Predicting length of stay in hospitals intensive care unit using general admission features

Abdelrazek, Mohamed A; Eltahawi, Ahmed; El-Aziz, Mohamed Hashem Abd; Abd-Elwhab, Mohamed N.

doi:10.1016/j.asej.2021.02.018

Cited by 32 publications

(18 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The models used in this work include KNN [ 18 ], multivariate regression [ 36 ], decision tree [ 37 ], random forest [ 4 ], ANN [ 38 ], and XGBoost [ 39 ] so that the results of the improved model can be compared. All models were built in Python version 3.8.5.…”

Section: Methodsmentioning

confidence: 99%

“…Fuzzy logic had the best prediction results, followed by random forest, with an accuracy value of 0.92 and 0.9, respectively. Parameter tuning was not mentioned in the modeling process [ 18 ]. Mahboub et al used the decision tree model to predict the LOS of COVID-19 patients.…”

Section: Related Workmentioning

confidence: 99%

“…Related works can also be classified in terms of the type of studied sample. Various types of hospital units, such as intensive care units (ICUs) [ 14 , 18 ] and newborns units [ 4 , 19 ], as well as different medical diagnoses, were studied, including COVID-19 patients [ 20 ] and lung cancer [ 21 ]. Although the methods used in the literature have yielded good results, the hyperparameter tuning problem still exists in the modeling procedure [ 4 , 16 , 18 , 20 , 21 ].…”

Section: Introductionmentioning

confidence: 99%

“…Various types of hospital units, such as intensive care units (ICUs) [ 14 , 18 ] and newborns units [ 4 , 19 ], as well as different medical diagnoses, were studied, including COVID-19 patients [ 20 ] and lung cancer [ 21 ]. Although the methods used in the literature have yielded good results, the hyperparameter tuning problem still exists in the modeling procedure [ 4 , 16 , 18 , 20 , 21 ]. There are two types of parameters in ML models, those learned during the training process and hyperparameters, such as maximum depth in a decision tree.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

Mansoori

Zeinalnezhad

Nazarimanesh

2023

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

Mansoori

Zeinalnezhad

Nazarimanesh

2023

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…If the prediction error is low for the training data set but high for the tested data set, the technique outputs will suffer from excessive variance due to the over tting issue. The technique is under tting, though, and the outcome is highly biassed if the prediction error is considerable for both the training and testing data sets [21].…”

Section: Cross-validationmentioning

confidence: 99%

A data-driven approach to forecast the length of stay and overall treatment cost for resistant bacterial infections.

Chandra

Vandana

Mukhopadhyay

et al. 2022

Preprint

View full text Add to dashboard Cite

The length of stay (LOS) and healthcare expenses for patients are drastically impacted by antimicrobial resistance (AMR). In addition to building a prediction model for AMR infection outcomes, the study will examine how AMR influences the attributable cost and length of stay in hospitalized patients. WEKA-ML version 3.8.6 was used to build the models. The discretization of LOS and cost into distinct bins is normalized. Utilizing a number of feature selection techniques, the best characteristics associated with the outcome were selected. The optimal feature selection strategy was selected, and several methods were used to the training (66 percent / 80 percent) and test (34 percent /20 percent) data sets to prevent underfitting and overfitting. Using ROC curves, prediction error, and accuracy metrics, the best-predicted model is selected. In terms of forecasting LOS, RF performed better (accuracy=69.6, ROC=0.852) than bagging (accuracy=69.6, ROC=0.862) while using the cfs subset attribute evaluation+greedy stepwise approach and the Infogain+ranker method. The majority of patients fell between the ranges of 7 and 14 days. With 34% of test data sets, RF outperformed marginally better using the infogain attribute selection+ranker technique (Accuracy=80.8 ROC=0.967) in predicting cost. Most fell into the >$1720 range, then came the $814 range. Effective LOS and treatment cost prediction for resistant infections gives crucial data that helps hospital administration, and the medical staff make crucial decisions. While avoiding a significant loss of resources, hospital administration can provide the appropriate and essential resources and the best medical team for treating the patient.

show abstract

Missing Circles: A Dignitarian Approach to Doughnut Economics Through AI Applications

Prifti

2023

Philosophical Studies Series

View full text Add to dashboard Cite

This contribution aims at providing a more concrete and accurate understanding of Doughnut economics, its model, and its ideas. In doing so, it provides a comprehensive description of the Doughnut and its connection with the Sustainable Development Goals. Then, it inquires into the philosophical background of Doughnut economics, elucidating its existential rationale that relies on human dignity. Further, examples of four AI applications are used to showcase how the Doughnut model would address their use and challenges that arise thereof. From this testing exercise transpires the understanding that another limitation is required in the Doughnut model, pursuant to its philosophical background. Therefore, besides economic activities that may breach the ecological ceiling or the social foundation, activities that infringe human dignity, without breaching any of the boundaries, are also incompatible with the Doughnut model. This complementing proposal is conceptually represented within the model of Doughnut economics.

show abstract

Predicting length of stay in hospitals intensive care unit using general admission features

Cited by 32 publications

References 39 publications

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

A data-driven approach to forecast the length of stay and overall treatment cost for resistant bacterial infections.

Missing Circles: A Dignitarian Approach to Doughnut Economics Through AI Applications

Contact Info

Product

Resources

About