International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Insulearner: Machine Intelligence for Diabetes Foreseeing Prof. Sangram S. Dandge1, Aditya Jirapure2, Akshad Khursade3, Ashar Khan4, Tanmay Dhawak5 1 Assistant Professor, Dept. of CSE, Prof Ram Meghe Institute of Technology & Reaserch, Badnera , Amravati,
Maharashtra, India.
2,3,4,5 B.E. Final Year Student’s, Dept. of CSE, Prof Ram Meghe Institute of Technology & Reaserch, Badnera
Amravati, Maharashtra, India. ------------------------------------------------------------------------***------------------------------------------------------------------------professionals better understand and manage diabetes Abstract— Insulearner presents a novel approach to risk.
diabetes prediction by harnessing the power of ensemble learning techniques. Diabetes mellitus poses a significant public health challenge globally, necessitating early and accurate prediction methods for effective management. Leveraging a diverse array of machine learning algorithms including Decision Trees, Random Forest, and Naive Bayes, Insulearner achieves promising results in forecasting diabetes onset. Through a polling technique, the model combines the predictions from multiple algorithms and determines the final outcome based on the majority vote. Experimental evaluation demonstrates competitive test accuracies: Decision Tree (76.62%), Random Forest (72.08%), and Naive Bayes (76.62%). By aggregating the predictions, Insulearner enhances the overall accuracy and reliability of diabetes prediction, offering a valuable tool for proactive healthcare management. This research contributes to the ongoing efforts to advance machine intelligence in healthcare applications, paving the way for early disease detection and personalized treatment strategies.
This research paper explores the underlying principles, methodologies, and potential applications of Insulearner in the field of diabetes forecasting. Through an in-depth examination of existing literature, case studies, and experimental findings, we seek to elucidate the role of machine intelligence in revolutionizing diabetes care and prevention strategies. The subsequent sections will explore the key components of Insulearner, including its data acquisition techniques, predictive modelling approaches, and user interface design. Furthermore, we will analyse the broader implications of Insulearner for various stakeholders, ranging from patients and caregivers to healthcare professionals and policymakers. Through a comprehensive evaluation of Insulearner's capabilities, limitations, and ethical considerations, this paper aims to shed light on its potential to transform diabetes management. In conclusion, Insulearner stands as a testament to the transformative potential of machine intelligence in diabetes management. Through its innovative approach to forecasting blood glucose levels, Insulearner not only empowers individuals with diabetes to take control of their health but also facilitates more proactive and personalized care delivery. As we navigate the complexities of the digital age, projects like Insulearner offer a glimpse into the future of healthcare, where technology serves as a catalyst for improved outcomes, enhanced patient experiences, and ultimately, a healthier society.
Keywords— Machine Intelligence, Decision Tree, Random Forest, Naive Bayes, Polling Technique.
I.
INTRODUCTION
In recent years, the advancement of technology has paved the way for groundbreaking innovations in healthcare. Among these innovations is the development of Insulearner, a project dedicated to leveraging machine intelligence for the early detection and management of diabetes. Diabetes, a chronic condition characterized by high blood sugar levels, affect millions of people worldwide and poses significant health risks if eft untreated or unmanaged. The Insulearner project represents a novel approach to addressing the challenges associated with diabetes by harnessing the power of machine learning. By analysing vast amounts of data related to individual health metrics, lifestyle factors, and genetic predispositions, Insulearner aims to provide personalized insights and predictive analytics to help individuals and healthcare
© 2024, IRJET
|
Impact Factor value: 8.226
II.
LITERATURE REVIEW
KM Jyoti Rani [1] : The study emphasizes the role of machine learning in analysing data to predict the onset of the disease. Employing various algorithms such as K nearest neighbor, Logistic Regression, Randomforest, Support vector machine, and Decision tree, the study evaluates their accuracy in predicting diabetes using a dataset comprising 2000 cases sourced from Kaggle. Results indicate that the Decision tree algorithm
|
ISO 9001:2008 Certified Journal
|
Page 1208