Predicting unplanned readmission due to cardiovascular disease in hospitalized patients with cancer: a machine
Sola Han1, Ted J Sohn1, Boon Peng Ng2,3
1Health Outcomes Division, College of Pharmacy, The University of Texas at Austin, Austin, TX, 78712, USA.
Insights
Machine learning accurately predicts cardiovascular disease (CVD) readmissions in cancer patients. This aids in identifying high-risk individuals, potentially reducing costly unplanned hospitalizations and improving patient outcomes.
Area of Science:
- Oncology
- Cardiology
- Data Science
Background:
- Cardiovascular disease (CVD) complicates cancer care, increasing unplanned hospital readmissions, mortality, and costs.
- Predicting CVD-related readmissions in cancer patients is crucial for proactive management and resource allocation.
Purpose of the Study:
- To evaluate the feasibility of machine learning (ML) models in predicting 180-day unplanned readmissions due to CVD in hospitalized cancer patients.
- To identify key predictors of CVD-related unplanned readmissions within this population.
Main Methods:
- Utilized the 2017-2018 Nationwide Readmissions Database, including hospitalized cancer patients.
- Implemented and compared Decision Tree (DT), Random Forest, XGBoost, and AdaBoost ML algorithms.
- Assessed model performance using accuracy, precision, recall, F2 score, and AUC.
Main Results:
- 5.86% of 358,629 cancer patients experienced unplanned CVD-related readmissions within 180 days.
- Ensemble algorithms, particularly XGBoost, outperformed Decision Tree models.
- Significant predictors included length of stay, patient age, and undergoing cancer surgery.
Conclusions:
- Machine learning models demonstrate feasibility in predicting CVD-related unplanned readmissions in cancer patients.
- XGBoost shows strong performance, offering a valuable tool for risk stratification.
- Identifying key predictors can inform targeted interventions to reduce readmission rates.
Abstract:
Cardiovascular disease (CVD) in cancer patients can affect the risk of unplanned readmissions, which have been reported to be costly and associated with worse mortality and prognosis. We aimed to demonstrate the feasibility of using machine learning techniques in predicting the risk of unplanned 180-day readmission attributable to CVD among hospitalized cancer patients using the 2017-2018 Nationwide Readmissions Database. We included hospitalized cancer patients, and the outcome was unplanned hospital readmission due to any CVD within 180 days after discharge. CVD included atrial fibrillation, coronary artery disease, heart failure, stroke, peripheral artery disease, cardiomegaly, and cardiomyopathy. Decision tree (DT), random forest, extreme gradient boost (XGBoost), and AdaBoost were implemented. Accuracy, precision, recall, F2 score, and receiver operating characteristic curve (AUC) were used to assess the model's performance. Among 358,629 hospitalized patients with cancer, 5.86% (n = 21,021) experienced unplanned readmission due to any CVD. The three ensemble algorithms outperformed the DT, with the XGBoost displaying the best performance. We found length of stay, age, and cancer surgery were important predictors of CVD-related unplanned hospitalization in cancer patients. Machine learning models can predict the risk of unplanned readmission due to CVD among hospitalized cancer patients.
More Related Videos
05:15Cutoff 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
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Related Concept Videos
01:21Cancer Survival Analysis
01:24Kaplan-Meier Approach