actions' relationship succeeded in improving the model performance. However, the whole recognition system still works fairly and only for the wet towel removal step in the NLS procedure, but it has been useful to inform the adherence of recorded procedure to the NLS guideline. This study is an initial work that will advance toward the integration of automated variation recognition with reliability modelling work on the NLS procedure.

Citation

Tan, A., Remenyte-Prescott, R., Egede, J., Valstar, M., & Sharkey, D. (2023). Identifying Variation in the Newborn Life Support Procedure: An Automated Method. In M. P. Brito, T. Aven, P. Baraldi, M. Čepin, & E. Zio (Eds.), Proceedings of the 33rd European Safety and Reliability Conference (ESREL 2023) (607-614)

• Presentation Conference Type: Edited Proceedings
• Conference Name: 33rd European Safety and Reliability Conference (ESREL 2023)
• Start Date: Sep 3, 2023
• End Date: Sep 7, 2023
• Acceptance Date: Aug 28, 2023
• Online Publication Date: Sep 7, 2023
• Publication Date: Sep 7, 2023
• Deposit Date: Sep 18, 2023
• Publicly Available Date: Sep 18, 2023
• Pages: 607-614
• Series Title: European Conference on Safety and Reliability (ESREL)
• Book Title: Proceedings of the 33rd European Safety and Reliability Conference (ESREL 2023)
• ISBN: 9789811880728
• Keywords: Newborn Life Support; Image Segmentation; Action Recognition; Reliability in Healthcare
• Public URL: https://nottingham-repository.worktribe.com/output/25360915
• Related Public URLs: https://www.esrel2023.com/