MACHINE LEARNING BASED DIETARY RECOMMENDATION AND REMINDER SYSTEM FOR DIABETICS PATIENTS USING RANDOMN FOREST

Diabetes patients often struggle to manage their diets effectively because most existing dietary plans are generalized and do not consider individual factors such as blood glucose levels, Body Mass Index (BMI), age, lifestyle, and personal food preferences. As a result, many patients are unable to maintain stable blood sugar levels are at a higher risk of developing serious complications such as heart disease, kidney damage, nerve damage, and vision problems.

The people most affected are diabetic patients, especially those in developing countries with limited access to healthcare professionals and continuous medical supervision. The problem also affects caregivers and healthcare providers who face difficulties in monitoring patients regularly.

This issue matters because proper dietary management is one of the most important aspects of diabetes control. Poor adherence to meal schedules, forgetfulness, and lack of personalized guidance can worsen a patient's health condition and reduce their quality of life.

There is a significant gap in existing solutions because many digital health applications either provide only basic reminders or generic dietary advice without using intelligent decision-making techniques. Additionally, most systems do not integrate both personalized dietary recommendations and reminder functionalities into a single platform. Therefore, this project addresses this gap by developing a Machine Learning-Based Dietary Recommendation and Reminder System using the Random Forest algorithm to provide personalized, accurate, and timely dietary support for diabetic patients.