Key result
Multiple-layer neural networks provided slightly better discrimination for myocardial injury than single-layer models (AUC 0.77 vs 0.76; P<0.001) with all variables included.
Why the study?
Myocardial injury due to ischaemia within 30 days of non-cardiac surgery is prognostically relevant, motivating the evaluation of machine learning neural networks to predict it and death.
Do multiple-layer neural networks improve prediction of myocardial injury and death within 30 postoperative days in patients undergoing non-cardiac surgery compared to single-layer neural networks?
Cohort (n=24,589)
Do multiple-layer neural networks improve prediction of myocardial injury and death within 30 postoperative days in patients undergoing non-cardiac surgery compared to single-layer neural networks?
Effect estimate: AUC 0.77 (95% CI 0.76-0.78)
Absolute Event Rate: 0.77% vs 0.76%
p-value: p=<0.001
Multiple-layer neural networks provided a statistically significant but clinically modest improvement in discrimination for myocardial injury compared to single-layer models, with no significant difference for predicting death.
Modest improvement in myocardial injury prediction does not support added model complexity in practice; leaves open whether multilayer networks meaningfully advance perioperative risk stratification.
Myocardial injury due to ischaemia within 30 days of non-cardiac surgery is prognostically relevant. We aimed to determine the discrimination, calibration, accuracy, sensitivity and specificity of single-layer and multiple-layer neural networks for myocardial injury and death within 30 postoperative days. We analysed data from 24,589 participants in the Vascular Events in Non-cardiac Surgery Patients Cohort Evaluation study. Validation was performed on a randomly selected subset of the study population. Discrimination for myocardial injury by single-layer vs. multiple-layer models generated areas (95%CI) under the receiver operating characteristic curve of: 0.70 (0.69-0.72) vs. 0.71 (0.70-0.73) with variables available before surgical referral, p < 0.001; 0.73 (0.72-0.75) vs. 0.75 (0.74-0.76) with additional variables available on admission, but before surgery, p < 0.001; and 0.76 (0.75-0.77) vs. 0.77 (0.76-0.78) with the addition of subsequent variables, p < 0.001. Discrimination for death by single-layer vs. multiple-layer models generated areas (95%CI) under the receiver operating characteristic curve of: 0.71 (0.66-0.76) vs. 0.74 (0.71-0.77) with variables available before surgical referral, p = 0.04; 0.78 (0.73-0.82) vs. 0.83 (0.79-0.86) with additional variables available on admission but before surgery, p = 0.01; and 0.87 (0.83-0.89) vs. 0.87 (0.85-0.90) with the addition of subsequent variables, p = 0.52. The accuracy of the multiple-layer model for myocardial injury and death with all variables was 70% and 89%, respectively.
No takes yet. Share an insight, caveat, or question.
Nolde et al. (2023) conducted a cohort in Non-cardiac surgery (n=24,589). Multiple-layer neural networks vs. Single-layer neural networks was evaluated on Discrimination (AUC) for myocardial injury with all variables (AUC 0.77, 95% CI 0.76-0.78, p=<0.001). Multiple-layer neural networks provided slightly better discrimination for myocardial injury than single-layer models (AUC 0.77 vs 0.76; P<0.001) with all variables included.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: