Unleashing the power of machine learning: Advancing early prediction and analysis of diabetes mellitus

-, Nancy, Sil, Sagarika, Rani, Ritu, Bisla, Nidhi, Jaiswal, Garima and Sharma, Arun (2023) Unleashing the power of machine learning: Advancing early prediction and analysis of diabetes mellitus. In: 2023 World Conference on Communication & Computing (WCONF), 14-16, July,2023, Raipur.

Full text not available from this repository. (Request a copy)


Diabetes is a condition which makes it difficult to regulate blood sugar/glucose. Diabetes is a leading cause of heart failure, stroke, renal failure, disability, blindness, and kidney failure. As per the figures given by International Diabetes Federation, there are 382 million diabetics worldwide. By 2035, there is a possibility that this will increase to 592 million. There are multiple forms of diabetes, and each one is treated differently. The most crucial step, however, is a precise diagnosis of the level of diabetes. Diabetes risk and severity can be significantly reduced if reliable early prognosis is possible. Here, we are proposing a model to predict diabetes using variables like glucose, body mass index (BMI), age, insulin, etc. using Johndasilva dataset. Several machine learning algorithms, including Random Forest(RF), Support Vector Machine (SVM), and Decision Tree (DT), are employed. The model is then chosen among those with the maximum accuracy. Random Forest gave the greatest accuracy of 99.5%.

Item Type: Conference or Workshop Item (Paper)
Keywords: Decision Forest | Diabetes Prediction | Johndasilva Dataset | Machine Learning | Random Forest | Support Vector Machine
Subjects: Social Sciences and humanities > Business, Management and Accounting > General Management
JGU School/Centre: Jindal Global Business School
Depositing User: Amees Mohammad
Date Deposited: 12 Oct 2023 07:48
Last Modified: 12 Oct 2023 07:48
Official URL: https://doi.org/10.1109/WCONF58270.2023.10235242
URI: https://pure.jgu.edu.in/id/eprint/6740


Downloads per month over past year

Actions (login required)

View Item
View Item