Related Experiment Video
Updated: Nov 10, 2025
Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
Published on: February 21, 2025
Mortality Prediction of Patients With Cardiovascular Disease Using Medical Claims Data Under Artificial Intelligence
Linh Tran1, Lianhua Chi2, Alessio Bonti1
1School of Info Technology, Deakin University, Burwood, Australia.
Insights
Artificial intelligence (AI) models can efficiently predict cardiovascular disease (CVD) mortality using claims data. Gradient Boosting Trees and Random Forest models demonstrated high accuracy, aiding clinicians in early risk assessment.
Area of Science:
- Health Informatics
- Machine Learning in Medicine
- Cardiovascular Disease Research
Background:
- Cardiovascular disease (CVD) poses a significant health burden in Australia, leading to high mortality rates and healthcare costs.
- Predicting CVD mortality is crucial for timely clinical intervention and resource allocation.
- Existing prediction models often require extensive patient data, limiting their practical application.
Purpose of the Study:
- To benchmark various artificial intelligence (AI) architectures for predicting CVD patient mortality using structured medical claims data.
- To identify efficient AI models that utilize a minimal set of features for accurate mortality prediction.
- To empower health professionals with data-driven tools for early CVD risk assessment.
Main Methods:
- Utilized a large dataset (346,201 records) from Australian Medicare and Pharmaceutical Benefits Schemes (2004-2014).
- Developed and compared five AI algorithms: Logistic Regression (LR), Random Forest (RF), Extra Trees (ET), Gradient Boosting Trees (GBT), and Deep Neural Network (DNN).
- Employed the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance in the dataset.
Main Results:
- Gradient Boosting Trees (GBT) and Random Forest (RF) achieved the highest discrimination, with AUCs of 97.8% and 97.7%, respectively.
- Deep Neural Network (DNN) showed the lowest discrimination (95.3%), while Logistic Regression (LR) had the least reliable calibration.
- SMOTE improved LR performance, and GBT and DNN effectively handled imbalanced data without SMOTE.
Conclusions:
- AI models, particularly GBT and RF, offer efficient and high-performance prediction of CVD mortality using limited claims data.
- The study provides a valuable comparison to guide clinicians in selecting appropriate AI models for pre-clinic CVD risk assessment.
- These findings can enhance early intervention strategies and potentially reduce healthcare system costs associated with CVD.
Background:
Cardiovascular disease (CVD) is the greatest health problem in Australia, which kills more people than any other disease and incurs enormous costs for the health care system. In this study, we present a benchmark comparison of various artificial intelligence (AI) architectures for predicting the mortality rate of patients with CVD using structured medical claims data. Compared with other research in the clinical literature, our models are more efficient because we use a smaller number of features, and this study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit.
Objective:
This study aims to support health clinicians in accurately predicting mortality among patients with CVD using only claims data before a clinic visit.
Methods:
The data set was obtained from the Medicare Benefits Scheme and Pharmaceutical Benefits Scheme service information in the period between 2004 and 2014, released by the Department of Health Australia in 2016. It included 346,201 records, corresponding to 346,201 patients. A total of five AI algorithms, including four classical machine learning algorithms (logistic regression [LR], random forest [RF], extra trees [ET], and gradient boosting trees [GBT]) and a deep learning algorithm, which is a densely connected neural network (DNN), were developed and compared in this study. In addition, because of the minority of deceased patients in the data set, a separate experiment using the Synthetic Minority Oversampling Technique (SMOTE) was conducted to enrich the data.
Results:
Regarding model performance, in terms of discrimination, GBT and RF were the models with the highest area under the receiver operating characteristic curve (97.8% and 97.7%, respectively), followed by ET (96.8%) and LR (96.4%), whereas DNN was the least discriminative (95.3%). In terms of reliability, LR predictions were the least calibrated compared with the other four algorithms. In this study, despite increasing the training time, SMOTE was proven to further improve the model performance of LR, whereas other algorithms, especially GBT and DNN, worked well with class imbalanced data.
Conclusions:
Compared with other research in the clinical literature involving AI models using claims data to predict patient health outcomes, our models are more efficient because we use a smaller number of features but still achieve high performance. This study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit.
More Related Videos
07:51Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
Related Concept Videos
01:20Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
01:24Kaplan-Meier Approach
01:21Cancer Survival Analysis