Deep Learning Techniques for the Prediction of Diabetes: A Review

Sunit Kumar Mishra, Arvind Kumar Tiwari

Kamla Nehru Institute of Technology, Sultanpur, India

Keywords ANN,

CNN, LSTM, BLSTM, SVM, AUC

Abstract Diabetes is a verycommon disease in the world. If diabetes is detected in early stage, it can be cured easily.

Several machine learning techniques are available to predict diabetes in earlier stage using data set. This

paper presents review of several machine learning based methods to predict diabetes.This paper provides

the comparative analysis of Naive Bayes, ANN, SVM, KNN, Random Forest, LSTM, CNN, BLSTM,

ensemble of CNN and LSTM and ensemble of CNN and BLSTM to predict diabetes by taking a dataset.

1 INTRODUCTION

Diabetes is a common disease in our society. Every

third person is affected from this serious disease.

This is caused by irregular life style, bad eating

habits, and lack of exercise and also during

pregnancy. In human body blood sugar level is

controlled by insulin hormone released by

pancreas.When due to any reason secretion of

insulin hormone becomes irregular, blood sugar

level also affected. In this way a person may be

affected from diabetes. The patients affected from

diabetes can be cured by regular exercise, and by

adopting healthy lifestyle. To control blood sugar

level some medicine may be given or insulin may be

given explicitly. To know whether a person is

affected from diabetes, some diagnosis is required. If

we came to know about the disease in early stage,

we may prevent this harmful disease. For early stage

prediction machine learning techniques have been

used (Kerner & Bruckel,2014). Machine learning

techniques learn from dataset to predict outcomes.

Some data is used as a training data which is used to

train and then we can perform prediction using test

data (Bottou,2014).For early stage diabetes

prediction the various researchers have been used

Support Vector Machine(Vishwanathan et

al.,2002),Naive Bayes (Rish,2001), Artificial Neural

Network (Wang,2003), Decision tree (Safavian et

al.,1991)(Pal,2005),K nearest Neighbour (Liao &

Vemuri ,2002),LSTM(Long Short Term

Memory)(Sherstinsky ,2020).

2 RELATED WORK

In the literaturevarious researchers have been

proposed machine learning approaches for

prediction of diabetes. In paper authors (Aljumah et

al.,2013) authors has been proposed SVM based

approach by using the Dataset of disease in Saudi

Arabia to observe obesityand predicts chances of

diabetes in a person. The authors (Chen & Pan

,2018) have been proposed diabetes prediction

model based on boosting algorithms. They

performed non parametric testing using two

algorithms, Adaboost and Logitboost on test data of

35669 individuals and got area under characteristics

curve 0.99. The authors (Mercaido et al.,2017)

worked on the concept of classification. They used

Pima Indians dataset and obtained precision value

0.770 and recall value 0.775.The authors (Patil et

al.,2010) proposed a prediction Model which used

simple K-means algorithm and C4.5

algorithmusingPima Indians diabetes data and

achieved an accuracy of 93.5%.The authors

(Kavakiotis et al.,2017) have been proposed SVM

based model and got the accuracy of 85%. The

authors (Kohli & Arora,2018) have been proposed

logistic regression on separate datasets of heart,

breast cancer and diabetesand got accuracy of

80.77%.The authors (Perveen et al.,2016) performed

classification technique, decision tree J48 and

achieved Area under ROC is 0.98.The authors

(Sisodia, 2018)used DT, SVM and NB classification

methods on Pima Indians Diabetes datasets. NB

gave accuracy of 76.30%. The authors (Kowsher et

al., 2019) proposed that deep ANN gave 95.14%

232

Mishra, S. and Tiwari, A.

Deep Learning Techniques for the Prediction of Diabetes: A Review.

DOI: 10.5220/0010567400003161

In Proceedings of the 3rd International Conference on Advanced Computing and Software Engineering (ICACSE 2021), pages 232-237

ISBN: 978-989-758-544-9

accuracy using dataset of 9483 diabetes patients.

The authors (Srivastava et al.,2019) used Pima

Indian dataset(PIDD) and ANN and achieved the

accuracy of 92%. The authors (Kaur &

Kumari,2020) proposed SVM on PIDD and

achieved accuracy of 89%.The authors

(Maniruzzaman et al.,2020) proposed combination

of Logistic Regression and Random Forest classifier

which gave accuracy of 94.25% and AUC 0.95 on

dataset taken from NHE Survey of 6561

respondents. The authors (Alam et al.,2019) used

OCTA image database with Logistic regression-

based model and found 95.01% sensitivity. The

authors (Zhang et al.,2018) used Multilayer feed

forward network to predict diabetes on PIDD. The

authors (Birjais et al.,2019) proposed the Gradient

Boosting based method for the prediction and

diagnosis of future diabetes risk and got the

accuracy 86%.The authors (Durairaj et al.,2015)

used Back propagation algorithm with Pima Indian

diabetes dataset and achieved an accuracy of

91%.The authors (Dagliati et al.,2018) used random

forest method on ICSM dataset and got accuracy of

77.7%.The authors (Donsa et al.,2015) proposed

ANN model with large clinical dataset and achieved

accuracy of 94%. The author (Dwivedi,2018)

proposed logistic regression technique on the dataset

maintained by NIDDK Diseases and achieved 78%

accuracy. The authors (Fitriyani et al.,2019)

proposed an ensemble learning approach with four

different datasets and achieved accuracy of

75.78%.The authors (Georga et al., 2013) considered

two predictive models support vector regression and

Gaussian process, one for short term glucose control

and second for long term glucose control using

thedatasetconsists of 15 diabetic patients. The

authors (Han et al,2014) have been performed

extraction of rules from SVM using ensemble

learning approach on CHNS data and got precision

of 94.2% and recall 93.9%.The authors (Jankovic et

al.,2016) proposed deep learning methods on the

concentration of glucose, on clinical data. Two layer

networks can be used. First layer performs

prediction whereas second layer is used for

correctness. The authors (Karthikeyan et al., 2019)

proposed rule based classification system to predict

diabetes using PIDD for diabetes and got accuracy

of 81.97%. The authors (Mhaskar et al.,2017) used a

deep learning network for Hypoglycemia:

Euglycemia: Hyperglycemia patients and got

highest accuracy of 79.97%, 81.89% and 62.72%

respectively. The authors (Nilashi et al., 2017)

proposed CART(classification and regression trees)

algorithm on PIDD and got accuracy of 93.6%. The

authors (Pappada et al., 2011) used multi layered

feed forward neural network on clinical dataset of 10

patients, for real time predictions to predict the rise

or fall in glucose level in every 90 minutes.The

authors (Rakshit et al.,2017) proposed neural

network on PIDD dataset and achieved accuracy of

83.3%. The authors (Rashid et al.,2016) proposed

two algorithms one is Artificial neural network, to

predict rate of fasting blood sugar and the second is

decision tree take decision on the basis of symptoms.

The algorithms was applied on the clinical data set

of 500 patients and got accuracy of 84.8% with

feature extraction.The authors (Tama & Rhee, 2019)

proposed LMT (logistic model tree) based

classification techniques for prediction of diabetes in

a patient in early stage, on clinical data and got the

accuracy 96.38%.The authors (Wu J et al., 2009)

proposed a semi supervised machine learning

algorithm Laplacian support vector machine on

Pima indians dataset and achieved accuracy of

82.29%.The authors (Zheng et al., 2017) have been

compared machine learning techniques like KNN

and naïve Bayes.The authors (Choi et al., 2014) have

been developed two models to predict pre-diabetes

one is Artificial Neural Network and the other is

SVM. Data is taken from KNHANES. They got area

under curve using SVM is 0.731 and using ANN is

0.729.The authors ( Park & Edington, 2001)

proposed multilayer neural network with back

propagation model for the prediction of diabetes on

6142 patients and get the sensitivity 86.04%.The

authors (Wu M et al.,2019) used deep learning

techniques to diagnose diabetes and got accuracy

84.95% ,specificity 83.45%, sensitivity 86.44% and

AUC of 0.8540. Authors ( Han et al.,2008) used

Rapid-I’s to analyze Pima Indians Diabetes Dataset.

Theyused ID3 decision tree to predict diabetes with

80% of accuracy. Authors ( Ding et al.,2015) used

extreme learning machine algorithm which uses

single layer feed forward neuralnetwork and also

points out future perspectives of ELM and gave

accuracy of 77.63% on UCI dataset.The authors

(Swapna et al., 2018) performs classification of

HRV and diabetic signals by using long short-term

memory and convolutional neural network or a

combination of both to extract features of input

HRV data which was treated as input to SVM and

got the accuracy of 95.7%.The authors (Yang &

Wright , 2018) proposed convolutional neural

network to predict diabetes on the Brigham and

Women’s Hospital dataset set and got AUC of

0.97.The authors (Ramesh et al.,2017)proposed

Recurrent Deep Neural Network (RNN) model on

PIMA Indian diabetes datasetand got the accuracy of

Deep Learning Techniques for the Prediction of Diabetes: A Review

233

81%.The authors (Hasan et al.,2020) proposed

multilayer perceptron model to predict diabetes

using AUC values as the performance parameter and

got AUC value 0.95 on PIDD. The authors (Naz &

Ahuja, 2020)proposed deep learning model to

predict diabetes on PIDD and got accuracy of 98.07

percent. The authors (Rehman et al., 2020)

proposed DELM based deep learning technique to

predict diabetes got accuracy of 92.8 percent on

sample of 4500. The authors ( Srivastava et

al.,2021) proposed ABC-DNN model to predict

diabetes using PIDD and got accuracy of 94.74

percent. The authors (Bora et al., 2021) proposed a

deep learning model for predicting the risk of

development of diabetic retinopathy on a set of

575431 eyes and got ROC value 0.79.

3 MATERIALS AND METHODS

Here, in this paper the description of diabetes

dataset, methodology to compare the performance of

various machine learning models has been provided.

3.1 Data Description

In this paper the PIMA Indian diabetes dataset

(Thomas et al., 2019) was used which was taken

from Kaggle(https://www.kaggle.com/uciml/pima-

indians-diabetes-database) . It is made to predict

diabetes in women more than 21 years of age. It

contains eight attributes or input variables and one

output variable. The attributes are as follows:

Pregnancies: It represents number of pregnancies of

a woman. During pregnancy the glucose level of

women may increase which is called gestational

diabetes. If women got pregnant number of times the

gestational diabetes may leads to diabetes mellitus.

Glucose: It represents glucose concentration in

blood. If glucose concentration in blood increases

than a certain value then it may cause diabetes.

Blood Pressure: It represents BP(diastolic in mm

Hg). Higher diastolic blood pressure increases the

risk of diabetes.

BMI: It represents body mass index (weight

(kg)/height (m)^2). It determines the obesity of the

patient. Hence it is an important metric to predict

diabetes.

Skin Thickness: It represents skin thickness (mm).

In case of varying ratio of muscle mass and fat mass

BMI is not adequate parameter to assess obesity

which may lead to diabetes. Hence triceps skinfold

thickness plays an important role to predict the

patient may be diabetic or not.

Insulin: It represents serum insulin (mu U/ml). It is

2 hour serum insulin which indicates that how the

body of a person respond on taking food.

Diabetes Pedigree Function:It is a function which

determines the probability of diabetes on the basis of

diabetic family history of a person.

Age: It is generally observed that person having age

greater than 60 years are more prone to diabetes.

3.2 Performance Evaluation

In this paper the Accuracy, Precision, Recall, F1

Score and AUCare used to measure the performance

of the proposed approach.Accuracy of the models is

determined by confusion metrics through K-Fold

cross validation. The Confusion matrix consists of

True Positive (TP), True Negative (TN), and

Falsepositive (FP) and False Negative (FP) where:

Accuracy = TP + TN (1)

TP + TN + FP + FN

Precision = TP (2)

TP + FP

Recall = TP (3)

TP + FN

F1 score = 2*(Recall * Precision) (4)

Recall + precision

AUC-ROC Curve

AUC-ROC curve is used for measuring the

performance of classification problems. ROC

represents a curve of probability and AUC defines

the degree of separability. It defines the capability of

a model to distinguish between classes. Higher the

AUC value better will be the prediction.ROC curve

can be drawn by using TPR(true positive rate also

known as Recall) and FPR(False positive rate). See

Figure 1.

FPR

TPR

ROC

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

234

TPR/Recall = TP

TP+FN (5)

Specificity = TN (6)

TN+FP

FPR = 1 – Specificity (7)

FPR = FP (8)

TN + FP

3.3 Methodology

In this paper, the dataset is loaded on Jupiter

Notebook. Then data cleaning is performed using

Python queries. All the analysis is carried out on

Jupiter Notebook on Anaconda. For the comparative

analysis this paper uses the Naive Bayes, ANN,

SVM, KNN, Random Forest, LSTM, CNN,

BLSTM, ensemble of CNN and

LSTMandensembleof CNN and BLSTM.

4 COMPARATIVE ANALYSIS

This paper used the PIMA Indian diabetes dataset

taken from Kaggle and uploaded onto the Jupitor

Notebook. After data cleaning and pre-processing

the data is converted into numpy array which is

required for machine learning models.Here 10 fold

cross validation is used for the performance

evaluation.For the comparative analysis this paper

uses the Naive Bayes, ANN, SVM, KNN, Random

Forest, LSTM, CNN, BLSTM, ensemble of CNN

and LSTM and ensemble of CNN and BLSTM for

the prediction of diabetes (See Table - 1).

Table 1: Comparative analysis of Machine Learning Based

Approaches

ML Model

Accuracy

Precision

Recall

F1 Score

AUC

NAIV

BAYE

0.90

0.88

0.89

0.96

RAND

FORE

0.96

0.95

0.97

0.96

0.98

SVM 0.92

0.92

0.91

0.97

KNN 0.90

0.92

0.86

0.89

0.95

ANN 0.96

0.96

0.95

0.96

LSTM 0.95

0.94

0.95

0.94

0.95

BLST

0.96

0.95

0.96

CNN 0.96

0.96

0.95

0.96

CNN+

LSTM

0.97

0.96

0.97

CNN+

BLST

0.96

From the comparative analysis it is observed that

deep learningapproachesperformed better in

comparison tosimple machine learning algorithms

like Naive Bayes, ANN, SVM, KNN, Random

Forest etc.

5 CONCLUSIONS

To predict the early stage of diabetes is one of the

most challenging and important task. If diabetes is

detected in early stage, it can be cured easily.

Several machine learning techniques are available to

predict diabetes in earlier stage using data set. This

paper has been presentedareview of several machine

learning based for the prediction of

diabetes.Thispaper also provided the comparative

analysis of Naive Bayes, ANN, SVM, KNN,

Random Forest, LSTM, CNN, BLSTM, ensemble of

CNN and LSTM and ensemble of CNN and BLSTM

for the prediction of diabetes by using PIDD. The

comparative analysis shown that deep learning

approaches performs better in comparison simple

machine learning algorithms like Naive Bayes,

ANN, SVM, KNN, Random Forest etc.

REFERENCES

Alam, M., Le, D., Lim, J. I., Chan, R. V., & Yao, X.

(2019). Supervised machine learning based multi-task

artificial intelligence classification of

retinopathies. Journal of clinical medicine, 8(6), 872.

Aljumah, A. A., Ahamad, M. G., &Siddiqui, M. K. (2013).

Application of data mining: Diabetes health care in

young and old patients. Journal of King Saud

University-Computer and Information Sciences, 25(2),

127-136.

Birjais, R., Mourya, A. K., Chauhan, R., &Kaur, H.

(2019). Prediction and diagnosis of future diabetes

Deep Learning Techniques for the Prediction of Diabetes: A Review

235

risk: a machine learning approach. SN Applied

Sciences, 1(9), 1112.

Bora, A., Balasubramanian, S., Babenko, B., Virmani, S.,

Venugopalan, S., Mitani, A., ... &Bavishi, P. (2021).

Predicting the risk of developing diabetic retinopathy

using deep learning. The Lancet Digital Health, 3(1),

e10-e19.

Bottou, L. (2014). From machine learning to machine

reasoning. Machine learning, 94(2), 133-149.

Chen, P., & Pan, C. (2018). Diabetes classification model

based on boosting algorithms. BMC

bioinformatics, 19(1), 109.

Choi, S. B., Kim, W. J., Yoo, T. K., Park, J. S., Chung, J.

W., Lee, Y. H., ... & Kim, D. W. (2014). Screening for

prediabetes using machine learning

models. Computational and mathematical methods in

medicine, 2014.

Dagliati, A., Marini, S., Sacchi, L., Cogni, G., Teliti, M.,

Tibollo, V., ... &Bellazzi, R. (2018). Machine learning

methods to predict diabetes complications. Journal of

diabetes science and technology, 12(2), 295-302.

Ding, S., Zhao, H., Zhang, Y., Xu, X., &Nie, R. (2015).

Extreme learning machine: algorithm, theory and

applications. Artificial Intelligence Review, 44(1),

103-115.

Donsa, K., Spat, S., Beck, P., Pieber, T. R., &Holzinger, A.

(2015). Towards personalization of diabetes therapy

using computerized decision support and machine

learning: some open problems and challenges.

In Smart Health (pp. 237-260). Springer, Cham.

Durairaj, M., &Kalaiselvi, G. (2015). Prediction of

diabetes using back propagation

algorithm. International Journal of Emerging

Technology and Innovative Engineering, 1(8).

Dwivedi, A. K. (2018). Analysis of computational

intelligence techniques for diabetes mellitus

prediction. Neural Computing and

Applications, 30(12), 3837-3845.

Fitriyani, N. L., Syafrudin, M., Alfian, G., & Rhee, J.

(2019). Development of disease prediction model

based on ensemble learning approach for diabetes and

hypertension. IEEE Access, 7, 144777-144789.

Georga, E. I., Protopappas, V. C., Mougiakakou, S. G., &

Fotiadis, D. I. (2013, November). Short-term vs. long-

term analysis of diabetes data: Application of machine

learning and data mining techniques. In 13th IEEE

International Conference on BioInformatics and

BioEngineering (pp. 1-4). IEEE.

Han, J., Rodriguez, J. C., &Beheshti, M. (2008,

December). Diabetes data analysis and prediction

model discovery using rapidminer. In 2008 Second

international conference on future generation

communication and networking (Vol. 3, pp. 96-99).

IEEE.

Han, L., Luo, S., Yu, J., Pan, L., & Chen, S. (2014). Rule

extraction from support vector machines using

ensemble learning approach: an application for

diagnosis of diabetes. IEEE journal of biomedical and

health informatics, 19(2), 728-734.

Hasan, M. K., Alam, M. A., Das, D., Hossain, E., &Hasan,

M. (2020). Diabetes prediction using ensembling of

different machine learning classifiers. IEEE Access, 8,

76516-76531.

https://www.kaggle.com/uciml/pima-indians-diabetes-

database

Jankovic, M. V., Mosimann, S., Bally, L., Stettler, C.,

&Mougiakakou, S. (2016, November). Deep

prediction model: The case of online adaptive

prediction of subcutaneous glucose. In 2016 13th

Symposium on Neural Networks and Applications

(NEUREL) (pp. 1-5). IEEE.

Karthikeyan, R., Geetha, P., &Ramaraj, E. (2019,

February). Rule Based System for Better Prediction of

Diabetes. In 2019 3rd International Conference on

Computing and Communications Technologies

(ICCCT) (pp. 195-203). IEEE.

Kaur, H., &Kumari, V. (2020). Predictive modelling and

analytics for diabetes using a machine learning

approach. Applied computing and informatics.

Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N.,

Vlahavas, I., &Chouvarda, I. (2017). Machine learning

and data mining methods in diabetes

research. Computational and structural biotechnology

journal, 15, 104-116.

Kerner, W., &Brückel, J. (2014). Definition, classification

and diagnosis of diabetes mellitus. Experimental and

clinical endocrinology & diabetes, 122(07), 384-386.

Kohli, P. S., &Arora, S. (2018, December). Application of

machine learning in disease prediction. In 2018 4th

International Conference on Computing

Communication and Automation (ICCCA) (pp. 1-4).

IEEE.

Kowsher, M., Turaba, M. Y., Sajed, T., &Rahman, M. M.

(2019, December). Prognosis and Treatment

Prediction of Type-2 Diabetes Using Deep Neural

Network and Machine Learning Classifiers. In 2019

22nd International Conference on Computer and

Information Technology (ICCIT) (pp. 1-6). IEEE.

Liao, Y., &Vemuri, V. R. (2002). Use of k-nearest

neighbor classifier for intrusion detection. Computers

& security, 21(5), 439-448.

Maniruzzaman, M., Kumar, N., Abedin, M. M., Islam, M.

S., Suri, H. S., El-Baz, A. S., &Suri, J. S. (2017).

Comparative approaches for classification of diabetes

mellitus data: Machine learning paradigm. Computer

methods and programs in biomedicine, 152, 23-34.

Maniruzzaman, M., Rahman, M. J., Ahammed, B.,

&Abedin, M. M. (2020). Classification and prediction

of diabetes disease using machine learning

paradigm. Health Information Science and

Systems, 8(1), 7.

Mercaldo, F., Nardone, V., &Santone, A. (2017). Diabetes

mellitus affected patients classification and diagnosis

through machine learning techniques. Procedia

computer science, 112, 2519-2528.

Mhaskar, H. N., Pereverzyev, S. V., & van der Walt, M. D.

(2017). A deep learning approach to diabetic blood

glucose prediction. Frontiers in Applied Mathematics

and Statistics, 3, 14.

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

236

Naz, H., &Ahuja, S. (2020). Deep learning approach for

diabetes prediction using PIMA Indian dataset. Journal

of Diabetes & Metabolic Disorders, 19(1), 391-403.

Nilashi, M., bin Ibrahim, O., Ahmadi, H., &Shahmoradi,

L. (2017). An analytical method for diseases

prediction using machine learning

techniques. Computers & Chemical Engineering, 106,

212-223.

Pal, M. (2005). Random forest classifier for remote

sensing classification. International journal of remote

sensing, 26(1), 217-222.

Pappada, S. M., Cameron, B. D., Rosman, P. M., Bourey,

R. E., Papadimos, T. J., Olorunto, W., &Borst, M. J.

(2011). Neural network-based real-time prediction of

glucose in patients with insulin-dependent

diabetes. Diabetes technology & therapeutics, 13(2),

135-141.

Park, J., &Edington, D. W. (2001). A sequential neural

network model for diabetes prediction. Artificial

intelligence in medicine, 23(3), 277-293.

Patil, B. M., Joshi, R. C., &Toshniwal, D. (2010). Hybrid

prediction model for type-2 diabetic patients. Expert

systems with applications, 37(12), 8102-8108.

Perveen, S., Shahbaz, M., Guergachi, A., &Keshavjee, K.

(2016). Performance analysis of data mining

classification techniques to predict diabetes. Procedia

Computer Science, 82, 115-121.

Rakshit, S., Manna, S., Biswas, S., Kundu, R., Gupta, P.,

Maitra, S., & Barman, S. (2017, March). Prediction of

Diabetes Type-II Using a Two-Class Neural Network.

In International Conference on Computational

Intelligence, Communications, and Business

Analytics (pp. 65-71). Springer, Singapore.

Ramesh, S., Caytiles, R. D., &Iyengar, N. C. S. (2017). A

Deep Learning Approach to Identify

Diabetes. Advanced Science and Tech Letter, 145, 44-

49.

Rashid, T. A., Abdullah, S. M., & Abdullah, R. M. (2016).

An intelligent approach for diabetes classification,

prediction and description. In Innovations in Bio-

Inspired Computing and Applications (pp. 323-335).

Springer, Cham.

Rehman, A., Athar, A., Khan, M. A., Abbas, S., Fatima, A.,

&Saeed, A. (2020). Modelling, simulation, and

optimization of diabetes type II prediction using deep

extreme learning machine. Journal of Ambient

Intelligence and Smart Environments, (Preprint), 1-14.

Rish, I. (2001, August). An empirical study of the naive

Bayes classifier. In IJCAI 2001 workshop on empirical

methods in artificial intelligence (Vol. 3, No. 22, pp.

41-46).

Safavian, S. R., &Landgrebe, D. (1991). A survey of

decision tree classifier methodology. IEEE

transactions on systems, man, and cybernetics, 21(3),

660-674.

Sherstinsky, A. (2020). Fundamentals of recurrent neural

network (rnn) and long short-term memory (lstm)

network. Physica D: Nonlinear Phenomena, 404,

132306.

Sisodia, D., &Sisodia, D. S. (2018). Prediction of diabetes

using classification algorithms. Procedia computer

science, 132, 1578-1585.

Srivastava, A. K., Kumar, Y., & Singh, P. K. (2021).

Artificial Bee Colony and Deep Neural Network-

Based Diagnostic Model for Improving the Prediction

Accuracy of Diabetes. International Journal of E-

Health and Medical Communications (IJEHMC),

12(2), 32-50.

Srivastava, S., Sharma, L., Sharma, V., Kumar, A.,

&Darbari, H. (2019). Prediction of Diabetes Using

Artificial Neural Network Approach. In Engineering

Vibration, Communication and Information

Processing (pp. 679-687). Springer, Singapore.

Swapna, G., Vinayakumar, R., &Soman, K. P. (2018).

Diabetes detection using deep learning

algorithms. ICT Express, 4(4), 243-246.

Tama, B. A., & Rhee, K. H. (2019). Tree-based classifier

ensembles for early detection method of diabetes: an

exploratory study. Artificial Intelligence

Review, 51(3), 355-370.

Thomas, J., Joseph, A., Johnson, I., & Thomas, J. (2019).

Machine learning approach for diabetes prediction.

International Journal of Information, 8(2).

Vishwanathan, S. V. M., &Murty, M. N. (2002, May).

SSVM: a simple SVM algorithm. In Proceedings of

the 2002 International Joint Conference on Neural

Networks. IJCNN'02 (Cat. No. 02CH37290) (Vol. 3,

pp. 2393-2398). IEEE.

Wang, S. C. (2003). Artificial neural network.

In Interdisciplinary computing in java

programming (pp. 81-100). Springer, Boston, MA.

Wu, J., Diao, Y. B., Li, M. L., Fang, Y. P., & Ma, D. C.

(2009). A semi-supervised learning based method:

Laplacian support vector machine used in diabetes

disease diagnosis. Interdisciplinary Sciences:

Computational Life Sciences, 1(2), 151-155.

Wu, M., Yang, Y., Wang, H., &Xu, Y. (2019). A deep

learning method to more accurately recall known

lysine acetylation sites. BMC bioinformatics, 20(1),

49.

Yang, B., & Wright, A. (2018). Development of deep

learning algorithms to categorize free-text notes

pertaining to diabetes: convolution neural networks

achieve higher accuracy than support vector

machines. arXiv preprint arXiv:1809.05814.

Zhang, Y., Lin, Z., Kang, Y., Ning, R., &Meng, Y. (2018).

A feed-forward neural network model for the accurate

prediction of diabetes mellitus. International Journal of

Scientific and Technology Research, 7(8), 151-155.

Zheng, T., Xie, W., Xu, L., He, X., Zhang, Y., You, M., ...

& Chen, Y. (2017). A machine learning-based

framework to identify type 2 diabetes through

electronic health records. International journal of

medical informatics, 97, 120-127.

Deep Learning Techniques for the Prediction of Diabetes: A Review

237