Search published articles


Showing 2 results for Prediction

Parisa Karimi Darabi, Mohammad Jafar Tarokh,
Volume 8, Issue 3 (10-2020)
Abstract

Background and Objectives: Currently, diabetes is one of the leading causes of death in the world. According to several factors diagnosis of this disease is complex and prone to human error. This study aimed to analyze the risk of having diabetes based on laboratory information, life style and, family history with the help of machine learning algorithms. When the model is trained properly, people can examine their risk of having diabetes.
Material and Methods: To classify patients, by using Python, eight different machine learning algorithms (Logistic Regression, Nearest Neighbor, Decision Tree, Random Forest, Support Vector Machine, Naive Bayesian, Neural Network and Gradient Boosting) were analysed. were evaluated by accuracy, sensitivity, specificity and ROC curve parameters.
ResultsThe model based on the gradient boosting algorithm showed the best performance with a prediction accuracy of %95.50.
ConclusionIn the future, this model can be used for diagnosis diabete. The basis of this study is to do more research and develop models such as other learning machine algorithms.

Hediye Shariaty , Fatemeh Bagheri ,
Volume 12, Issue 4 (4-2024)
Abstract

Background: Diabetes is a prevalent condition with no definitive cure, often referred to as a” silent killer.” Diabetes is primarily categorized into three types: Type I, Type II, and gestational diabetes. In Type I diabetes, the body's immune system attacks and damages the insulin-producing cells. Conversely, Type II diabetes, which is more common than Type I, occurs when the body does not respond adequately to the insulin being produced, resulting in elevated blood sugar levels. Effectively treating pre-diabetes can prevent its progression to full-blown diabetes.
Methods: In the present research, a semi-supervised approach is proposed to predict diabetes. Improved missing value imputation (MVI) is achieved by utilizing Gaussian mixture model (GMM) clustering. The proposed classifier integrates GMM with a machine learning algorithm, specifically random forest (RF), thereby inducing a more robust predictive model via the fusion of clustering and classification techniques.
Results: The proposed method achieves an accuracy of 84%, a precision of 82.03%, a recall of 69.75%, and an F1-score of 75.12% base on experiments conducted on the PIMA Indian population.
Conclusion: Employing GMM to fill in missing values provides the advantage of replacing invalid data with the most similar records, thereby enhancing the quality of the dataset. The proposed classifier also exhibits strong predictive capabilities in identifying diabetes. By integrating this combined approach, this study offers an effective method for predicting diabetes, making a significant contribution to healthcare analytics as a whole.


Page 1 from 1     

© 2025 CC BY-NC 4.0 | Jorjani Biomedicine Journal

Designed & Developed by : Yektaweb