Key result
ML models predict in-hospital mortality in MI patients with a C-index of 0.83.
Why the study?
Due to diverse ML models, modeling variables, and significant data imbalance, the predictive accuracy of machine learning models for in-hospital mortality in MI patients remains controversial.
Do machine learning models accurately predict in-hospital mortality in patients with acute myocardial infarction?
Systematic Review (n=32)
Do machine learning models accurately predict in-hospital mortality in patients with acute myocardial infarction?
Answers are grounded in this paper and cite their sources.
Machine learning models demonstrate good overall discrimination and specificity for predicting in-hospital mortality in AMI, though their sensitivity is not superior to established clinical risk scores and is hindered by imbalanced training data.
• Some ML models can effectively predict the risk of in-hospital mortality in AMI. • Models built on unbalanced data are less accurate. • PROBAST and ChAMAI tools are used to assess research bias and quality. • The interpretability of ML models can be improved through result visualization and transparent operation logic. • Models based on unbalanced data can be optimized using methods such as oversampling, and SMOTE algorithm. Machine learning (ML) models have been constructed to predict the risk of in-hospital mortality in patients with myocardial infarction (MI). Due to diverse ML models and modeling variables, along with the significant imbalance in data, the predictive accuracy of these models remains controversial. This study aimed to review the accuracy of ML in predicting in-hospital mortality risk in MI patients and to provide evidence-based advices for the development or updating of clinical tools. PubMed, Embase, Cochrane, and Web of Science databases were searched, up to June 4, 2024. PROBAST and ChAMAI checklist are utilized to assess the risk of bias in the included studies. Since the included studies constructed models based on severely unbalanced datasets, subgroup analyses were conducted by the type of dataset (balanced data, unbalanced data, model type). This meta-analysis included 32 studies. In the validation set, the pooled C-index, sensitivity, and specificity of prediction models based on balanced data were 0.83 (95% CI: 0.795–0.866), 0.81 (95% CI: 0.79–0.84), and 0.82 (95% CI: 0.78–0.86), respectively. In the validation set, the pooled C-index, sensitivity, and specificity of ML models based on imbalanced data were 0.815 (95% CI: 0.789–0.842), 0.66 (95% CI: 0.60–0.72), and 0.84 (95% CI: 0.83–0.85), respectively. ML models such as LR, SVM, and RF exhibit high sensitivity and specificity in predicting in-hospital mortality in MI patients. However, their sensitivity is not superior to well-established scoring tools. Mitigating the impact of imbalanced data on ML models remains challenging.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2025) conducted a systematic review in Acute myocardial infarction (n=32). Machine learning models vs. Well-established scoring tools was evaluated on In-hospital mortality prediction (C-index) (Pooled C-index 0.83, 95% CI 0.795-0.866). Machine learning models predicted in-hospital mortality in myocardial infarction patients with a pooled C-index of 0.83 (95% CI 0.795-0.866) on balanced data and 0.815 on imbalanced data.
Synapse has enriched 10 related papers. Consider them for comparative context: