A Data-driven Approach to Predict Hospital Length of Stay - A Portuguese Case Study

Caetano, Nuno; Laureano, Raul; Cortez, Paulo

doi:10.5220/0004892204070414

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the XGBoost regression model also showed better results in Gabriel et al ( 2023 ) for spine surgery LoS prediction. In another study on regression outcomes (Caetano et al, 2014 ), which examined the general patient population, six regression techniques were compared, including average prediction, decision trees, multiple regression, ANN ensembles, RF, and SVM. The RF regression model was found to yield the most accurate results with the lowest loss.…”

Section: Discussionmentioning

confidence: 99%

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

Zeleke

Palumbo

Malaguti

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

ObjectiveThis study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework).MethodsWe analyzed a dataset of patients admitted through the ED to the “Sant”Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%).ResultsA total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6–7 day mean difference between actual and predicted LoS.ConclusionOur results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

Zeleke

Palumbo

Malaguti

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…As in those studies, the analysis was performed on the basis of hospitalizations, so that one patient may be represented by several cases. Model performance was evaluated mainly based on the Akaike Information Criterion (AIC), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) [ 28 , 29 ]. The derivation of the model with R code is portrayed in S1 File .…”

Section: Methodsmentioning

confidence: 99%

Interaction of mental comorbidity and physical multimorbidity predicts length-of-stay in medical inpatients

Stahl-Toyota,

Nikendei,

Nagy

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Background Mental comorbidities of physically ill patients lead to higher morbidity, mortality, health-care utilization and costs. Objective The aim of the study was to investigate the impact of mental comorbidity and physical multimorbidity on the length-of-stay in medical inpatients at a maximum-care university hospital. Design The study follows a retrospective, quantitative cross-sectional analysis approach to investigate mental comorbidity and physical multimorbidity in internal medicine patients. Patients The study comprised a total of n = 28.553 inpatients treated in 2017, 2018 and 2019 at a German Medical University Hospital. Main measures Inpatients with a mental comorbidity showed a median length-of-stay of eight days that was two days longer compared to inpatients without a mental comorbidity. Neurotic and somatoform disorders (ICD-10 F4), behavioral syndromes (F5) and organic disorders (F0) were leading with respect to length-of-stay, followed by affective disorders (F3), schizophrenia and delusional disorders (F2), and substance use (F1), all above the sample mean length-of-stay. The impact of mental comorbidity on length-of-stay was greatest for middle-aged patients. Mental comorbidity and Elixhauser score as a measure for physical multimorbidity showed a significant interaction effect indicating that the impact of mental comorbidity on length-of-stay was greater in patients with higher Elixhauser scores. Conclusions The findings provide new insights in medical inpatients how mental comorbidity and physical multimorbidity interact with respect to length-of-stay. Mental comorbidity had a large effect on length-of-stay, especially in patients with high levels of physical multimorbidity. Thus, there is an urgent need for new service models to especially care for multimorbid inpatients with mental comorbidity.

show abstract

LoSNet: A Tailored Deep Neural Network Framework for Precise Length of Stay Prediction in Disease-Specific Hospitalization

Mushtaq

2024

Procedia Computer Science

View full text Add to dashboard Cite

A Data-driven Approach to Predict Hospital Length of Stay - A Portuguese Case Study

Cited by 4 publications

References 14 publications

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

Interaction of mental comorbidity and physical multimorbidity predicts length-of-stay in medical inpatients

LoSNet: A Tailored Deep Neural Network Framework for Precise Length of Stay Prediction in Disease-Specific Hospitalization

Contact Info

Product

Resources

About