Machine learning is more accurate and biased than risk scoring tools in the prediction of postoperative atrial fibrillation after cardiac surgery
Ho, J. C.; Joshi, S.; Valverde, E.; Wood, K.; Grubb, K. J.; Leal, M. A.; Hertzberg, V. S.
Show abstract
Incidence of postoperative atrial fibrillation (POAF) after cardiac surgery remains high and is associated with adverse patient outcomes. Risk scoring tools have been developed to predict POAF, yet discrimination performance remains moderate. Machine learning (ML) models can achieve better performance but may exhibit performance heterogeneity across race and sex subpopulations. We evaluate 8 risk scoring tools and 6 ML models on a heterogeneous cohort derived from electronic health records. Our results suggest that ML models achieve higher discrimination yet are less fair, especially with respect to race. Our findings highlight the need for building accurate and fair ML models to facilitate consistent and equitable assessment of POAF risk.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The effect of coronary revascularization treatment timing on mortality in patients with stable ischemic heart disease in British Columbia 95%
- Effects of low versus high inspired oxygen fraction on myocardial injury after transcatheter aortic valve implantation: A randomized clinical trial 95%
- ChatGPT Provides Inconsistent Risk-Stratification of Patients With Atraumatic Chest Pain 94%
Similar papers in this journal
- Use of a Continuous Single Lead Electrocardiogram Analytic to Predict Patient Deterioration Requiring Rapid Response Team Activation 94%
- QRS detection in single-lead, telehealth electrocardiogram signals: benchmarking open-source algorithms 94%
- Detecting QT prolongation From a Single-lead ECG With Deep Learning 92%
Similar papers in this journal
- Optimized Feature Selection and Advanced Machine Learning for Stroke Risk Prediction in Revascularized Coronary Artery Disease Patients 94%
- Prediction of Unplanned 30- day Readmission for ICU Patients with Heart Failure 93%
- OASIS+: leveraging machine learning to improve the prognostic accuracy of OASIS severity score for predicting in-hospital mortality 93%
Similar papers in this journal
- Development and Validation of a Nomogram for Predicting Survival in Patients With Cardiogenic Shock 94%
- Predicting long-term prognosis after percutaneous coronary intervention in patients with acute coronary syndromes: a prospective nested case-control analysis for county-level health services 94%
- Fragmented QRS is independently predictive of long-term adverse clinical outcomes in Asian patients hospitalized for heart failure: a retrospective cohort study 94%
Similar papers in this journal
- A Comparative Analysis of Privacy-Preserving Large Language Models For Automated Echocardiography Report Analysis 93%
- Biometric Contrastive Learning for Data-Efficient Deep Learning from Electrocardiographic Images 93%
- Real-Time Electronic Health Record Mortality Prediction During the COVID-19 Pandemic: A Prospective Cohort Study 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.