SG-APSIC1053: Detection of SARS-COV-2 in nasopharyngeal swags with MALDI-TOF MS and machine learning
Bibliographic record
Abstract
Objectives: The widespread distribution of SARS-CoV-2 and its high contagiousness pose a challenge for researchers seeking to develop a rapid and cost-effective screening method to identify carriers of this virus. RT-PCR is considered the gold standard for detecting viral RNA in nasopharyngeal swabs, but it is time-consuming and requires constant changes in the primer composition due to the mutation of SARS-CoV-2 strains. We propose a method for the detection of SARS-CoV-2 in nasopharyngeal swabs using MALDI-TOF MS and machine learning. Methods: Nasopharyngeal swabs from patients with PCR-confirmed COVID-19 and control participants were tested (130 and 80 swabs, respectively) with MALDI-TOF MS MicroFlex LT using the HCCA matrix. MALDI spectra were preprocessed in R version 4.1.2 software with the MALDIquant R package using the workflow: sqrt transformation, wavelet smoothing, SNIP-based base removal, and PQN intensity calibration. Peaks were detected with MAD algorithms with following Peak alignment on the following parameters: minFreq 70% and tolerance 0.005. Machine learning was performed with the rtemis r package on GLM, random forest, and XGBoost models. Results: These models were characterized by specificity, sensitivity, and F1 score. GLM models (specificity 1 and sensitivity 0.5) showed a low F1 score of 0.71. However, the random forest and XGBoost models demonstrated sensitivity, specificity, and F1 score equaling 1. Conclusions: We propose a screening method for SARS-CoV-2 detection (sensitivity 1 and specificity 1). This methodology combines the analysis of nasopharyngeal swab samples using MALDI-TOF-MS with machine learning. It is suitable for screening patients with COVID-19 at the first stages of diagnosis. Random forest and XGBoost models demonstrated sensitivity, specificity, and F1 scores equaling 1.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".