DESIGN AND IMPLEMENTATION OF A FOOD RECOMMENDATION SYSTEM FOR DIABETIC PATIENTS

CHAPTER ONE

INTRODUCTION

1.1 Background of the Study

In today's modern world everyone is so busy in their day to day life and in that hectic life sometimes people tend to eat unhealthy fast food or food that has less nutritious value. Food and nutrition are a key to having good health, they are important for everyone to maintain a healthy diet especially for diabetic patients who have several limitations. In 2021, the International Diabetics Federation (IDF) reported 6.7 million deaths due to diabetes. Diabetes costs the healthcare system approximately USD 966 billion, a 316% rise over the past 15 years. The report captured that 1 in 10 adults, or 537 million people, between the ages of 20 and 79 had diabetes. Impaired glucose tolerance (IGT) affected 541 million adults, putting them at a significant risk of developing type 2 diabetes. One in twenty persons (24 million adults) in Africa had diabetes. According to estimates from the IDF, it is estimated to even get worse. By 2030, it is expected to reach 643 million, and by 2045, it will reach 783 million, that is, there will be 55 million people worldwide with diabetes, a 129% increase from the current level. (IDF, 2021).

Diabetes is a chronic disease that develops when the human body can’t properly process blood sugar. Diabetes can significantly lower life expectancy and negatively affect the quality of life. It is a chronic disease that occurs either when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin it produces. Insulin is a hormone that regulates blood sugar. IDF (2023) defines diabetes mellitus as a persistent condition that affects how the body breaks down food into glucose, which is utilized as energy. Either the body generates little to no insulin, or perhaps the body does not utilize the insulin efficiently, according to IDF's definition of DM. Long-term harm, dysfunction, and failure of various human body organs, including neuropathy (nerve difficulties), retinopathy (eye problems), nephropathy (kidney problems), and macro vascular consequences, are linked to the chronic hyperglycemia effects of diabetes. The severe acute and chronic problems brought on by these detrimental barriers might result in kidney failure, adult-onset blindness, and lower limb amputations. Diabetes comes in three different forms: type 1 diabetes, type 2 diabetes, and gestational diabetes. Kind 1, or insulin-dependent diabetes, affects 5–10% of adults with diabetes and is the most prevalent type (IDF, 2023).

World Health Organization (WHO) estimates that the number of people with diabetes will grow 114% by 2030 (WHO, 1999). Prevalence of type 2 diabetes quickly raised in native and immigrant Asian people too. Therefore, the morbidity and mortality related to the disease and its complications are also common in Asian population. During recent decades, type 2 diabetes have been rapidly increased in Asia. Prevalence of type 2 diabetes at an early age has affected Asian countries economy. So, national preventive strategies must be taken to increase public awareness about the disease and improve standards of care and health in this respect. Diet therapy is essential for effective management of diabetes, type 2 in particular to reduce the risk of long term damage of tissues. Diet/nutrition therapy is a major solution to prevent, manage and control diabetes by managing the nutrition based on the belief that food provides vital medicine and maintains a good health. Typically, diabetic patients need to avoid additional sugar and fat so the food pyramid is recommended to the patients for finding the substitution from the same food group. All suggestions should be offered based on scientific evidences. They have to fit for the individual, considering cultural and personal preferences, beliefs and lifestyle (Evert, et al, 2014).

Humans face a wide range of health problems, including mental and physical health problems. Numerous studies demonstrate that inadequate dietary intake and poor nutrition quality are the primary cause for numerous illnesses and health issues. Heart attacks, ischemic heart disease, and gastrointestinal cancer are the leading causes of death around the world, according to WHO research. Nutrition is an important part of a healthy lifestyle when you have diabetes. Your blood glucose, also known as blood sugar, can be kept within the desired range after a good meal. You must balance what you eat and drink in order to control your blood sugar. According to the National Institute of Diabetes and Digestive and Kidney Diseases, eating the right foods at the right times will help you maintain a healthy blood sugar level (NIDDK, 2023).

Everyone should eat a well-balanced diet to overcome this. A healthy diet is essential for your organs and tissues to function properly. A healthy diet can help strengthen the immune system and prevent disease, according to medical research. A balanced diet includes a wide range of substances, notably water, vitamins, minerals, carbohydrate, proteins, and fats. Medical research has revealed that proper diet plan helps to build up the immune system and fight against diseases. Consumption of proper diet provides energy, vitamins, carbohydrates, proteins, fats, vitamins, minerals, and water multinomial analysis and random forest algorithm is to be integrated to provide healthy diet plan recommendation according to user characteristic.

Because of significant effects of diet therapy combined with improving diseases, nutritionists and practitioners pay more attentions to developing food recommender systems. Recommendation systems are sort of information systems helping people to make decisions in intricate area by suggesting evidence-based pieces of advices. Hence this project looks into the development of a food recommendation system specifically tailored for diabetic patients.

1.2 Statement of Problem   

Diabetes is a pervasive and growing health concern, affecting millions of individuals worldwide. Managing diabetes requires strict adherence to dietary guidelines to maintain optimal blood sugar levels and prevent complications. However, many diabetic patients struggle to identify suitable foods that meet their nutritional needs while accommodating their personal preferences and cultural habits. Current dietary management tools and resources often lack personalization, making it challenging for patients to adhere to recommended dietary plans. Consequently, there is a critical need for a food recommendation system that can provide personalized, evidence-based dietary advice for diabetic patients to help them manage their condition more effectively.

1.3 Aim and Objectives of the Study

The aim of this project work is to develop a Food Recommendation System for Diabetic Patients. The objectives are:

i.       To design and implement the Food Recommendation System using K-Nearest Neighbour (KNN) Machine Learning Algorithm

ii.     To integrate machine learning algorithms to personalize dietary recommendations based on user data

iii.   To evaluate and test the proposed system for accuracy and effectiveness in managing diabetes

1.4 Significance of the Study  

This study addresses a critical challenge for diabetic patients: maintaining a healthy diet that controls blood sugar levels while considering individual preferences and cultural backgrounds. The proposed food recommendation system can empower diabetic patients by providing personalized dietary plans that cater to their specific needs and preferences. This can lead to improved adherence to dietary guidelines and better blood sugar control. Also, by facilitating effective dietary management, the system can potentially help diabetic patients avoid complications associated with poorly controlled blood sugar, such as heart disease, kidney problems, and blindness. The system can be a valuable tool for healthcare professionals by providing personalized dietary recommendations to complement their existing treatment plans. This can lead to better patient outcomes and reduced healthcare costs associated with diabetes complications. Generally, this study has the potential to significantly improve the lives of diabetic patients by empowering them to manage their condition more effectively through personalized dietary recommendations.

1.5 Scope of the Study

This study focuses on the development, evaluation, and potential impact of a food recommendation system designed specifically for diabetic patients. This study employs the use of datasets from the Nigerian Foods database API available at https://nigerianfoods.herokuapp.com and K-Nearest Neighbour (KNN) machine learning algorithm for its implementation.

1.6 Limitations of the Study

While the proposed food recommendation system has the potential to greatly benefit diabetic patients, there are some important limitations to consider. The system's effectiveness relies heavily on the quality and completeness of the underlying data. Inaccurate or incomplete information about food composition, glycemic index, or user preferences could lead to misleading recommendations. The system's ability to personalize recommendations may be limited by the amount and variety of user data collected. Also, the availability and affordability of the technology could limit access for some patients. The system's effectiveness may depend on its integration with existing healthcare practices and communication with patients' doctors or dietitians. These limitations highlight the need for ongoing development and refinement of the food recommendation system.

1.7 Definition of Terms

Diabetic Patients: Individuals diagnosed with diabetes mellitus, a chronic condition affecting blood sugar regulation.

Personalized Diet: A dietary plan tailored to an individual's specific needs, considering factors like blood sugar control, age, weight, activity level, and cultural preferences.

Machine Learning Algorithms: Computer programs that learn from data to make predictions or recommendations. In this project, they will be used to analyze user data and suggest suitable meals.

K-Nearest Neighbors (KNN): K-Nearest Neighbors (KNN) is a simple, yet powerful, supervised machine learning algorithm used for classification and regression tasks.

Glycemic Index (GI): A ranking system that assigns a value to foods based on their impact on blood sugar levels.

User Data: Information collected from diabetic patients using the system, including blood sugar levels, dietary restrictions, and preferences.

Real-Time Data: Data that is collected and analyzed as it happens, allowing for immediate feedback and adjustments. (This may not be directly applicable in this project, but it's a related term).

Cultural Preferences: Dietary habits and restrictions influenced by a person's cultural background.

Food Composition: The breakdown of nutrients (carbohydrates, proteins, fats) present in a particular food item.

Accuracy: The degree to which the system's recommendations correspond to patients' actual needs and blood sugar management goals.

User Adherence: The extent to which diabetic patients consistently follow the dietary recommendations provided by the system.