Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modeling

Viegas, Rita; Salgado, Ctia M.; Curto, Srgio; Carvalho, João Paulo; Vieira, Susana M.; Finkelstein, Stan N.

doi:10.1016/j.eswa.2017.02.036

Cited by 18 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jian et al [2] author presents a decision cloud-based system for the risk assessment of heart disease by leveraging the techniques of a fuzzy expert system. Viegas et al [3] use fuzzy logic to solve patients readmitted to care units, also Morsi and Gawad [4] use fuzzy logic in health-related diagnosis for the diagnosis of heart and blood pressure measurements. Viegas et al [3] proposed a model to predict readmissions of care units using feature selection and fuzzy logic approaches.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Viegas et al [3] use fuzzy logic to solve patients readmitted to care units, also Morsi and Gawad [4] use fuzzy logic in health-related diagnosis for the diagnosis of heart and blood pressure measurements. Viegas et al [3] proposed a model to predict readmissions of care units using feature selection and fuzzy logic approaches. Alkahtani and Jilani [5] use machine learning to predict the return on donor blood donation with data mining.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A fuzzy-based prediction approach for blood delivery using machine learning and genetic algorithm

Midaoui

Qbadou

Mansouri

2022

IJECE

View full text Add to dashboard Cite

Multiple diseases require a blood transfusion on daily basis. The process of a blood transfusion is successful when the type and amount of blood is available and when the blood is transported at the right time from the blood bank to the operating room. Blood distribution has a large portion of the cost in hospital logistics. The blood bank can serve various hospitals; however, amount of blood is limited due to donor shortage. The transportation must handle several requirements such as timely delivery, vibration avoidance, temperature maintenance, to keep the blood usable. In this paper, we discuss in first section the issues with blood delivery and constraint. The second section present routing and scheduling system based on artificial intelligence to deliver blood from the blood-banks to hospitals based on single blood bank and multiple blood banks with respect of the vehicle capacity used to deliver the blood and creating the shortest path. The third section consist on solution for predicting the blood needs for each hospital based on transfusion history using machine learning and fuzzy logic. The last section we compare the results of well-known solution with our solution in several cases such as shortage and sudden changes.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

A fuzzy-based prediction approach for blood delivery using machine learning and genetic algorithm

Midaoui

Qbadou

Mansouri

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…The fuzzy modelling was performed to predict ICU patient readmissions (Fialho et al, 2012). Viegas Rita et al learned from the ideas of Fialho André S et al; fuzzy modelling and ensemble learning were combined to predict the daily readmission rates of ICU patients (Viegas et al, 2017). Similarly, LR, RF, and XGBoost were suggested to predict the probability of patient readmissions occurring within 24-72 h after discharge (Pakbin et al, 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Doctors can infer the possibility of readmission in the future based on a risk score (Cotter et al, 2012; Hu et al, 2018). Numerous machine learning models have focused on identifying the influencing factors for ICU patient readmissions (Magruder et al, 2015; Pakbin et al, 2018; Viegas et al, 2017; Xue et al, 2019). Based on these risk factors, some studies have further developed different models that can predict whether a patient will be readmitted.…”

Section: Introductionmentioning

confidence: 99%

“…For the prediction of patient readmissions, many machine learning models, including logistic regression (LR), random forest (RF), support vector machine (SVM), and AdaBoost, have been proposed in previous studies (Magruder et al, 2015; Pakbin et al, 2018; Viegas et al, 2017; Xue et al, 2019). These models are all implemented to address the binary classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HFS‐LightGBM: A machine learning model based on hybrid feature selection for classifying ICU patient readmissions

et al. 2020

View full text Add to dashboard Cite

Compared to patients readmitted to general wards, readmitted patients in the intensive care unit (ICU) are exposed to higher mortality rates and prolonged hospital stays. Moreover, the readmission of ICU patients brings pressing challenges for ICU management. Most models are devoted to identifying the risk factors and developing classification models that can predict whether ICU patients will be readmitted. Though these models are prominent, they do not provide estimates for the frequency of readmissions. This paper establishes a prediction model, hybrid feature selection‐LightGBM (HFS‐LightGBM), to evaluate the probability and frequency of ICU patient readmissions empirically. In terms of feature selection, a hybrid feature selection (HFS) algorithm for LightGBM combines the filter and wrapper methods. Pearson's correlation coefficient is employed in the filter procedure. Then we adopt the targeted LightGBM classifier along with the recursive feature elimination and cross‐validated (RFECV) to produce the optimal feature subset. Additionally, the hyperparameters of the HFS‐LightGBM are optimized. The HFS‐LightGBM is employed on the real‐world ICU dataset containing 1722 patients' electronic health records. This model outperforms the current prevailing readmission models. The identified frequency can assist doctors in making specific interventions for patients to reduce the ICU readmission rate.

show abstract

Machine Learning and Deep Learning Models for Privacy Management and Data Analysis in Smart Cites

Bhowmik

Bhadwaj

Kumar

et al. 2022

Intelligent Systems Reference Library

View full text Add to dashboard Cite

Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modeling

Cited by 18 publications

References 25 publications

A fuzzy-based prediction approach for blood delivery using machine learning and genetic algorithm

A fuzzy-based prediction approach for blood delivery using machine learning and genetic algorithm

HFS‐LightGBM: A machine learning model based on hybrid feature selection for classifying ICU patient readmissions

Machine Learning and Deep Learning Models for Privacy Management and Data Analysis in Smart Cites

Contact Info

Product

Resources

About