Related Experiment Video
Updated: Jul 25, 2025
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
Diagnosis of COVID-19 from blood parameters using convolutional neural network
Gizemnur Erol Doğan1, Betül Uzbaş2
1Software Engineering Department, Konya Technical University, Konya, Turkey.
Insights
This study introduces a novel method for detecting COVID-19 using blood parameters transformed into images and analyzed with convolutional neural networks (CNNs). This approach achieved a high 94.85% success rate for accurate COVID-19 detection.
Area of Science:
- Medical Diagnostics
- Artificial Intelligence in Medicine
- Bioinformatics
Background:
- Asymptomatic COVID-19 cases and viral genomic variants complicate disease detection and control.
- Rapid and accessible diagnostic methods are crucial for managing the COVID-19 pandemic.
- Blood parameters offer valuable, easily obtainable clinical information for infectious disease assessment.
Purpose of the Study:
- To develop an effective and accessible model for COVID-19 detection using readily available blood parameters.
- To explore the application of convolutional neural networks (CNNs) for analyzing blood data converted into image format for disease detection.
- To investigate a novel approach for COVID-19 diagnosis by transforming one-dimensional blood data into two-dimensional images.
Main Methods:
- One-dimensional (1D) blood parameters were preprocessed and converted into two-dimensional (2D) image data.
- t-distributed stochastic neighbor embedding (t-SNE) was used for feature vector projection onto a 2D plane.
- Convex hull and minimum bounding rectangle algorithms framed the data into images, which were then processed by a 3-line CNN architecture.
Main Results:
- The developed CNN model successfully detected COVID-19 using 2D image data derived from 1D blood parameters.
- The model achieved a high detection success rate of 94.85%.
- This method offers a promising alternative to traditional imaging techniques like chest X-rays or CT scans for COVID-19 detection.
Conclusions:
- The study presents an effective and successful model for COVID-19 detection by integrating low-cost blood parameters with CNN-based image processing.
- This novel approach provides a new perspective on COVID-19 diagnostics by leveraging blood data in an image-based format.
- The findings highlight the potential of using accessible blood parameters and advanced AI techniques for efficient and accurate infectious disease detection.
Abstract:
Asymptomatically presenting COVID-19 complicates the detection of infected individuals. Additionally, the virus changes too many genomic variants, which increases the virus's ability to spread. Because there isn't a specific treatment for COVID-19 in a short time, the essential goal is to reduce the virulence of the disease. Blood parameters, which contain essential clinical information about infectious diseases and are easy to access, have an important place in COVID-19 detection. The convolutional neural network (CNN) architecture, which is popular in image processing, produces highly successful results for COVID-19 detection models. When the literature is examined, it is seen that COVID-19 studies with CNN are generally done using lung images. In this study, one-dimensional (1D) blood parameters data were converted into two-dimensional (2D) image data after preprocessing, and COVID-19 detection was made with CNN. The t-distributed stochastic neighbor embedding method was applied to transfer the feature vectors to the 2D plane. All data were framed with convex hull and minimum bounding rectangle algorithms to obtain image data. The image data obtained by pixel mapping was presented to the developed 3-line CNN architecture. This study proposes an effective and successful model by providing a combination of low-cost and rapidly-accessible blood parameters and CNN architecture making image data processing highly successful for COVID-19 detection. Ultimately, COVID-19 detection was made with a success rate of 94.85%. This study has brought a new perspective to COVID-19 detection studies by obtaining 2D image data from 1D COVID-19 blood parameters and using CNN.
