An automated machine learning model for diagnosing COVID-19 infection
IAES International Journal of Artificial Intelligence
; 12(3):1360-1369, 2023.
Article
in English
| Scopus | ID: covidwho-2299389
ABSTRACT
The coronavirus disease 2019 (COVID-19) epidemic still impacts every facet of life and necessitates a fast and accurate diagnosis. The need for an effective, rapid, and precise way to reduce radiologists' workload in diagnosing suspected cases has emerged. This study used the tree-based pipeline optimization tool (TPOT) and many machine learning (ML) algorithms. TPOT is an open-source genetic programming-based AutoML system that optimizes a set of feature preprocessors and ML models to maximize classification accuracy on a supervised classification problem. A series of trials and comparisons with the results of ML and earlier studies discovered that most of the AutoML beat traditional ML in terms of accuracy. A blood test dataset that has 111 variables and 5644 cases were used. In TPOT, 450 pipelines were used, and the best pipeline selected consisted of radial basis function (RBF) Sampler preprocessing and Gradient boosting classifier as the best algorithm with a 99% accuracy rate. © 2023, Institute of Advanced Engineering and Science. All rights reserved.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
IAES International Journal of Artificial Intelligence
Year:
2023
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS