Machine Learning and Data Mining Methods in Diabetes Research

Machine Learning and Data Mining Methods in Diabetes Research

2017 | Ioannis Kavakiots, Olga Tsave, Athanasios Salifoglou, Nicos Maglaveras, Ioannis Vlahavas, Ioanna Chouvarda
This article reviews the application of machine learning and data mining techniques in diabetes research, focusing on prediction and diagnosis, diabetic complications, genetic background and environment, and healthcare management. The study aims to extract valuable knowledge from large datasets generated by high-throughput sequencing and clinical information. Machine learning algorithms, particularly supervised learning approaches, are widely used, with support vector machines (SVM) being the most successful. Clinical datasets are primarily utilized. The review highlights the importance of these methods in transforming available data into actionable knowledge, aiding in disease diagnosis, management, and treatment. Key applications include biomarker identification, prediction of diabetic complications, drug and therapy selection, genetic risk factor identification, and healthcare cost prediction. The study emphasizes the need for further research to improve the accuracy and effectiveness of these methods in diabetes management.This article reviews the application of machine learning and data mining techniques in diabetes research, focusing on prediction and diagnosis, diabetic complications, genetic background and environment, and healthcare management. The study aims to extract valuable knowledge from large datasets generated by high-throughput sequencing and clinical information. Machine learning algorithms, particularly supervised learning approaches, are widely used, with support vector machines (SVM) being the most successful. Clinical datasets are primarily utilized. The review highlights the importance of these methods in transforming available data into actionable knowledge, aiding in disease diagnosis, management, and treatment. Key applications include biomarker identification, prediction of diabetic complications, drug and therapy selection, genetic risk factor identification, and healthcare cost prediction. The study emphasizes the need for further research to improve the accuracy and effectiveness of these methods in diabetes management.
Reach us at info@study.space
[slides] Machine Learning and Data Mining Methods in Diabetes Research | StudySpace