A Machine Learning-Based Solution for Diabetes Diagnosis: Integrating Clinical Data and Vital Signs
DS Journal of Digital Science and Technology · 30.09.2025 · 4 (3) · 1-15
DOI: 10.59232/dst-v4i3p101 ↗Kurz gefasst
Fachartikel in der Zeitschrift DS Journal of Digital Science and Technology, online erschienen am 30.09.2025. Verfasst von Huy Huynh und 2 weiteren Autor:innen.
Themen: Künstliche Intelligenz in der Pflege, Diabetes mellitus
Abstract (Originalsprache)
The diagnosis of diabetes mellitus utilizing clinical data and vital signs is essential for the early identification and efficient management of the condition, particularly as its global prevalence rises. This study examines general diagnostic methodologies utilizing diverse indicators, with a particular emphasis on diabetes diagnostics, subsequently identifying pertinent features to develop an effective, cohesive diagnostic solution. The suggested solution uses both structured and unstructured features. Structured features include vital signs, demographics, and lab tests, while unstructured features include chief complaints and medical notes. This solution is based on the MIMIC-IV dataset, which is a rich and varied source of medical data. The research suggests creating a prototype diagnostic system that uses modern machine learning models like Logistic Regression, Support Vector Machine (SVM), Gradient Boosting, Random Forest, and XGBoost. This system is built to automatically process and combine information from different types of data, such as medical text and biological indicators, to improve the prediction process and help doctors make decisions. This solution not only offers a thorough and efficient method for diagnosing diabetes, but it also shows how it could be used in real-world healthcare systems. The prototype system can be used to help doctors make quick and correct clinical decisions. It can also be used as a starting point for future research and applications in smart healthcare.
Zitieren
APA
Huynh, H., Cao, T., & Tran, H. (2025). A Machine Learning-Based Solution for Diabetes Diagnosis: Integrating Clinical Data and Vital Signs. DS Journal of Digital Science and Technology, 4(3), 1-15. https://doi.org/10.59232/dst-v4i3p101
Vancouver
Huynh H, Cao T, Tran H. A Machine Learning-Based Solution for Diabetes Diagnosis: Integrating Clinical Data and Vital Signs. DS Journal of Digital Science and Technology. 2025;4(3):1-15. doi:10.59232/dst-v4i3p101
BibTeX
@article{Huynh2025,
author = {Huynh, Huy and Cao, Thanh and Tran, Hai},
title = {A Machine Learning-Based Solution for Diabetes Diagnosis: Integrating Clinical Data and Vital Signs},
journal = {DS Journal of Digital Science and Technology},
year = {2025},
volume = {4},
number = {3},
pages = {1--15},
doi = {10.59232/dst-v4i3p101}
}
EUVIMED