Key result
Deep neural network identifies post-cardiac surgery patients at ~2.7-fold higher readmission or mortality risk.
Why the study?
Machine learning models to predict 30-day readmissions or post-discharge mortality after cardiac surgery using the Australian ANZSCTS Database have limited demonstrated accuracy and require evaluation.
Can machine learning algorithms developed from the ANZSCTS database accurately predict readmissions or post-discharge mortality within 30 days of cardiac surgery?
Observational (n=61,721)
Yes
Can machine learning algorithms developed from the ANZSCTS database accurately predict readmissions or post-discharge mortality within 30 days of cardiac surgery?
Odds Ratio: 2.7 (95% CI 2.2–3.2)
Machine learning models derived solely from a national cardiac surgery database demonstrated limited predictive ability for 30-day readmission or mortality, highlighting the need for additional informative variables like those from electronic medical records.
AIM This study aimed to create machine learning algorithms using the Australian & New Zealand Society of Cardiac & Thoracic Surgeons (ANZSCTS) Database that can predict readmissions or post-discharge mortality within 30 days of cardiac surgery. METHOD Data from 54 public and private Australian hospitals from January 2017 to December 2021 were included in this study. Only coronary artery bypass grafting (CABG), valvular heart surgery, or aortic surgery cases were included for analysis. The primary outcome of this study was the performance of our machine learning models measured using sensitivity, specificity, positive and negative predictive values, accuracy, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve. RESULTS Of the 178,252 patients in the database, 61,721 CABG, valvular heart surgery, and aortic surgery cases were identified. The incidence of 30-day readmission or post-discharge mortality was 10.3% (6,351/61,721). The best-performing model was the deep neural network (AUROC, 0.615). A calibrated version of this model predicted one in five patients at higher risk of readmissions or post-discharge mortality compared with the lowest risk group (2.4× increase in incidence rate and an odds ratio of 2.7 [2.2-3.2]). CONCLUSIONS Using machine learning, models developed from the Australian ANZSCTS Database demonstrated limited predictive ability for readmissions or post-discharge mortality. The ANZSCTS Database may require additional informative variables before models become sufficiently accurate. Individual hospitals or small hospital networks may be best placed to incorporate routinely collected information (such as electronic medical records) alongside ANZSCTS data to create more accurate models.
No takes yet. Share an insight, caveat, or question.
Hui et al. (2026) conducted an observational in Post-cardiac surgery (n=61,721). Machine learning algorithms (deep neural network) vs. Lowest risk group was evaluated on Performance of machine learning models for predicting 30-day readmission or post-discharge mortality (OR 2.7, 95% CI 2.2-3.2). A deep neural network demonstrated limited ability to predict 30-day readmission or mortality after cardiac surgery (AUROC 0.615), though it identified a high-risk cohort (OR 2.7; 95% CI 2.2-3.2).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: