Application of MALDI-MS and Machine Learning to Detection of SARS-CoV-2 and non-SARS-CoV-2 Respiratory Infections.

Publication date: Sep 01, 2023

Background: Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) could aid the diagnosis of acute respiratory infections (ARI) owing to its affordability and high-throughput capacity. MALDI-MS has been proposed for use on commonly available respiratory samples, without specialized sample preparation, making this technology especially attractive for implementation in low-resource regions. Here, we assessed the utility of MALDI-MS in differentiating SARS-CoV-2 versus non-COVID acute respiratory infections (NCARI) in a clinical lab setting of Kazakhstan. Methods: Nasopharyngeal swabs were collected from in- and outpatients with respiratory symptoms and from asymptomatic controls (AC) in 2020-2022. PCR was used to differentiate SARS-CoV-2+ and NCARI cases. MALDI-MS spectra were obtained for a total of 252 samples (115 SARS-CoV-2+, 98 NCARI and 39 AC) without specialized sample preparation. In our first sub-analysis, we followed a published protocol for peak preprocessing and Machine Learning (ML), trained on publicly available spectra from South American SARS-CoV-2+ and NCARI samples. In our second sub-analysis, we trained ML models on a peak intensity matrix representative of both South American (SA) and Kazakhstan (Kaz) samples. Results: Applying the established MALDI-MS pipeline “as is” resulted in a high detection rate for SARS-CoV-2+ samples (91.0%), but low accuracy for NCARI (48.0%) and AC (67.0%) by the top-performing random forest model. After re-training of the ML algorithms on the SA-Kaz peak intensity matrix, the accuracy of detection by the top-performing Support Vector Machine with radial basis function kernel model was at 88.0, 95.0 and 78% for the Kazakhstan SARS-CoV-2+, NCARI, and AC subjects, respectively with a SARS-CoV-2 vs. rest ROC AUC of 0.983 [0.958, 0.987]; a high differentiation accuracy was maintained for the South American SARS-CoV-2 and NCARI. Conclusions: MALDI-MS/ML is a feasible approach for the differentiation of ARI without a specialized sample preparation. The implementation of MALDI-MS/ML in a real clinical lab setting will necessitate continuous optimization to keep up with the rapidly evolving landscape of ARI.

Concepts Keywords
Arithmetic Clinical
Forest Cov
Germany Karaganda
Immunochromatography Kazakhstan


Type Source Name
disease MESH Respiratory Infections
disease VO protocol
drug DRUGBANK Saquinavir
disease VO Canada
disease MESH infection
disease MESH COVID 19
disease MESH sore throat
disease MESH lymphadenopathy
disease VO Viruses
disease VO Optaflu
disease MESH parainfluenza
disease VO Respiratory syncytial virus
disease MESH influenza
disease VO Metapneumovirus
disease VO Bacteria
disease IDO symptom
drug DRUGBANK Water
drug DRUGBANK Medical air
disease IDO algorithm
drug DRUGBANK Pidolic Acid
drug DRUGBANK Flunarizine
disease IDO process
drug DRUGBANK Pentaerythritol tetranitrate
disease VO age

(Visited 1 times, 1 visits today)