Currently submitted to: JMIR Medical Informatics
Date Submitted: Nov 18, 2019
Open Peer Review Period: Nov 14, 2019 - Jan 9, 2020
(currently open for review)
An algorithm for monitoring childbirth in settings where tracking all parameters in the WHO partograph is not feasible: design and expert validation
After determining the key childbirth monitoring items from experts in childbirth, we designed an algorithm to represent the experts’ suggestions and we validated it.
In this paper we describe the abridged algorithm for labour and delivery (LaD) management and use theoretical case to compare its performance to human childbirth experts.
The LaD algorithm encompasses the tracking of six of the 12 childbirth parameters monitored using the World Health Organisation partograph. It has recommendations on how to manage a patient when parameters are outside the normal ranges. We validated the algorithm with purposively selected experts selecting actions for a stratified sample of patient case scenarios. The experts’ selections were compared to get pairwise sensitivity and false positive rates (FPR) between them and the algorithm.
The mean weighted pairwise sensitivity among experts was 68.2% (StD. 6.95; CI. 59.6, 76.8) while that between the experts and LaD algorithm was 69.4% (StD. 17.95; CI. 47.1, 91.7). The pairwise FPR amongst the experts ranged from 12% to 33% with a mean of 23.9% (CI. 12.6, 35.2) and that between the experts and the algorithm ranged from 18% to 43% (mean 26.3%; CI. 13.3, 39.3). The was a correlation (mean of 0.67) in the actions selected by the expert pairs for the different patient cases with a reliability coefficient 0.91.
The LaD algorithm was more sensitive but with a higher FPR than the childbirth experts, although the differences were not statistically significant. An electronic tool for childbirth monitoring with fewer than WHO-recommended parameters may not be inferior to human experts in labour and delivery clinical decision support.
Request queued. Please wait while the file is being generated. It may take some time.
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.