International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 08 | Aug 2024
p-ISSN: 2395-0072
www.irjet.net
Diabetes Detection System based on Feature Engineering using Machine Learning Swapnshri Patel 1, Prof. Anjali Singh2, 1Reseacrh Scholar, Department of CSE, Aditya College of Technology and Sciences, Satna, M.P. 2Professor, Departmet of CSE, Aditya College of Technology and Sciences, Satna, M.P.
---------------------------------------------------------------------***-------------------------------------------------------------------type 2 diabetes, and gestational diabetes (gdm). Type 1 Abstract – Diabetes remains an important health challenge
diabetes is more common in children; while type 2 diabetes is more common in adults and the elderly, gdm is more common in women and is diagnosed during pregnancy. While insulin secretion does not work in type 1 diabetes due to the destruction of pancreatic beta cells, there is a disorder in insulin secretion and function in type 2 diabetes. Gdm is a glucose intolerance first diagnosed during pregnancy; it may be mild, but it is also associated with high blood sugar and high insulin levels during pregnancy. All of these types can cause a lack of blood sugar in the body, which can lead to serious diseases in the body. In other words, when blood sugar rises above normal, this condition is called hyperglycemia. On the other hand, when it decreases and falls below normal, the condition is called hypoglycemia [1][5]. Both conditions can have a negative impact on a person's health. For example, high blood sugar can cause chronic problems and lead to kidney disease, retinopathy, diabetes, heart attack and other tissue damage, while hypoglycemia can also be affected. Short term. It can cause kidney disease, retinopathy, heart disease, and heart attack, and other damage can lead to diabetic coma [1], [2]. Diabetes has become an important health problem in today's world due to its prevalence in children and adults. According to [6], [7] , approximately 8.8% of adults worldwide had diabetes in 2015, and this number was approximately 415 million and is expected to reach approximately 642 million in 2040. More than 500,000 children were killed during this period. And nearly 5 million people died. On the other hand, the global economic burden of diabetes was estimated to be approximately 673 billion dollars in 2015, and is expected to reach 802 billion dollars in 2040. Self-monitoring of blood glucose (smbg) using fingertip blood glucose meters is a diabetes treatment method introduced three years ago [8], [9]. In this way, diabetics measure their blood sugar levels using a finger glucometer on the skin of their fingers three to four times a day. The idea is to provide this: to increase insulin resistance. However, this method is laborious and laborious, and can only be understood if insulin estimation is obtained from small smbg samples. In other words, this may cause the blood sugar in the blood to be higher than normal. To overcome this problem, continuous blood glucose monitoring (cgm) has been introduced, which can provide maximum information about changes in blood sugar within a few days, allowing a good treatment decision to be made for people with diabetes. In this way, blood sugar concentration
with its widespread presence steadily increasing around the world. It can lead to other serious issues such as cardiovascular diseases, renal failure, and neuropathy and contribute to rising mortality rates in diabetic patients. Considering the situation, accurately predicting mortality risks in diabetic patients is crucial for several reasons like identifying high-risk individuals, forming proper diabetic treatment options and mitigating mortality among older patients. Studies conducted by WHO and CDC indicate that risk of mortality is very high in diabetic patients and it’s hard to predict the insulin amount required for each patient and it gets progressively harder when the patient has additional complications and comorbidities like HIV/Depression/Alcohol Abuse etc. Many influencing factors that could affect the diabetic complications need to be considered and hence there is a need to develop an all-cause mortality prediction model that could be utilized by healthpractitioners for devising better diabetic treatment plans, identifying sensitive individuals and controlling the mortality rate. Our work mainly focuses on Type 2 Diabetes Mellitus which generally occurs when insulin is not effectively used by the body due to excess body weight and physical inactivity. The study tracks the mortality status of patients at both the 5year and 10-year intervals. The work however will not cover the patients with Type 1 Diabetes or gestational diabetes and usage of external datasets for the validation of model is also not within the scope of the work. Keywords: Diabetes Mellitus, Mortality, features, Machine learning, XGBoost, AUC, Accuracy.
1. INTRODUCTION Diabetes is a non-communicable disease that affects the control of blood sugar levels in the body. Blood glucose concentration is normally controlled by insulin and glucagon, two hormones secreted by the beta (β) and alpha (α) cells of the pancreas, respectively. The normal release of the two hormones regulates blood sugar in the body within the range of 70 - 180 mg/dl (4.0 - 7.8 mmol/l). Insulin lowers blood sugar, while glucagon increases blood sugar. However, abnormality of these hormones can lead to diabetes. However, there are many types of diabetes, including different types of diabetes such as type 1 diabetes,
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 629