Early diagnosis of dengue continues to be a concern for public health in countries with a high incidence of this disease. In this work, we compared two machine learning techniques: artificial neural networks (ANN) and support vector machines (SVM) as assistance tools for medical diagnosis. The performance of classification models was evaluated in a real dataset of patients with a previous diagnosis of dengue extracted from the public health system of Paraguay during the period 2012-2016. The ANN multilayer perceptron achieved better results with an average of 96% accuracy, 96% sensitivity, and 97% specificity, with low variation in thirty different partitions of the dataset. In comparison, SVM polynomial obtained results above 90% for accuracy, sensitivity, and specificity.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6702853PMC
http://dx.doi.org/10.1155/2019/7307803DOI Listing

Publication Analysis

Top Keywords

diagnosis dengue
12
medical diagnosis
8
public health
8
predictive models
4
models medical
4
diagnosis
4
dengue case
4
case study
4
study paraguay
4
paraguay early
4

Similar Publications

The ongoing emergence of SARS-CoV-2 variants, combined with antigen exposures from different waves and vaccinations, poses challenges in updating COVID-19 vaccine antigens. We collected 206 sera from individuals with vaccination-only, hybrid immunity, and single or repeated omicron post-vaccination infections (PVIs), including non-JN.1 and JN.

View Article and Find Full Text PDF

Equipmentless point-of-care testing of dengue antibodies using ELISA and smartphones.

J Pharm Biomed Anal

January 2025

INTEC (Universidad Nacional del Litoral-CONICET), Predio CCT CONICET-Santa Fe, RN 168, Santa Fe S3000GLN, Argentina. Electronic address:

Infections with the dengue virus affect more than 100 million people every year. The infected can present a mild form of the disease or a severe form, which can, eventually, lead to death. Dengue prevails in tropical and subtropical regions, although increased incidence has been observed in the last years in tempered climates.

View Article and Find Full Text PDF

Purpose Of Review: Arboviral infections caused by Dengue, Zika, and Chikungunya viruses continue to pose a significant global health threat, particularly in endemic regions. This review is timely because of the increasing prevalence of these infections, driven by factors such as urbanization and climate change. Dermatological manifestations of these viruses are crucial for early diagnosis, especially given the overlap in symptoms, which can complicate differential diagnosis.

View Article and Find Full Text PDF

A low pre-existing anti-NS1 humoral immunity to DENV is associated with microcephaly development after gestational ZIKV exposure.

PLoS Negl Trop Dis

January 2025

División de Inmunología, Programa de Medicina, Facultad de Ciencias de la Salud, Universidad Surcolombiana, Neiva, Huila, Colombia.

Background: Gestational Zika virus (ZIKV) infection is associated with the development of congenital Zika syndrome (CZS), which includes microcephaly and fetal demise. The magnitude and quality of orthoflavivirus-specific humoral immunity have been previously linked to the development of CZS. However, the role of ZIKV NS1-specific humoral immunity in mothers and children with prenatal ZIKV exposure and CZS remains undefined.

View Article and Find Full Text PDF
Article Synopsis
  • Immune thrombocytopenic purpura (ITP) is an autoimmune disorder that leads to low platelet counts, mostly seen in children after viral infections, while adults may develop chronic ITP.
  • In adults, though rare, ITP can occur following viral infections like dengue fever, with symptoms typically showing up towards the end of the first week of illness.
  • A case study of a woman in her forties experiencing ITP as a primary symptom of dengue fever illustrates the necessity for early diagnosis and proper treatment, underscoring ITP as a potential complication of viral infections.
View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!