Related Experiment Video
Updated: Jun 29, 2025
Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
A cost-sensitive deep neural network-based prediction model for the mortality in acute myocardial infarction patients
Huilin Zheng1,2, Syed Waseem Abbas Sherazi1, Jong Yun Lee1
1Department of Computer Science, Chungbuk National University, Cheongju, Republic of Korea.
Insights
A new cost-sensitive deep neural network (CSDNN) model accurately predicts mortality in acute myocardial infarction (AMI) patients with hypertension using imbalanced data, outperforming existing methods.
Area of Science:
- Cardiology
- Artificial Intelligence
- Data Science
Background:
- Hypertension is a major risk factor and leading cause of mortality in cardiovascular diseases (CVDs).
- Accurate mortality prediction is crucial for patients with CVDs and hypertension.
- Out-of-hospital acute myocardial infarction (AMI) patients with hypertension present a significant challenge for mortality prediction due to imbalanced data.
Purpose of the Study:
- To develop a novel cost-sensitive deep neural network (CSDNN)-based model for mortality prediction in out-of-hospital AMI patients with hypertension.
- To address the challenge of imbalanced data in mortality prediction.
- To improve the accuracy and decision-making process for managing AMI patients with hypertension.
Main Methods:
- Data extracted from the Korea Acute Myocardial Infarction Registry-National Institutes of Health (KAMIR-NIH) and preprocessed.
- A cost-sensitive deep neural network (CSDNN) model was designed to handle skewed class distribution.
- Threshold moving technique and random search with 5-fold cross-validation were employed for model optimization and evaluation.
Main Results:
- The proposed CSDNN model with threshold moving achieved superior performance on imbalanced data.
- The CSDNN model demonstrated significant improvements in AUC compared to the best machine learning and ensemble models (2.58% and 2.55% increase, respectively).
- The model provides precise mortality prediction, aiding clinical decision-making.
Conclusions:
- The CSDNN-based model offers a highly effective solution for mortality prediction in hypertensive AMI patients with imbalanced datasets.
- This approach enhances the accuracy of risk stratification and supports better patient management.
- The study highlights the potential of advanced AI techniques in improving outcomes for cardiovascular disease patients.
Background And Objectives:
Hypertension is one of the most serious risk factors and the leading cause of mortality in patients with cardiovascular diseases (CVDs). It is necessary to accurately predict the mortality of patients suffering from CVDs with hypertension. Therefore, this paper proposes a novel cost-sensitive deep neural network (CSDNN)-based mortality prediction model for out-of-hospital acute myocardial infarction (AMI) patients with hypertension on imbalanced data.
Methods:
The synopsis of our research is as follows. First, the experimental data is extracted from the Korea Acute Myocardial Infarction Registry-National Institutes of Health (KAMIR-NIH) and preprocessed with several approaches. Then the imbalanced experimental dataset is divided into training data (80%) and test data (20%). After that, we design the proposed CSDNN-based mortality prediction model, which can solve the skewed class distribution between the majority and minority classes in the training data. The threshold moving technique is also employed to enhance the performance of the proposed model. Finally, we evaluate the performance of the proposed model using the test data and compare it with other commonly used machine learning (ML) and data sampling-based ensemble models. Moreover, the hyperparameters of all models are optimized through random search strategies with a 5-fold cross-validation approach.
Results And Discussion:
In the result, the proposed CSDNN model with the threshold moving technique yielded the best results on imbalanced data. Additionally, our proposed model outperformed the best ML model and the classic data sampling-based ensemble model with an AUC of 2.58% and 2.55% improvement, respectively. It aids in decision-making and offers a precise mortality prediction for AMI patients with hypertension.
