Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Performance Evaluation of Classifiers for Predicting Dengue Virus Infection Cases Based on Clinical Diagnosis Criteria

Rektorat UDINUS 2020 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2020
Goals
Record
929bada2-ea8b-4094-90dd-264f777ee3e5
Published
2026-10-30

Universitas Dian Nuswantoro conducted an evaluation of classification algorithms for predicting dengue virus infection cases based on clinical diagnosis criteria. The activity involved Fahmi, Amiq; Purwitasari, Diana; Sumpeno, Surya; and Purnomo, Mauridhi Hery as participants in the UDINUS research activity. The study addressed dengue fever as a severe health threat that can lead to death and considered the role of data mining and classification methods in the medical and health field.

The activity focused on three clinical diagnosis classes: dengue fever (DF), dengue hemorrhagic fever (DHF), and dengue shock syndrome (DSS). These classifications were considered in relation to clinical signs and symptoms and laboratory examinations. The primary objective was to test and evaluate eight classification algorithms in order to identify the best algorithm in terms of efficiency and effectiveness. The algorithms compared were Neural Networks, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Random Forest, Naive Bayes, AdaBoost, and Logistic Regression.

The dataset, called DBDDKK, was collected from the Division of Disease Prevention and Control in the Semarang City Health Office, Central Java, Indonesia. During preprocessing, missing values were imputed, relevant features were selected, and features were normalized. This process resulted in 14,019 records with 16 attributes for each record. The dataset was divided into 70% training data and 30% testing data. Ten-fold cross-validation was applied to validate accuracy during the training process. Algorithm performance was assessed using accuracy, precision, and recall for prediction across the three dengue diagnosis classes. The comparison found that the Neural Networks algorithm achieved the best accuracy among the evaluated algorithms. This UDINUS activity addresses a health-related research objective through classification of dengue virus infection cases.

Reference https://www.scopus.com/pages/publications/85096757342?origin=resultslist