Symptom-based Machine Learning Models for the Early Detection of COVID-19: A Narrative Review

TL;DR

This narrative review examines symptom-based machine learning models for early COVID-19 detection, highlighting their performance, limitations, and comparison with image-based models, with ensemble classifiers showing high accuracy.

Contribution

It provides a comprehensive overview of symptom-only machine learning models for COVID-19 prediction, including performance metrics and comparison with image-based approaches.

Findings

Ensemble classifiers achieved up to 97.88% accuracy.

Gradient Boosting identified key predictive features.

Image-based models often outperform symptom-based models.

Abstract

Despite the widespread testing protocols for COVID-19, there are still significant challenges in early detection of the disease, which is crucial for preventing its spread and optimizing patient outcomes. Owing to the limited testing capacity in resource-strapped settings and the limitations of the available traditional methods of testing, it has been established that a fast and efficient strategy is important to fully stop the virus. Machine learning models can analyze large datasets, incorporating patient-reported symptoms, clinical data, and medical imaging. Symptom-based detection methods have been developed to predict COVID-19, and they have shown promising results. In this paper, we provide an overview of the landscape of symptoms-only machine learning models for predicting COVID-19, including their performance and limitations. The review will also examine the performance of symptom-based models when compared to image-based models. Because different studies used varying datasets, methodologies, and performance metrics. Selecting the model that performs best relies on the context and objectives of the research. However, based on the results, we observed that ensemble classifier performed exceptionally well in predicting the occurrence of COVID-19 based on patient symptoms with the highest overall accuracy of 97.88%. Gradient Boosting Algorithm achieved an AUC (Area Under the Curve) of 0.90 and identified key features contributing to the decision-making process. Image-based models, as observed in the analyzed studies, have consistently demonstrated higher accuracy than symptom-based models, often reaching impressive levels ranging from 96.09% to as high as 99%.