Machine Learning and Post-operative outcomes

Discussions
, , ,
1

Kia Ora!

I’m new to the e-health forum and was hoping to get some perspective from any experts in the periop field.

I’m an Auckland anaesthesia trainee looking at presenting this article at my dept journal club next month.

Multicentre validation of a machine learning model for predicting respiratory failure after noncardiac surgery
Br J Anaesth. 2024 Jun;132(6):1304-1314.doi: 10.1016/j.bja.2024.01.030. Epub 2024 Feb 26.

I was wondering what people’s perspectives and experience were of using such technology on a clinical basis.

So far it’s been interesting to see that the model has essentially come up with 8 variables that we already know to be strong predictors of outcome in surgery, although the benefit seems to be that this removes a lot of subjective assessment from the clinician side.

Many thanks!

Andrew

3 Likes
2

Welcome to the eHealth Forum, Andrew!

This looks like a good example of where AI / machine learning can potentially helpful.

Doing this here in NZ would be challenging due to the lack of EHR infrastructure. Also, to be actually useful, it would need to be very carefully implemented (like any decision support).