Related Experiment Video
Updated: Nov 11, 2025
11:37
Zika Virus Specific Diagnostic Epitope Discovery
Published on: December 12, 2017
8.0K
Classification algorithm for congenital Zika Syndrome: characterizations, diagnosis and validation.
Rafael V Veiga1,2, Lavinia Schuler-Faccini3, Giovanny V A França4
1Center of Data and Knowledge Integration for Health (CIDACS), Instituto Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, Bahia, Brazil. rafaelvalenteveiga@gmail.com.
Scientific Reports
|March 25, 2021
Summary
A machine learning algorithm can now classify Congenital Zika Syndrome (CZS) probability using clinical data. This aids in understanding the Zika epidemic
Area of Science:
- Virology
- Epidemiology
- Machine Learning
Background:
- The 2015 Zika virus epidemic in Brazil highlighted challenges in diagnosing Congenital Zika Syndrome (CZS).
- Accurate classification of CZS cases is crucial for public health and scientific understanding.
Purpose of the Study:
- To develop an automated machine learning algorithm for classifying CZS probability from clinical data.
- To improve diagnostic accuracy and support health surveillance efforts.
Main Methods:
- Utilized a machine learning algorithm to analyze structured and unstructured clinical data.
- Evaluated algorithm performance on datasets with and without textual information.
Main Results:
- The algorithm achieved 83% accuracy using textual data from medical records and image reports.
- The algorithm achieved 76% accuracy using only non-textual clinical data.
Conclusions:
- The developed machine learning algorithm shows significant potential for classifying CZS cases.
- This tool can help clarify the epidemic's impact and enhance future epidemic monitoring.
