Early Prediction of Diabetes Using an Ensemble of Machine Learning Models
Open accessThe DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index.
Abstract
Diabetes is one of the most rapidly spreading diseases in the world, resulting in an array of significant complications, including cardiovascular disease, kidney failure, diabetic retinopathy, and neuropathy, among others, which contribute to an increase in morbidity and mortality rate. If diabetes is diagnosed at an early stage, its severity and underlying risk factors can be significantly reduced. However, there is a shortage of labeled data and the occurrence of outliers or data missingness in clinical datasets that are reliable and effective for diabetes prediction, making it a challenging endeavor. Therefore, we introduce a newly labeled diabetes dataset from a South Asian nation (Bangladesh). In addition, we suggest an automated classification pipeline that includes a weighted ensemble of machine learning (ML) classifiers: Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), XGBoost (XGB), and LightGBM (LGB). Grid search hyperparameter optimization is employed to tune the critical hyperparameters of these ML models. Furthermore, missing value imputation, feature selection, and K-fold cross-validation are included in the framework design. A statistical analysis of variance (ANOVA) test reveals that the performance of diabetes prediction significantly improves when the proposed weighted ensemble (DT + RF + XGB + LGB) is executed with the introduced preprocessing, with the highest accuracy of 0.735 and an area under the ROC curve (AUC) of 0.832. In conjunction with the suggested ensemble model, our statistical imputation and RF-based feature selection techniques produced the best results for early diabetes prediction. Moreover, the presented new dataset will contribute to developing and implementing robust ML models for diabetes prediction utilizing population-level data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013) · Wiley Series in Probability and Statistics · doi:10.1002/9781118548387 · Cited by 13,861
An Introduction to Statistical Learning
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013) · Springer Texts in Statistics · doi:10.1007/978-1-4614-7138-7 · Cited by 12,106 · cited 1×
“FS approaches are commonly implemented in model simplifi-cation for more straightforward interpretation, reduced training times, reduced dimensionality, enhanced predictive accuracy by choosing the relevant features, and avoiding over-fitting [52,53].”
Saeedi, P., Petersohn, I., Salpea, P., Malanda, B., Karuranga, S., Unwin, N., Colagiuri, S., Guariguata, L., Motala, A. A., Ogurtsova, K., et al. (2019) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2019.107843 · Cited by 10,792
Global Burden of Disease Cancer Collaboration, Fitzmaurice, C., Allen, C., Barber, R. M., Barregard, L., Bhutta, Z. A., Brenner, H., Dicker, D. J., Chimed-Orchir, O., Dandona, R., et al. (2017) · JAMA Oncology · doi:10.1001/jamaoncol.2016.5688 · Cited by 6,215 · cited 1×
“According to Fitzmaurice et al. [3], the percentage of adults around the world who had diabetes in 2017 was roughly 8.8%, and it is projected that by 2045, this percentage will rise to 9.9%.”
MethodInfluentialBiau, G., & Scornet, E. (2016) · Test · doi:10.1007/s11749-016-0481-7 · Cited by 4,149 · cited 1×
“…Bayes (NB) [18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN) [26] have been employed in the prediction of diabetes…”
MethodA survey of cross-validation procedures for model selection
Arlot, S., & Célisse, A. (2010) · LillOA (Université de Lille (University Of Lille)) · Cited by 3,663
Danaei, G., Finucane, M. M., Lu, Y., Singh, G. M., Cowan, M. J., Paciorek, C. J., Lin, J. K., Farzadfar, F., Khang, Y.-H., Stevens, G. A., et al. (2011) · The Lancet · doi:10.1016/s0140-6736(11)60679-x · Cited by 3,568
A survey of cross-validation procedures for model selection
Arlot, S., & Celisse, A. (2010) · Statistics Surveys · doi:10.1214/09-ss054 · Cited by 3,522 · cited 1×
“K-Fold Cross-Validation K-fold Cross-Validation (KCV) is one of the most extensively employed methods for selecting classifiers and predicting error [58].”
MethodA systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088 · cited 1×
“A class imbalance problem emerges when the frequency of one class (for example, cancer) can be 1000 times lower than that of another class (for example, healthy patient) [47].”
BackgroundState-of-the-art in artificial neural network applications: A survey
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018) · Heliyon · doi:10.1016/j.heliyon.2018.e00938 · Cited by 3,054 · cited 1×
“…(LDA) [16], Quadratic Discriminant Analysis (QDA) [17], Naive Bayes (NB) [18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN)…”
Diagnosis and classification of diabetes mellitus
American Diabetes Association (2009) · Diabetes Care · doi:10.2337/dc09-s062 · Cited by 1,817
A review of feature selection methods with applications
Jovic, A., Brkic, K., & Bogunovic, N. (2015) · 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) · doi:10.1109/mipro.2015.7160458 · Cited by 1,209 · cited 1×
“Among the supervised, semi-supervised, and unsupervised FS procedures, the supervised FS method typically outperforms the others [31,54].”
MethodDecision tree methods: applications for classification and prediction.
Song, Y. Y., & Lü, Y. (2015) · PubMed · doi:10.11919/j.issn.1002-0829.215044 · Cited by 1,132 · cited 1×
“…Discriminant Analysis (QDA) [17], Naive Bayes (NB) [18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN) [26] have been employed…”
MethodCross-validation pitfalls when selecting and assessing regression and classification models
Krstajic, D., Buturovic, L. J., Leahy, D. E., & Thomas, S. (2014) · Journal of Cheminformatics · doi:10.1186/1758-2946-6-10 · Cited by 1,090 · cited 1×
“Then we fine-tuned the hyperparameters by applying the grid search algorithm [59].”
MethodHyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.06560 · Cited by 1,018 · cited 2×
“Since ML algorithms are sensitive to multiple hyperparameters, they need the best batch of hyperparameters [31,60,61].”
BackgroundType 1 Diabetes Through the Life Span: A Position Statement of the American Diabetes Association
Chiang, J. L., Kirkman, M. S., Laffel, L. M. B., Peters, A. L., & Authors, O. B. O. T. T. 1. D. S. (2014) · Diabetes Care · doi:10.2337/dc14-1140 · Cited by 965 · cited 1×
“It accounts for around 5.0% to 10.0% of all cases of diabetes [9,10] and is generally diagnosed in children and young adults [11].”
BackgroundInfluentialPredicting Diabetes Mellitus With Machine Learning Techniques
Zou, Q., Qu, K., Luo, Y., Yin, D., Ju, Y., & Tang, H. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00515 · Cited by 920 · cited 1×
“2018 [37] LMHC None None All RF Acc: 0.”
BackgroundPrediction of Diabetes using Classification Algorithms
Sisodia, D., & Sisodia, D. S. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.05.122 · Cited by 900 · cited 1×
“The authors in [30] used three distinct ML classifiers: NB, DT, and SVM, in order to predict diabetes and found that NB provided the highest AUC value.”
MethodPattern classification with missing data: a review
García-Laencina, P. J., Sancho-Gómez, J.-L., & Figueiras-Vidal, A. R. (2010) · Neural Computing and Applications · doi:10.1007/s00521-009-0295-6 · Cited by 759 · cited 1×
“For MVI purposes, median and KNN-based imputation techniques have been applied most frequently for several decades [15,51].”
MethodClass imbalances versus small disjuncts
Jo, T., & Japkowicz, N. (2004) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1007730.1007737 · Cited by 683 · cited 1×
“Classes with a substantial number of instances are referred to as majority classes, whereas classes with fewer instances are known as minority classes [46].”
BackgroundDiabetes Prediction Using Ensembling of Different Machine Learning Classifiers
Hasan, M. K., Alam, M. A., Das, D., Hossain, E., & Hasan, M. (2020) · IEEE Access · doi:10.1109/access.2020.2989857 · Cited by 604 · cited 9×
“The boosting classifiers applied in this article are extreme gradient boosting and one of the well-known gradient boosting procedures (ensemble), which improved interpretation and swiftness in tree-based ML algorithms [31,64].”
BackgroundMethodInfluentialSelf-citationMitteroecker, P., & Bookstein, F. (2011) · Evolutionary Biology · doi:10.1007/s11692-011-9109-8 · Cited by 504 · cited 1×
“Different machine learning (ML) algorithms, for instance, Linear Discriminant Analysis (LDA) [16], Quadratic Discriminant Analysis (QDA) [17], Naive Bayes (NB) [18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23],…”
MethodTaha, A. A., & Malebary, S. J. (2020) · IEEE Access · doi:10.1109/access.2020.2971354 · Cited by 443 · cited 1×
“LGB Classifier LGB is based on DT techniques, employing a technique known as Gradient-based One-side Sampling (GOSS) and Exclusive Feature Bundling (EFB), which takes advantage of leaf-and level-wises tactics to speed up the training process [62,63] (see Algorithm 5).”
MethodSkin lesion classification with ensembles of deep convolutional neural networks
Harangi, B. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.08.006 · Cited by 439
The global implications of diabetes and cancer
Shi, Y., & Hu, F. B. (2014) · The Lancet · doi:10.1016/s0140-6736(14)60886-2 · Cited by 424 · cited 1×
“It accounts for more than 90.0% of all instances of diabetes according to Shi and Hu [12], and is not only prevalent in those older than 45 years old but also in younger age groups such as children, adolescents, and young adults.”
BackgroundInfluentialAnalysis of diabetes mellitus for early prediction using optimal features selection
Sneha, N., & Gangil, T. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0175-6 · Cited by 407
Decision Tree Analysis on J48 Algorithm for Data Mining
Bhargava, N., Sharma, G., Bhargava, R., & Mathuria, M. (2013) · Computer Science and Software Engineering · Cited by 369
Classification and prediction of diabetes disease using machine learning paradigm
Maniruzzaman, M., Rahman, M. J., Ahammed, B., & Abedin, M. M. (2020) · Health Information Science and Systems · doi:10.1007/s13755-019-0095-z · Cited by 369
Linear vs. quadratic discriminant analysis classifier: a tutorial
Tharwat, A. (2016) · International Journal of Applied Pattern Recognition · doi:10.1504/ijapr.2016.079050 · Cited by 352 · cited 1×
“Different machine learning (ML) algorithms, for instance, Linear Discriminant Analysis (LDA) [16], Quadratic Discriminant Analysis (QDA) [17], Naive Bayes (NB) [18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23],…”
MethodAkter, S., Rahman, M. M., Abe, S. K., & Sultana, P. (2014) · Bulletin of the World Health Organization · doi:10.2471/blt.13.128371 · Cited by 325 · cited 1×
“The percentage of diabetes patients in the intended geographic region, which is Bangladesh, skyrocketed to 10.0% in 2011, up from 4.0% in 1995–2000, 5.0% in 2001–2005, and 6.0% in 2006–2010, in consonance with Akter et al. [6].”
BackgroundInfluentialApplication of high-dimensional feature selection: evaluation for genomic prediction in man
Bermingham, M. L., Pong-Wong, R., Spiliopoulou, A., Hayward, C., Rudan, I., Campbell, H., Wright, A. F., Wilson, J. F., Agakov, F., Navarro, P., et al. (2015) · Scientific Reports · doi:10.1038/srep10312 · Cited by 322 · cited 1×
“FS approaches are commonly implemented in model simplifi-cation for more straightforward interpretation, reduced training times, reduced dimensionality, enhanced predictive accuracy by choosing the relevant features, and avoiding over-fitting [52,53].”
Predictive modelling and analytics for diabetes using a machine learning approach
Kaur, H., & Kumari, V. (2022) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.12.004 · Cited by 317
Diabetes in developing countries
Misra, A., Gopalan, H., Jayawardena, R., Hills, A. P., Soares, M., Reza‐Albarrán, A. A., & Ramaiya, K. L. (2019) · Journal of Diabetes · doi:10.1111/1753-0407.12913 · Cited by 300
Performance Analysis of Data Mining Classification Techniques to Predict Diabetes
Perveen, S., Shahbaz, M., Guergachi, A., & Keshavjee, K. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.016 · Cited by 290 · cited 1×
“In [34], the ensemble AB model performed better than the Bagging ensemble model when it came to classifying diabetes mellitus (DM).”
MethodAccurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers
Maniruzzaman, M., Rahman, M. J., Al-MehediHasan, M., Suri, H. S., Abedin, M. M., El-Baz, A., & Suri, J. S. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-0940-7 · Cited by 275 · cited 1×
“…[18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN) [26] have been employed in the prediction of diabetes diseases [14,27,28].”
MethodComparative approaches for classification of diabetes mellitus data: Machine learning paradigm
Maniruzzaman, M., Kumar, N., Menhazul Abedin, M., Shaykhul Islam, M., Suri, H. S., El-Baz, A. S., & Suri, J. S. (2017) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2017.09.004 · Cited by 270 · cited 2×
“Due to non-linearity, non-normality, and the complicated and linked structure in the majority of medical data, diabetes data categorization is a challenging endeavor [14].”
BackgroundMethodChen, C., Zhang, Q., Yu, B., Yu, Z., Lawrence, P. J., Ma, Q., & Zhang, Y. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103899 · Cited by 238 · cited 1×
“Therefore, for executing the ablation analyses for our suggested DDC datasets, this paper employs the four most typically exploited supervised FS techniques: RF, Information Gain (IG) [55], XGB [56], and LightGBM (LGB) [57], to minimize attribute redundancy.”
MethodSmart home health monitoring system for predicting type 2 diabetes and hypertension
Chatrati, S. P., Hossain, G., Goyal, A., Bhan, A., Bhattacharya, S., Gaurav, D., & Tiwari, S. M. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.01.010 · Cited by 213 · cited 1×
“2020 [43] PIDD Case deletion None 2 SVM AUC: 0.”
BackgroundImbalance class problems in data mining: a review
Ali, H., Salleh, M. N. M., Saedudin, R. R., Hussain, K., & Mushtaq, M. F. (2019) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v14.i3.pp1552-1563 · Cited by 200 · cited 1×
“The majority class samples outnumber the minority class samples according to the class ratios, which can be 100 to 1 or 1000 to 1 or so on [48].”
BackgroundSikder, N., Masud, M., Bairagi, A. K., Arif, A. S. M., Nahid, A.-A., & Alhumyani, H. A. (2021) · Symmetry · doi:10.3390/sym13040670 · Cited by 196 · cited 1×
“…explained (GNB, BNB, RF, DT, XGB, LGB), are utilized for the ensemble frameworks as they can enhance the effectiveness of ML-based classifiers [31,66] and outperform in numerous medical fields, for instance, pneumonia, diabetic retinopathy, and measles vaccination uptake classifications [64,67,68].”
MethodSelf-citationYang, H., Luo, Y., Ren, X., Wu, M., He, X., Peng, B., Deng, K., Yan, D., Tang, H., & Lin, H. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.02.015 · Cited by 191 · cited 1×
“2021 [45] LMHC Case deletion ANOVA, GI 16 XGB AUC: 0.”
BackgroundHasan, M. K., Alam, M. A., Roy, S., Dutta, A., Jawad, M. T., & Das, S. (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100799 · Cited by 158 · cited 6×
“However, the practical dataset commonly includes an abnormal proportion of missing values, typically represented as NaNs, null, blanks, undefined, or similar place-holders [15].”
BackgroundMethodResultInfluentialSelf-citationA Feature Selection Method Based on Information Gain and Genetic Algorithm
Lei, S. (2012) · International Conference on Computer Science and Electronics Engineering (ICCSEE) · doi:10.1109/iccsee.2012.97 · Cited by 157 · cited 1×
“Therefore, for executing the ablation analyses for our suggested DDC datasets, this paper employs the four most typically exploited supervised FS techniques: RF, Information Gain (IG) [55], XGB [56], and LightGBM (LGB) [57], to minimize attribute redundancy.”
MethodBashir, S., Qamar, U., & Khan, F. H. (2015) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2015.12.001 · Cited by 147 · cited 1×
“…[18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN) [26] have been employed in the prediction of diabetes diseases [14,27,28].”
MethodWang, Q., Cao, W., Guo, J., Ren, J., Cheng, Y., & Davis, D. N. (2019) · IEEE Access · doi:10.1109/access.2019.2929866 · Cited by 142
Transfer learning for class imbalance problems with inadequate data
Al-Stouhi, S., & Reddy, C. K. (2015) · Knowledge and Information Systems · doi:10.1007/s10115-015-0870-3 · Cited by 132 · cited 1×
“Therefore, DDC datasets are standard datasets [49], with an approximately equal number of samples in each class.”
BackgroundDai, R., Zhang, W., Tang, W., Wynendaele, E., Zhu, Q., Bin, Y., Spiegeleer, B. D., & Xia, J. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01115 · Cited by 116 · cited 1×
“…including sensitivity ( Sn ), specificity ( Sp ), accuracy ( Acc ), and the receiver operating characteristic (ROC) curve with AUC value [15,69,70], which are estimated in this way: where TP , FN , TN , and FP indicate the numbers of true positives, false negatives, true negatives, and false…”
BackgroundType 2 diabetes and its correlates among adults in Bangladesh: a population based study
Chowdhury, M. A. B., Uddin, M. J., Khan, H. M. R., & Haque, M. R. (2015) · BMC Public Health · doi:10.1186/s12889-015-2413-y · Cited by 112 · cited 3×
“Using data from the 2011 BDHS, Chowdhury et al. [71] discovered that the overall prevalence of diabetes was 11%, and that the frequency was somewhat lower in males (10.6”
BackgroundMethodInfluentialAwal, M. A., Masud, M., Hossain, M. S., Bulbul, A. A.-M., Mahmud, S., & Bairagi, A. K. (2021) · IEEE Access · doi:10.1109/access.2021.3050852 · Cited by 103 · cited 1×
“Since ML algorithms are sensitive to multiple hyperparameters, they need the best batch of hyperparameters [31,60,61].”
BackgroundSelf-citationComparison and integration of computational methods for deleterious synonymous mutation prediction
Cheng, N., Li, M., Zhao, L., Zhang, B., Yang, Y., Zheng, C.-H., & Xia, J. (2019) · Briefings in Bioinformatics · doi:10.1093/bib/bbz047 · Cited by 92
Design Ensemble Machine Learning Model for Breast Cancer Diagnosis
Hsieh, S.-L., Hsieh, S.-H., Cheng, P., Chen, C., Hsu, K.-P., Lee, I.-S., Wang, Z., & Lai, F. (2011) · Journal of Medical Systems · doi:10.1007/s10916-011-9762-6 · Cited by 80 · cited 1×
“…explained (GNB, BNB, RF, DT, XGB, LGB), are utilized for the ensemble frameworks as they can enhance the effectiveness of ML-based classifiers [31,66] and outperform in numerous medical fields, for instance, pneumonia, diabetic retinopathy, and measles vaccination uptake classifications [64,67,68].”
MethodSathi, N. J., Islam, M. A., Ahmed, M. S., & Islam, S. M. S. (2022) · PLoS ONE · doi:10.1371/journal.pone.0267243 · Cited by 62
Self-citationMasud, M., Bairagi, A. K., Nahid, A.-A., Sikder, N., Rubaiee, S., Ahmed, A., & Anand, D. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/8862089 · Cited by 60 · cited 1×
“…explained (GNB, BNB, RF, DT, XGB, LGB), are utilized for the ensemble frameworks as they can enhance the effectiveness of ML-based classifiers [31,66] and outperform in numerous medical fields, for instance, pneumonia, diabetic retinopathy, and measles vaccination uptake classifications [64,67,68].”
MethodSelf-citationIslam, M. M., Rahman, M. J., Roy, D. C., & Maniruzzaman, M. (2020) · Diabetes & Metabolic Syndrome Clinical Research & Reviews · doi:10.1016/j.dsx.2020.03.004 · Cited by 54
Self-citationDetection of Diabetes Using Multilayer Perceptron
Mohapatra, S. K., Swain, J. K., & Mohanty, M. N. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-2182-5_11 · Cited by 51
Rahman, M. A. (2022) · PLoS ONE · doi:10.1371/journal.pone.0274978 · Cited by 47 · cited 1×
“This is despite the fact that some studies are attempting to investigate the prevalence of diabetes in Bangladesh as well as the factors that influence the disease [71–74].”
BackgroundOptimal Feature Selection for EMG-Based Finger Force Estimation Using LightGBM Model
Ye, Y., Liu, C., Zemiti, N., & Yang, C. (2019) · IEEE RO-MAN · doi:10.1109/ro-man46459.2019.8956453 · Cited by 43 · cited 1×
“Therefore, for executing the ablation analyses for our suggested DDC datasets, this paper employs the four most typically exploited supervised FS techniques: RF, Information Gain (IG) [55], XGB [56], and LightGBM (LGB) [57], to minimize attribute redundancy.”
MethodIslam, M. S., Awal, M. A., Laboni, J. N., Pinki, F. T., Karmokar, S., Mumenin, K. M., Al-Ahmadi, S., Rahman, M. A., Hossain, M. S., & Mirjalili, S. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105671 · Cited by 40 · cited 1×
“…of this article has been illustrated in Figure 1 and essentially incorporates and investigates a preprocessing method and an ensemble ML classifier with hyperparameter optimization [50], Missing Value Imputation (MVI), and Feature Selection (FS) schemes are included in the suggested preprocessing.”
MethodSelf-citationRallapalli, S., & Suryakanthi, T. (2016) · International Conference on Advances in Computing and Communication Engineering · doi:10.1109/icacce.2016.8073762 · Cited by 40 · cited 1×
“Moreover, in [33], the authors have suggested a predictive model for classifying diabetes based on several criteria employing the CART and Scalable RF.”
MethodAn Intelligent Approach for Diabetes Classification, Prediction and Description
Rashid, T. A., Abdullah, S. M., & Abdullah, R. M. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-28031-8_28 · Cited by 33 · cited 1×
“The authors of [35] built a prediction model with two sub-modules: ANN and Fasting Blood Sugar (FBS).”
MethodPrediction of Epileptic Seizure by Analysing Time Series EEG Signal Using k -NN Classifier
Hasan, M. K., Ahamed, M. A., Ahmad, M., & Rashid, M. A. (2017) · Applied Bionics and Biomechanics · doi:10.1155/2017/6848014 · Cited by 32 · cited 1×
“…[18], Support Vector Machine (SVM) [19], Artificial Neural Network (ANN) [20], Decision Tree (DT) [21], J48 [22], Random Forest (RF) [23], Logistic Regression (LR) [24], AdaBoost (AB) [25], and K-nearest Neighborhood (KNN) [26] have been employed in the prediction of diabetes diseases [14,27,28].”
MethodSelf-citationHasan, M. K., Jawad, M. T., Dutta, A., Awal, M. A., Islam, M. A., Masud, M., & Al‐Amri, J. F. (2021) · IEEE Access · doi:10.1109/access.2021.3108551 · Cited by 32 · cited 4×
“We have conducted ablation studies to build an appropriate ensemble classifier with improved diabetes categorization results, as it has been revealed that such a classifier yields more profitable results that are experimentally validated in [31,64].”
MethodInfluentialSelf-citationDiabetes Mellitus and Gestational Diabetes Mellitus
Begum, S., Afroz, R., Khanam, Q., Khanom, A., & Choudhury, T. (2015) · Journal of Paediatric Surgeons of Bangladesh · doi:10.3329/jpsb.v5i1.23887 · Cited by 26 · cited 1×
“It accounts for around 5.0% to 10.0% of all cases of diabetes [9,10] and is generally diagnosed in children and young adults [11].”
BackgroundInfluentialHasan, M. K., Aleef, T. A., & Roy, S. (2020) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp50017.2020.9230708 · Cited by 22 · cited 4×
“In a similar vein, researchers working on [36] have utilized a variety of ML techniques, including SVM, AB, Bagging, KNN, and RF algorithms.”
MethodInfluentialSelf-citationBharath, C., Saravanan, N., & Venkatalakshmi, S. (2017) · Brazilian Dental Science · doi:10.14295/bds.2017.v20i3.1437 · Cited by 18 · cited 1×
“It is estimated that around 1.5 million individuals died directly from diabetes in the year 2012, while 2.2 million perished from cardiovascular diseases, chronic kidney disease, and tuberculosis [5].”
BackgroundInfluentialRaihan, M., Islam, M. M., Ghosh, P., Shaj, S. A., Chowdhury, M. R., Mondal, S., & More, A. (2018) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccitechn.2018.8631930 · Cited by 18 · cited 1×
“In a similar vein, researchers working on [36] have utilized a variety of ML techniques, including SVM, AB, Bagging, KNN, and RF algorithms.”
BackgroundSelf-citation
Metadata
- Authors
- Dutta, A., Hasan, M. K., Ahmad, M., Awal, M. A., Islam, M. A., Masud, M., & Meshref, H.
- Venue
- International Journal of Environmental Research and Public Health
- Publisher
- MDPI AG
- Published
- 2022-09-28
- Volume
- 19
- Issue
- 19
- Pages
- 12378
- ISSN
- 1660-4601 (ISSN-L)
- OpenAlex
- W4297478341
- Cited by
- 162
- References
- 66
- FWCI
- 23.42
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.