Table 10 Comparison with existing methods for diabetes prediction

[48]

Iyer et al. (2015)

ML model with PIMA Indian

Diabetes dataset

J48

Naïve Bayes

74.86 % (Accuracy)

79.56 % (Accuracy)

[49]

Mamuda et al. (2017)

ML based Learning algorithms

with PIMA Indian Diabetes dataset

Levenberg-Marquardt learning algorithm

Bayesian regulation learning algorithm

Scaled conjugate gradient learning algorithm

0.00025091 (MSE)

2.021e-05 (MSE)

8.3583 (MSE)

[50]

Kaur et al. (2018)

ML based supervised machine

learning algorithm.

Radial Basis Kernel SVM

0.85 (AUC)

[51]

Hang Li et al. (2019)

ML Predictive model

Gradient Boosting Method

0.87 (Recall)

[52]

Soltani et al. (2016)

A new ML based Artificial Neural Network

with PIMA Indian Diabetes dataset

Probabilistic Neural Network (PNN)

81.49%

(Test accuracy)

Proposed Technique

ML based Classifiers with data modeling

approach on PIMA Indian diabetes dataset

Random Forest (RF)

82.82% (Accuracy)

81.59 (Precision)

81.88 (Recall)

0.855 (ROC)

[53]

Zhou et al. (2020)

DPLD (Deep Learning for Predicting

Diabetes) with PIMA Indian Dataset

Enhanced deep neural network with dropout regularization

94.02% (Accuracy)

[54]

Gupta et al. (2021)

ML model and DL Model with PIMA

Indian diabetes dataset

QML (Quantum Machine Learning Model)

DL network trained with root mean square propagation (RMSprop)

0.85 (Accuracy)

0.74 (Precision)

0.79 (F1 score)

0.95 (Accuracy)

0.90 (Precision)

0.93 (F1 score)

[55]

Krishnamoorthi et al. (2022)

Unique Intelligent Diabetes Mellitus Prediction

framework (IDMPF) with PIMA Indian diabetes dataset

Random Forest (RF)

Proposed Logistic Regression

81% (Accuracy)

90% (Accuracy)

Proposed Technique

DL model with PIMA Indian diabetes dataset

7-layered deep convolutional neural network

88.38% (Accuracy)

83.33% (Precision)

Proposed Technique

Customized deep learning with data modeling approach

7-layered deep convolutional neural network with data modeling

96.13% (Accuracy)

94.44% (Precision)

0.957 (AUC)