Assessing Different Machine Learning Algorithms to Identify Traumatic Cardiac Arrest.

AI / informaticsAnnals of epidemiology· Aug 2026

Assessing Different Machine Learning Algorithms to Identify Traumatic Cardiac Arrest.

Signe Amalie Wolthers, Mehdi Parviz, Caroline Kamuk Ostenfeldt … Helle Collatz Christensen

Read paper

Resuscitation & Cardiac ArrestAI / informaticsClinical practiceQ2IF 2.4

BERT algorithm identified traumatic cardiac arrest with 0.96 recall, highest among models tested

Assessing Different Machine Learning Algorithms to Identify Traumatic Cardiac Arrest.

Signe Amalie Wolthers … Helle Collatz Christensen

Annals of epidemiology · Aug 2026

Purpose

This study evaluated five machine learning classifiers' ability to identify traumatic cardiac arrest in the Danish Cardiac Arrest Registry, which currently relies on manual review.

Methods

This retrospective study employed split sampling to train and test models using medical records of cardiac arrest patients from 2016 to 2021.

n = 30,171 medical records

0.96

Results

0.96

BERT caught nearly all trauma arrest cases, missing the fewest

n = 30,171 medical records

More results

30,171 medical records included, with 985 involving traumatic cardiac arrests.

The histogram gradient boosting model achieved the highest F1-score of 0.62, with precision (positive predictive value) of 0.61 and recall (sensitivity) of 0.62.

More results

For histogram gradient boosting and random forest, the increasing presence of "car", "thorax", and "head" was linked to trauma.

“

Conclusion · 1 of 3

This study represents the first steps towards using machine learning algorithms to support manual validation of the Danish Cardiac Arrest Registry.

Conclusion · 2 of 3

Histogram gradient boosting yielded the best overall results; however, the BERT model demonstrated significantly improved recall in detecting trauma cases.

Conclusion · 3 of 3

Hence, applying the BERT model to the validation would substantially reduce the present workload.

Assessing Different Machine Learning Algorithms to Identify Traumatic Cardiac Arrest.

Assessing Different Machine Learning Algorithms to Identify Traumatic Cardiac Arrest.

Related papers