Articles

Hyperparameter Tuning of Random Forest Algorithm for Diabetes Classification

/0 Comments/in /by

This study aims to optimize the hyperparameters of the Random Forest model in diabetes classification using the Pima Indian Diabetes dataset, given the importance of early diabetes diagnosis to mitigate serious health impacts. While Random Forest is a popular algorithm for classification due to its resistance to overfitting, the selection of the right hyperparameters significantly affects its performance. Therefore, this research utilizes Grid Search and Random Search techniques for hyperparameter tuning to improve model accuracy. The research methodology includes data collection, preprocessing, dataset splitting (80% for training and 20% for testing), feature scaling using Standard Scaler, and the application of the Random Forest algorithm with hyperparameter tuning and model evaluation based on accuracy, precision, recall, and F1-Score. The results show that Random Forest, when tuned with Grid Search and Random Search, significantly improved model performance, with Random Search yielding the best results, achieving an accuracy of 0.75, precision of 0.64, and recall of 0.69. This study demonstrates that hyperparameter tuning can significantly enhance the performance of the Random Forest model, contributing to the development of machine learning applications for medical diabetes diagnosis.

Knowledge, Attitudes, and Beliefs of Paulinian College Students about Diabetes

/in /by

The main purpose of the study was to evaluate the degree of knowledge, attitudes, and beliefs of Paulinian college students on diabetes for appropriate plans and interventions. The participants were 218 Paulinian college students at St. Paul University Surigao during the academic year 2022-2023. The study employed a quantitative descriptive research design involving the use of a researcher-made survey questionnaire that underwent validation and pilot testing. The data gathered were analyzed and treated by using the following descriptive statistical tools: frequency count and percentage distribution, mean and standard deviation, analysis of variance (ANOVA), and Shapiro-Wilk test. Results showed that the college students had a significant degree of difference in the level of respondent’s attitudes and beliefs on Diabetes based on behavior formation and belief generation when grouped according to age, sex, and socio-economic status. Students had significant differences in their attitudes and beliefs when grouped as to their knowledge as there was found to be a correlation between attitudes and beliefs. Generally, the findings showed that there is a significant degree of difference in the level of respondent’s knowledge, attitudes, and beliefs. It was recommended to provide an action plan as a health education strategy according to their knowledge about Diabetes for a continuum favorable attitude of students and change their beliefs on a more scientific approach and analyze deeply the misconceptions regarding the disease.

Diabetes Mellitus: A Leading Cause of Death Worldwide

/in /by

Diabetes mellitus, or commonly known as diabetes, is a metabolic disorder characterized by chronic hyperglycemia which results in insulin resistance, impaired insulin synthesis, or sometimes both. Diabetes affects roughly 400 million people worldwide and the majority being those who are from middle to low income countries. With 1.5 million diabetes related deaths worldwide each year, this literature review aims to give information about the 2 types of diabetes and also highlighting the appropriate preventative measures. Type 1 diabetes refers to the lack of insulin production and type 2 diabetes refers to lower production of insulin and increased insulin resistance; both will result in hyperglycemia in diabetic patients. Furthermore, this literature review also aims to explore and describe the pathogenesis and treatments of the 2 types of diabetes.

Activities of Pancreatic Enzymes and Anthropometric Indices in Type 2 Diabetic Patients Attending Nnamdi Azikiwe University Teaching Hospital Nnewi, South Eastern, Nigeria

/in /by

Type 2 diabetes mellitus is the most common type of diabetes, having high blood glucose, reduced insulin secretion and / or inadequate glucagon secretion. The study is to assess the activities of pancreatic enzymes and anthropometric indices. 81 participants comprised 38 diabetic and 43 control were randomly recruited. Informed, oral and written consent was obtained from the participants. Ethical approval was obtained.6mls of fasting blood samples were collected. Plasma glucose; amylase and lipase activities were analyzed using standard laboratory methods. Body mass index (BMI) of participant was determined from height and weight. The results showed significantly increased plasma glucose level in the diabetic participants than in control at p=0.000 and in male diabetics than in female diabetics at p=0.048 in each case. But the activities of lipase, amylase, the mean age and BMI level were the same in both diabetic and control groups at p>0.05 respectively. BMI level, lipase and amylase activities were the same in both genders (p>0.05). Stronger positive correlation exist between Weight Vs BMI (r=0.834; p=0.000), followed by Lipase Vs Amylase (r=0.767; p=0.000), least between Age Vs BMI (r=0.353; p=0.022) but weaker negative associations exist between Height Vs BMI (r=-0.490; p=0.001) and Weight Vs FBS (r=-0.325; p=0.036) in the diabetic subjects. The significant higher level of blood glucose; stronger positive correlation between Lipase and Amylase; Weight and BMI may likely revealed pancreatic exocrine function abnormality in diabetes mellitus type 2.