Related Experiment Video
Updated: Jun 29, 2026
Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
Predicting mortality risk in hospitalized ACS patients with hypertensive comorbidity: an interpretable machine
Sazzli Kasim1, Kiew Xue Ning2, Sorayya Malek3
1Cardiovascular Advancement and Research Excellence Institute (CARE Institute), Universiti Teknologi MARA, Selangor, Malaysia.
Insights
A new risk prediction model accurately assesses mortality in Asian patients with Acute Coronary Syndrome (ACS) and hypertension. This machine learning model outperforms traditional scores, identifying key predictors for better patient outcomes.
Area of Science:
- Cardiology
- Machine Learning in Healthcare
- Public Health
Background:
- Hypertension is a major health concern in South Asia, complicating Acute Coronary Syndrome (ACS) prognosis.
- Existing ACS mortality risk scores (e.g., TIMI, GRACE) are suboptimal for Asian populations with comorbid hypertension.
- There is a need for a tailored risk prediction model for Asian ACS patients with hypertension.
Purpose of the Study:
- To develop and validate an interpretable machine learning model for predicting mortality in Asian patients with ACS and hypertension.
- To compare the performance of the developed model against conventional risk scores like TIMI.
Main Methods:
- Utilized in-hospital data (2006-2019) from the NCVD Registry for ACS patients with hypertension.
- Employed Sequential Backward Elimination for feature selection and various machine learning techniques with ensemble meta-learners.
- Validated model accuracy using Area Under the Curve (AUC), Platt Scaling, Net Reclassification Index (NRI), LIME, and SHAP for interpretability.
Main Results:
- The Random Forest (RF) model achieved an AUC of 0.95, significantly outperforming the TIMI score (AUC 0.641-0.83).
- The calibrated RF model demonstrated improved accuracy (15%-78%) compared to the TIMI score, as verified by NRI.
- SHAP and LIME analyses identified Killip classification and peak CK levels as key mortality predictors, while ACE medications were linked to survival.
Conclusions:
- The calibrated RF model offers superior predictive accuracy for mortality in Asian hypertensive ACS patients compared to traditional TIMI scores.
- The model effectively identifies crucial mortality predictors, enhancing clinical decision-making.
- Interpretability methods (LIME, SHAP) underscore the significance of selected features for risk assessment.
Background:
Hypertension serves as a prevalent health issue, particularly in South Asia, where it is also a risk factor and comorbidity that affects the prognosis of Acute Coronary Syndrome (ACS) by increasing the likelihood of complications such as heart failure and arrhythmias. Conventional tools for predicting ACS mortality risk, such as the TIMI and GRACE scores, often fail to adequately represent the Asian population and do not specifically address the needs of ACS patients with comorbid hypertension. Our study focuses on developing a tailored and interpretable risk prediction model to assess mortality rate of Asian ACS-hypertensive patients.
Methods:
We used in-hospital data from the NCVD Registry, which includes ACS patients with hypertension from 2006 to 2019 and selected key factors such as demographics, medications, and clinical details using Sequential Backward Elimination. We then used various ML techniques and combined them with ensemble meta-learners to predict mortality. We measured the model's accuracy using the area under the curve (AUC) and fine-tuned the best model with Platt Scaling. Our model was compared with the TIMI score to calculate the net reclassification index (NRI). Finally, we applied LIME and SHAP to understand feature importance and interpret model performance.
Results:
The RF model with selected 28 features outperforms other prediction models with an AUC of 0.95. The calibrated RF model has raised Brier score (ACS: 0.046; STEMI: 0.051; NSTEMI: 0.041), and Chi-squared (ACS: 10.253; STEMI: 6.023; NSTEMI: 23.030). NRI verified our calibrated model's better reclassification than the conventional TIMI risk score (improved accuracy by 15%-78%). The model's robustness was proven by its greater AUC (0.841-0.898) than the TIMI risk score (0.641-0.83). SHAP and LIME analyses revealed that the Killip classification and peak CK levels significantly influenced mortality. Conversely, ACE medications were found to be more strongly associated with survival.
Conclusion:
Our calibrated RF model demonstrated superior predictive accuracy in mortality risk for Asian hypertensive ACS patients, outperforming traditional TIMI scores. It efficiently identified key mortality predictors, which is further interpreted by SHAP and LIME, effectively underscore the significance of selected features for ACS mortality risk.