Predicting Length of Stay for Cardiovascular Hospitalizations in the Intensive Care Unit: Machine Learning Approach
Insights
Predicting heart failure patients' length of stay (LOS) in intensive care units (ICUs) is challenging. Gradient Boosting Regressor models accurately predicted LOS using electronic medical records, outperforming deep learning approaches.
Area of Science:
- Health Informatics
- Machine Learning in Healthcare
- Predictive Analytics
Background:
- Predicting cardiovascular patients' length of stay (LOS) in coronary care units (CCUs) or cardiac intensive care units (CICUs) presents a significant challenge for hospital management.
- While some studies have explored predictive analytics for cardiovascular inpatients in ICUs, few have specifically focused on machine learning models for predicting the length of stay for heart failure patients.
Purpose of the Study:
- To develop and evaluate a predictive research architecture for estimating the Length of Stay (LOS) for heart failure patients in ICUs.
- To compare the performance of various state-of-the-art machine learning models, including ensemble regressors and deep learning regression models, for LOS prediction using electronic medical records.
Main Methods:
- Utilized electronic medical records data for heart failure diagnoses.
- Implemented and compared ensemble regression models (Gradient Boosting Regressor, Staking Regressor, Random Forest Regressor) and deep learning regression models.
- Evaluated model performance using metrics such as R-squared value and training time.
Main Results:
- The Gradient Boosting Regressor (GBR) demonstrated superior performance with the highest R-squared value.
- The Staking Regressor also showed strong predictive capabilities.
- The Random Forest Regressor (RFR) exhibited the fastest training time among the evaluated models.
- Deep learning-based regressors did not yield better results compared to traditional regression models in this study.
Conclusions:
- Gradient Boosting Regressor is a highly effective model for predicting heart failure patients' length of stay in ICUs.
- Ensemble regression models show promise for improving hospital management systems through accurate LOS predictions.
- This research contributes valuable insights into predictive modeling for electronic medical records, aiding hospital resource management.
Abstract:
Predicting Cardiovascular Length of stay based hospitalization at the time of patients' admitting to the coronary care unit (CCU) or (cardiac intensive care units CICU) is deemed as a challenging task to hospital management systems globally. Recently, few studies examined the length of stay (LOS) predictive analytics for cardiovascular inpatients in ICU. However, there are almost scarcely real attempts utilized machine learning models to predict the likelihood of heart failure patients length of stay in ICU hospitalization. This paper introduces a predictive research architecture to predict Length of Stay (LOS) for heart failure diagnoses from electronic medical records using the state-of-art- machine learning models, in particular, the ensembles regressors and deep learning regression models. Our results showed that the gradient boosting regressor (GBR) outweighed the other proposed models in this study. The GBR reported higher R-squared value followed by the proposed method in this study called Staking Regressor. Additionally, The Random forest Regressor (RFR) was the fastest model to train. Our outcomes suggested that deep learning-based regressor did not achieve better results than the traditional regression model in this study. This work contributes to the field of predictive modelling for electronic medical records for hospital management systems.
Related Concept Videos
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
00:59Hospitals-II
Nurses that work in...
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.