Analysis of machine learning methods for COVID-19 detection using serum raman spectroscopy

Tracking #: 691-1671


Responsible editor: 

Manik Sharma

Submission Type: 

Research Paper


One of the most challenging aspects of the emergent COVID-19 pandemic caused by infection of SARS-CoV-2 has been the need for massive diagnostic tests to detect and track infection rates at the population level. Current tests such as RT-PCR can be low-throughput and labor intensive. An ultra-fast and accurate mode of detecting COVID-19 infection is crucial for healthcare workers to make informed decisions in fast-paced clinical settings. The high-dimensional, feature-rich components of raman spectra and validated predictive power for identifying human disease, cancer, as well as bacterial and viral infections poses the potential to train a supervised classification machine-learning algorithm on raman spectra of patient serum samples to detect COVID-19 infection. We developed a novel stacked subsemble classifier model coupled with an iteratively validated and automated feature selection and engineering workflow to predict COVID-19 infection status from raman spectra of 250 human serum samples, with a 10-fold cross validated classification accuracy of 98.4% (98.6% precision and 95.9% sensitivity). Furthermore, we benchmarked 9 machine learning and artificial neural network models when evaluated using 8 standalone performance metrics to assess whether ensemble methods offered any improvement from baseline machine learning models. Using a rank normalized scores derived from the performance metrics, the stacked subsemble model ranked higher than the Multi-layer Perceptron, which in turn ranked higher than the 8 other machine learning models. This study serves as a proof of concept that stacked ensemble machine learning models are a powerful predictive tool for COVID-19 diagnostics.



  • Reviewed

Data repository URLs: 

Date of Submission: 

Tuesday, March 30, 2021

Date of Decision: 

Saturday, May 22, 2021



Solicited Reviews:

1 Comment

Meta-Review by Editor

The idea mentioned in the manuscript is interesting. However, the manuscript needs revision. More background work need to be presented. There should be a separate related work section. More quality based literature related to the theme of the manuscript need to be explored and incorporated. The novelty and contribution of this work need to be clearly stated in the introduction section. It needs to be explicitly mentioned in the discussion section how the results have been validated. The author should revise the manuscript following these editor comments and the comments by the reviewers.

Manik Sharma (