EUVIMEDEUVIMED entdecken
CrossrefInfokarte

Advancing Early Dengue Detection through Machine Learning Techniques on Clinical Data

Wankhede Vishal Ashok, Mahadeo Digamber Kokate, Lohar Dinesh Vanji, Bachhav Swati Mothabhau

Frontiers in Health Informatics · 2024-12-16 · 536-554

DOI: 10.63682/fhi1325 ↗
AbstractBibliografische Angaben

Abstract

Dengue fever is a serious health problem worldwide, with India being one of the most affected countries. The process of diagnosing dengue is quite lengthy and requires several clinical tests, making it difficult to identify the disease quickly. However, early and accurate diagnosis is essential to reduce the mortality rate associated with dengue. Given this challenge, there is a need for an improved prediction model that can help detect dengue at an early stage. This study aims to develop a new prediction model for the early detection of dengue using advanced machine learning techniques, known as Effective Machine Learning Techniques (EMLT). The research focuses on creating dengue prediction models based on five powerful machine learning algorithms: K-Nearest Neighbor (KNN), Gradient Boosting Classifier (GBC), Extra Trees Classifier (ETC), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (Light GBM). Each of these machine learning algorithms was trained and tested on the dengue dataset using two validation methods: 10-Fold Cross-Validation and Hold-out Cross-Validation. During the evaluation, various performance metrics such as accuracy, F1-score, precision, recall, AUC (Area Under the Curve), and processing time were used to assess how well the models performed. The findings revealed that the Extra Trees Classifier (ETC) performed the best, achieving an accuracy of 99.12% in Hold-out Cross-Validation and 99.03% in 10-fold cross-validation. Based on these results, it can be concluded that the ETC is the most effective classifier when using the Hold-out Cross-Validation method. Furthermore, the study demonstrates that Hold-out Cross-Validation significantly enhances the performance of the classifier compared to the 10-fold cross-validation method. In conclusion, the proposed dengue prediction system shows great promise in assisting healthcare professionals by providing accurate and reliable predictions for dengue fever. This could lead to faster diagnosis and more effective treatment, ultimately helping to reduce the impact of dengue in regions where it is prevalent.

Wissen, das zu Ihrer Arbeit passt.

Vom kostenlosen Einstieg über die persönliche Recherche bis zur vollständigen Research Suite.

Tarife ansehen →

Sind alle Verlagsvolltexte enthalten?

Nein. Bibliografische Nachweise, Abstracts und Volltexte sind unterschiedliche Inhalte. Ob ein Volltext verfügbar ist, hängt von der Quelle, Open Access und Ihren vorhandenen Lizenzen ab. Ein EUVIMED-Tarif ersetzt keine zusätzlichen Verlagsrechte.

Tarife ansehen →