Exploratory study on classification of diabetes mellitus through a combined Random Forest Classifier

Abstract

Background Diabetes Mellitus (DM) has become the third chronic non-communicable disease that hits patients after tumors, cardiovascular and cerebrovascular diseases, and has become one of the major public health problems in the world. Therefore, it is of great importance to identify individuals at high risk for DM in order to establish prevention strategies for DM. Methods Aiming at the problem of high-dimensional feature space and high feature redundancy of medical data, as well as the problem of data imbalance often faced. This study explored different supervised classifiers, combined with SVM-SMOTE and two feature dimensionality reduction methods (Logistic stepwise regression and LAASO) to classify the diabetes survey sample data with unbalanced categories and complex related factors. Analysis and discussion of the classification results of 4 supervised classifiers based on 4 data processing methods. Five indicators including Accuracy, Precision, Recall, F1-Score and AUC are selected as the key indicators to evaluate the performance of the classification model. Results According to the result, Random Forest Classifier combining SVM-SMOTE resampling technology and LASSO feature screening method (Accuracy = 0.890, Precision = 0.869, Recall = 0.919, F1-Score = 0.893, AUC = 0.948) proved the best way to tell those at high risk of DM. Besides, the combined algorithm helps enhance the classification performance for prediction of high-risk people of DM. Also, age, region, heart rate, hypertension, hyperlipidemia and BMI are the top six most critical characteristic variables affecting diabetes. Conclusions The Random Forest Classifier combining with SVM-SMOTE and LASSO feature reduction method perform best in identifying high-risk people of DM from individuals. And the combined method proposed in the study would be a good tool for early screening of DM.

Predicting the 2-Year Risk of Progression from Prediabetes to Diabetes Using Machine Learning among Chinese Elderly Adults

“…We acknowledge that the performance of our models was not competitive with results presented in the literature for other relative machine learning research [ 25 , 26 , 27 ]. This may, in part, be attributed to the fact that all of the participants were elderly, who generally had several comorbid diseases.…”

Multi-Tier Ensemble Learning Model With Neighborhood Component Analysis to Predict Health Diseases

“…Their developed model obtained an accuracy of 82.1256% while predicting diabetes mellitus after employing the PID dataset. In comparison, Wang et al [25] developed various supervised ML classifiers with SVM-SMOTE, stepwise logistic regression, and LASSO dimension reduction approaches for classifying diabetes disease after employing a diabetes survey dataset obtained from China National chronic disease survey [25]. Their developed model: RF with SVM-SMOTE obtained an accuracy of 89%, the precision value of 86.9%, recall value of 91.9%, F1-score of 89.3%, and AUC value of 94.8% while classifying diabetes.…”

“…Their developed model generated an accuracy of 98% while predicting chronic liver disease. After examining the prior investigations, it has been revealed that various past studies included either for generating various dimension reduction approaches: attribute permutation and hierarchical clustering approach, binary firefly algorithm, cooperative coevolution technique, LDA, NCA, ReliefF, Chaotic Darcy optimization, CSO, KH, BFO included in [22], [28], [30], [32], [33], [34], [36], or employing various single ML classifiers: DT, SVM, RF, MLP, NB, LR, KNN, XGB, LGBM, SVM-linear included in [5], [9], [13], [14], [16], [17], [18], [21], [23], or developing several combined approaches consisting of various outlier detection and removal approaches along with the imbalance learning algorithms: cluster-based oversampling technique, DBSCAN with SMOTE, Isolation forest with SMOTETomek, IQR algorithm with SMOTE, Instance selection with SMOTE included in [10], [11], [12], [19], [26], or utilizing only single imbalance learning algorithms: SMOTE, SVM-SMOTE included in [20], [24], [25], [27], or implementing hyperparameter optimization strategies: 2level genetic optimizer with c-type SVM, LR with GA optimization strategy included in [29], [35], or implementing several DL-enabled techniques: Conv-LSTM, deep extreme learning model, LSTM, ANN, deep neural network, MLP, convergent artificial intelligence model, deep convolutional neural network, successive encoder-decoder approach, VAE, CLUSTIMP included in [2], [3], [37], [38], [39], [40], [41], [42], [44], [45], [46], [47], [48],…”

A Screening System for COVID-19 Severity using Machine Learning

“…It is a powerful supervised machine learning algorithm that is capable of performing both classification and regression tasks with high accuracy [18]- [20]. Various studies in the medical area have used RF algorithms to, for example, diagnose diabetes mellitus [21], [22], identify cervical cancer [23]- [25], or predict the risk of severity for COVID-19 patients at hospital admission [26].…”