An Comparative Analysis of Hybrid Ann With Logistic Regression Approach for Diabetic Prediction

Main Article Content

R. Jeyakanth
S. Chidambaram


Diabetes is one of the most serious illnesses that affects a lot of people. Obesity, inactivity, genetic diabetes, a poor lifestyle, eating unhealthily, high blood pressure, etc. can all add to diabetes mellitus. Patients with diabetes are more prone to illnesses including heart disease, kidney disease, stroke, visual problems, nerve damage, etc. A variety of tests are now routinely used in hospitals to acquire the information required for a diabetes diagnosis, and the diagnosis is then used to determine the appropriate course of treatment. Big data analytics is essential in the healthcare industry. The healthcare industry uses huge databases. With the use of big data analytics, it is possible to analyse enormous datasets, unearth concealed information, and discover concealed patterns in order to derive knowledge from the data and accurately foresee outcomes. The current strategy has poor categorization and prediction accuracy. In this project, we identify diabetics using a hybrid machine learning method called Hybrid ANN with a Logistic approach. We were able to attain high accuracy of over 90% with this strategy throughout testing and training.

Article Details

How to Cite
R. Jeyakanth, & S. Chidambaram. (2023). An Comparative Analysis of Hybrid Ann With Logistic Regression Approach for Diabetic Prediction. Journal of Coastal Life Medicine, 11(1), 2248–2256. Retrieved from


Rahatara Ferdousi,M.Anwar Hossain, and Abduk motaleb ElSaddik. “Ancient- platform threat vaticination of Non Communicable Disease utilizing Machine Learning in Health ” IEEE Access July, 2021. Vol 10,No. 110.

Sachin Ahuja and Huma Naz. utilizing the Indian PIMA dataset, a deep literacy plan for diabetes vaccination will be published in March 2020. in 2020, Springer Nature Switzerland AG., “An Integration of Archerfish Hunter specked Hyena optimization and Improved ELM Classifier for Multicollinear Big data Classification Tasks”, Neural Processing Letters, (SCI enrolled bump proxy2.908), DoI https//

“Diabetes forecasting refined With connected Machine knowledge" is the title of an advertisement featuring Usama Ahamed, Muhammad Adnan Khan, and et al., IEEE Access, January 2022, Issue 10, No 314.

International Journal of Advanced Directions in Computer Science and Engineering, Chidambaram S. et al., "Optimal mark subset choosing and MSVM classification based CBIR for Medical pictures," ISSN 2278- 3091, Vol. 9, Issue No. 4, August 2020.

Wei Zhou, Shengwu Liao, Xiakang Liang, and Ebtesam N. Alshemmary, Ming Ma. Radiomics Features for “Automated Diabetic Foot Prediction utilizing Fundus Pictures”, IEEE Access Volume 10, Number 3358, July 2021.

Diabetes Mellitus Affected Cases Bracket and Opinion by Machine Learning Patterns by Francesco Mercaldoa, Vittoria Nardoneb, and Antonella Santone. In September 2017, Marseille, France hosted KES2017, an international conference on wisdom-based and brainy data and engineering systems.

Sami Azam, Friso De Boer, Eva Ignatious, Ryana Quadir, Abhijith Reddy, Beera Volu, and Linta Antony. "A entire Unsupervised Framework for Habitual Order Disease Prediction".10.1109ACCESS.2021.3109168 is the DOI for this thing, September 2021.

Enrico Longato, Barbara Di Camillo, Gian Paolo Fadini, Giovanni Sparacino, Angelo Avogaro, Lara Tramontan. Executive Claims A Deep Learning system to Predict Diabetes Cardiovascular Complications. Vol. 25,No. 9, September 2021.

HCUP National Inpatient Sample(NIS), Agency for Healthcare Research and Quality (AHRQ), 2011. (Online) http//

Clashing Diabetes Forecasting Early Diabetes Patient Hospital Readmittance to Assist Improve Case, Care,X. Charlie,C. Christina, and P. Stephone, 2018., “Performance assessment of source vector machine classification approaches in data mining”, Cluster Computing The Journal of Networks, Software Tools- Springer (SCI Indexed), ISSN 1386- 7857, Feb 2018, DOI10.1007/ s10586-018-2036-z.

X. Yifan andJ. Sharma, "Diabetes case readmission vaticination applying large data analytical tools," http//, 2016.

Zhu, Meiying An 11-year retrospective analysis of death instruments, "Mortality Rates and the Causations of Passing Connected to Diabetes Mellitus in Shanghai Songjiang District ” BMC Endocrine diseases 15(2015) 45. PMC. Web.21Nov. 2017

"Defeat Diabetes Forecasting Early Diabetes Patient Hospital Readmittance to assist Improve Case Care," Charlie Xu, Stephone Christian, and Christina Pan, December 2018, Volume 2014, No. 781.

"Realtime Adaptive Miniatures for the Demonstrated Prediction of Glycemic Layout in Type 1 Diabetes Cases," Volume 14, No 2, February 2017, Pages 168 to 174 A. Prountzou, S. G. Mougiakakou, P. Diem, and E. Daskalaki.

The experimental paper "Tree- grounded classifier ensembles for early diabetes identification" appeared in the March 2019 issue of the journal Diabetes. K.H. Rhee as well as B.A. Tama.

A Tree-Predicated ensemble method-based objective inquiry by J. Liu, L. Wang, L. Zhang, Z. Zhang, and S. Zhang entitled "Predictive analytics for the absorption of blood glucose" appears in Issue 8, Number 0171, published in December 2020.