Non-Linear Feature Selection for Prediction of Hospital Length of Stay

Kabir, Sadaf; Farrokhvar, Leily

doi:10.1109/icmla.2019.00162

Cited by 9 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, another work performed by Bacchi et al showed that the MLP achieved the highest accuracy in the prediction of LOS with an MAE of 0.246, RMSE of 0.369, and AUC of 0.864 [43]. Kabir and Hijjry in their separate studies developed a prediction model to anticipate LOS and the results revealed that the backpropagation neural network with accuracies of 92.58% and 78.29%, respectively, outperformed all the other models in these studies [37,38]. East…”

Section: Introductionmentioning

confidence: 80%

“…So far, most efforts have been focused on the application of ANN for hospital LOS prediction and determining its affecting factors [21,[37][38][39][40][41]. Neto et al attempted to predict the LOS for stroke patients and reported that the ANN gained the best results with an RMSE and a mean absolute error (MAE) of 5.9451 and 4.6354, respectively [41].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19

et al. 2022

View full text Add to dashboard Cite

Background The exponential spread of coronavirus disease 2019 (COVID-19) causes unexpected economic burdens to worldwide health systems with severe shortages in hospital resources (beds, staff, equipment). Managing patients’ length of stay (LOS) to optimize clinical care and utilization of hospital resources is very challenging. Projecting the future demand requires reliable prediction of patients’ LOS, which can be beneficial for taking appropriate actions. Therefore, the purpose of this research is to develop and validate models using a multilayer perceptron-artificial neural network (MLP-ANN) algorithm based on the best training algorithm for predicting COVID-19 patients' hospital LOS. Methods Using a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020 to December 20, 2020 were analyzed. In this study, first, the correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at a P-value < 0.2 were used in model construction. Then, the prediction models were developed based on 12 training algorithms according to full and selected feature datasets (90% of the training, with 10% used for model validation). Afterward, the root mean square error (RMSE) was used to assess the models’ performance in order to select the best ANN training algorithm. Finally, a total of 343 patients were used for the external validation of the models. Results After implementing feature selection, a total of 20 variables were determined as the contributing factors to COVID-19 patients’ LOS in order to build the models. The conducted experiments indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian regularization (BR) training algorithm for whole and selected features with an RMSE of 1.6213 and 2.2332, respectively. Conclusions MLP-ANN-based models can reliably predict LOS in hospitalized patients with COVID-19 using readily available data at the time of admission. In this regard, the models developed in our study can help health systems to optimally allocate limited hospital resources and make informed evidence-based decisions.

show abstract

Section: Introductionmentioning

confidence: 80%

Section: Introductionmentioning

confidence: 99%

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For this purpose, several ML methods, including ANN, RBF, SVM, FNN, PNN, Pattern recognition network, and DT were fed by using the optimized predictor variables. Feature selection is a significant step to prepare and customize the data before feeding it to the ML classifiers [44]. In this study, 53 primary features are reduced to 20 by using the correlation coefficient at the P-value< 0.2.…”

Section: Performance Evaluation Of Modelsmentioning

confidence: 99%

Untitled

Afrash

Kazemi-Arpanahi²,

Ranjbar

et al. 2021

J. Med. Chem. Sci.

View full text Add to dashboard Cite

The rapid worldwide outbreak of COVID-19 has posed serious and unprecedented challenges to healthcare systems in predicting disease behavior, consequences and resource utilization. Therefore, predicting the Length of Stay (LOS) is necessary to ensure optimal allocate of scarce hospital resources. The purpose of this research was to construct a model for predicting COVID-19 patients' hospital LOS by multiple Machine Learning (ML) algorithms. Using a single-center registry, we studied the records of 1225 laboratory-confirmed COVID-19 hospitalized patients from February 9, 2020, to December 20, 2020. The most important clinical parameters in the COVID-19 LOS prediction were identified with a correlation coefficient at the P-value< 0.2. Then, the prediction models were developed based on seven ML techniques according to selected variables. Finally, to evaluate the performances of those models several standard quantitative measures includes accuracy, sensitivity, specificity and ROC curve were used to evaluate the proposed predictive models. After implementing feature selection, a total of 20 variables was identified as the most relevant predictors to build the prediction models. The results indicated that the best performance belonged to the Support Vector Machine (SVM) algorithm with the mean accuracy of 99.5%, mean specificity of 99.7%, mean sensitivity of 99.4%, and the standard deviation of 1.2. The SVM provided a reasonable level of accuracy and certainty in predicting the LOS in COVID-19 patients and potentially facilitates hospital bed management, turnover and optimized resource allocation.

show abstract

“…This method can be trained to recognize and categorize complex patterns of diseases and related healthcare events through an iterative learning process. So far, there are multiple ANN solutions were presented for LOS prediction and determining its affecting factors (10,(24)(25)(26)(27)(28).…”

Section: Introductionmentioning

confidence: 99%

Predictive modeling of hospital Length of Stay in COVID-19 patients using Artificial Neural Networks

Orooji

Shanbehzadeh

Kazemi-Arpanahi³

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundThe current pandemic of coronavirus disease (COVID-19) causes unexpected economic burdens to worldwide health organizations with severe shortages in hospital bed capacity and other related medical resources. Therefore, predicting the length of stay (LOS) is essential to ensure optimal allocating scarce hospital resources and inform evidence-based decision-making. Thus, the purpose of this research is to construct a model for predicting COVID-19 patients' hospital LOS by multiple multilayer perceptron-artificial neural network (MLP-ANN) algorithms. Material and MethodsUsing a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020, to December 20, 2020, were analyzed. The correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at the P-value< 0.2 were used in model construction. Ultimately the prediction models were developed based on 12 ANN techniques according to selected variables. ResultsAfter implementing feature selection, a total of 20 variables was determined as the most relevant predictors to build the models. The results indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian Regularization classifier for whole and selected features with RMSE of 1.6213 and 2.2332, respectively. ConclusionThe developed model in this study can help in the better calculation of LOS in COVID-19 patients. This model also can be leveraged in hospital bed management and optimized resource utilization.

show abstract

Non-Linear Feature Selection for Prediction of Hospital Length of Stay

Cited by 9 publications

References 27 publications

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19

Untitled

Predictive modeling of hospital Length of Stay in COVID-19 patients using Artificial Neural Networks

Contact Info

Product

Resources

About