A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

El–Sappagh, Shaker; Elmogy, Mohammed; Ali, Farman; Abuhmed, Tamer; Islam, S. M. Riazul; Kwak, Kyung Sup

doi:10.3390/electronics8060635

Cited by 26 publications

(10 citation statements)

References 60 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of combining data from multiple sources to provide a more informative decision is called data fusion [33]. Ensemblebased models have been successfully used for applications adopting the data fusion process [34] [35] [36].…”

Section: Introductionmentioning

confidence: 99%

Intensive Care Unit Mortality Prediction: An Improved Patient-Specific Stacking Ensemble Model

et al. 2020

Self Cite

View full text Add to dashboard Cite

The intensive care unit (ICU) admits the most seriously ill patients requiring extensive monitoring. Early ICU mortality prediction is crucial for identifying patients who are at great risk of dying and for providing suitable interventions to save their lives. Accordingly, early prediction of patients at high mortality risk will enable their provision of appropriate and timely medical services. Although various severity scores and machine-learning models have recently been developed for early mortality prediction, such prediction remains challenging. This paper proposes a novel stacking ensemble approach to predict the mortality of ICU patients. Our approach is more accurate and medically intuitive compared to the literature work. Data were prepared and feature selection was processed under the supervision of the ICU domain expert. The data were split into six modalities based on the expert's decisions. For the prediction process, a separate classifier was selected for each modality based on the performance of the classifiers. We utilized the most popular and diverse classifiers in the literature, including linear discriminant analysis, decision tree (DT), multilayer perceptron, k-nearest neighbor, and logistic regression (LR). Then, a stacking ensemble classifier was constructed and optimized based on the fusion of these five classifier decisions. The framework was evaluated using 10,664 patients from the medical information mart for intensive care (MIMIC III) benchmark dataset. To predict patient mortality, extensive experiments were conducted using the patients' time series data of different lengths. For each patient, the first 6, 12, and 24 hours of the first stay were tested. The results indicate that our model outperformed the state-of-the-art approaches in terms of accuracy (94.4%), F1 score (93.7%), precision (96.4%), recall (91.1%), and area under the receiver operator characteristic (ROC) curve (93.3%). These results demonstrate the ability and efficiency of our approach to predict ICU mortality.

show abstract

Section: Introductionmentioning

confidence: 99%

Intensive Care Unit Mortality Prediction: An Improved Patient-Specific Stacking Ensemble Model

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Performance comparison between the proposed models and other similar existing works addressing T2DM prediction is summarized in Table 9. Studies [6]- [12], [14] predict future progression of diabetes in advance of 5-7 years time-frame. The SAHS dataset was used for both model development and evaluation in the studies [16], [17].…”

Section: Results Benchmarkingmentioning

confidence: 99%

“…In the recent past, we have seen researchers applying machine learning techniques to detect and predict diabetes at an early stage [6]- [14]. Heikes et al [6] used the physiological data from the National Health and Nutrition Examination Survey (NHANES) for detecting undiagnosed diabetes and pre-diabetes by applying logistic regression (LR) and decision tree (DT) classifiers.…”

Section: Introductionmentioning

confidence: 99%

Advanced Techniques for Predicting the Future Progression of Type 2 Diabetes

et al. 2020

View full text Add to dashboard Cite

Diabetes is a costly and burdensome metabolic disorder that occurs due to the elevation of glucose levels in the bloodstream. If it goes unchecked for an extended period, it can lead to the damage of different body organs and develop life-threatening health complications. Studies show that the progression of diabetes can be stopped or delayed, provided a person follows a healthy lifestyle and takes proper medication. Prevention of diabetes or the delayed onset of diabetes is crucial, and it can be achieved if there exists a screening process that identifies individuals who are at risk of developing diabetes in the future. Although machine learning techniques have been applied for disease diagnosis, there is little work done on long term prediction of disease, type 2 diabetes in particular. Moreover, finding discriminative features or risk-factors responsible for the future development of diabetes plays a significant role. In this study, we propose two novel feature extraction approaches for finding the best risk-factors, followed by applying a machine learning pipeline for the long term prediction of type 2 diabetes. The proposed methods have been evaluated using data from a longitudinal clinical study, known as the San Antonio Heart Study. Our proposed model managed to achieve 95.94% accuracy in predicting whether a person will develop type 2 diabetes within the next 7-8 years or not.

show abstract

“…Logistic regression is a meta-level learning classifier that predicts the outcome of a categorical dependent variable from a set of predictor or independent variables [36]. The given data can be used to calculate the probability of a discrete outcome.…”

Section: F Logistic Regressionmentioning

confidence: 99%

Classifier Algorithms and Ensemble Models for Diabetes Mellitus Prediction: A Review

2021

IJATCSE

View full text Add to dashboard Cite

Timely disease prediction means a lot to the improvement of the health care services and this will go a long way to assist populaces to avoid unsafe health circumstances before resulting in complex medical situations. Diabetes Mellitus as one of the deadly diseases that is described by hyperglycemia taking place due to defects in insulin secretion which allow an irregular increase in glucose level. Diabetes Mellitus can lead to loss of sight, non-traumatic lower extremity amputation, chronic kidney disease, coronary heart disease, stroke, etc. Hence, prompt diagnosis of the Diabetes Mellitus disease has to pay more attention to in the recent area of research. Presently, there is a great and wide work carried out on Machine Learning with a focus on medical and its application. This paper reviewed recent journalsthat made use of Artificial Intelligencetechniques, different classifiers and ensemble methods to assist in the management of diabetes. Classifiers algorithms such as Naive Bayes, Decision Tree, Artificial Neural Network, Support Vector Machine, K-Nearest Neighbour and Multi-Layer Perceptron. The results from over 1,137most related reviewed journalsreveled that Ensemble Models have the highest average accuracy of 87.09 % in respect to prediction of diabetes mellitus

show abstract

A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

Cited by 26 publications

References 60 publications

Intensive Care Unit Mortality Prediction: An Improved Patient-Specific Stacking Ensemble Model

Intensive Care Unit Mortality Prediction: An Improved Patient-Specific Stacking Ensemble Model

Advanced Techniques for Predicting the Future Progression of Type 2 Diabetes

Classifier Algorithms and Ensemble Models for Diabetes Mellitus Prediction: A Review

Contact Info

Product

Resources

About