+1 Recommend
1 collections
      • Record: found
      • Abstract: found
      • Article: not found

      Diagnosis and prognosis of COVID-19 employing analysis of patients' plasma and serum via LC-MS and machine learning


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.



          To implement and evaluate machine learning (ML) algorithms for the prediction of COVID-19 diagnosis, severity, and fatality and to assess biomarkers potentially associated with these outcomes.

          Material and methods

          Serum (n = 96) and plasma (n = 96) samples from patients with COVID-19 (acute, severe and fatal illness) from two independent hospitals in China were analyzed by LC-MS. Samples from healthy volunteers and from patients with pneumonia caused by other viruses (i.e. negative RT-PCR for COVID-19) were used as controls. Seven different ML-based models were built: PLS-DA, ANNDA, XGBoostDA, SIMCA, SVM, LREG and KNN.


          The PLS-DA model presented the best performance for both datasets, with accuracy rates to predict the diagnosis, severity and fatality of COVID-19 of 93%, 94% and 97%, respectively. Low levels of the metabolites ribothymidine, 4-hydroxyphenylacetoylcarnitine and uridine were associated with COVID-19 positivity, whereas high levels of N-acetyl-glucosamine-1-phosphate, cysteinylglycine, methyl isobutyrate, l-ornithine and 5,6-dihydro-5-methyluracil were significantly related to greater severity and fatality from COVID-19.


          The PLS-DA model can help to predict SARS-CoV-2 diagnosis, severity and fatality in daily practice. Some biomarkers typically increased in COVID-19 patients’ serum or plasma (i.e. ribothymidine, N-acetyl-glucosamine-1-phosphate, l-ornithine, 5,6-dihydro-5-methyluracil) should be further evaluated as prognostic indicators of the disease.

          Related collections

          Most cited references90

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          MetaboAnalyst 5.0: narrowing the gap between raw spectra and functional insights

          Since its first release over a decade ago, the MetaboAnalyst web-based platform has become widely used for comprehensive metabolomics data analysis and interpretation. Here we introduce MetaboAnalyst version 5.0, aiming to narrow the gap from raw data to functional insights for global metabolomics based on high-resolution mass spectrometry (HRMS). Three modules have been developed to help achieve this goal, including: (i) a LC–MS Spectra Processing module which offers an easy-to-use pipeline that can perform automated parameter optimization and resumable analysis to significantly lower the barriers to LC-MS1 spectra processing; (ii) a Functional Analysis module which expands the previous MS Peaks to Pathways module to allow users to intuitively select any peak groups of interest and evaluate their enrichment of potential functions as defined by metabolic pathways and metabolite sets; (iii) a Functional Meta-Analysis module to combine multiple global metabolomics datasets obtained under complementary conditions or from similar studies to arrive at comprehensive functional insights. There are many other new functions including weighted joint-pathway analysis, data-driven network analysis, batch effect correction, merging technical replicates, improved compound name matching, etc. The web interface, graphics and underlying codebase have also been refactored to improve performance and user experience. At the end of an analysis session, users can now easily switch to other compatible modules for a more streamlined data analysis. MetaboAnalyst 5.0 is freely available at https://www.metaboanalyst.ca . Graphical Abstract From raw data to statistical and functional insights using MetaboAnalyst 5.0.
            • Record: found
            • Abstract: not found
            • Article: not found

            Machine learning for molecular and materials science

              • Record: found
              • Abstract: found
              • Article: not found

              Bacterial co-infection and secondary infection in patients with COVID-19: a living rapid review and meta-analysis

              Background Bacterial co-pathogens are commonly identified in viral respiratory infections and are important causes of morbidity and mortality. The prevalence of bacterial infection in patients infected with SARS-CoV-2 is not well understood. Aims To determine the prevalence of bacterial co-infection (at presentation) and secondary infection (after presentation) in patients with COVID-19. Sources We performed a systematic search of MEDLINE, OVID Epub and EMBASE databases for English language literature from 2019 to April 16, 2020. Studies were included if they (a) evaluated patients with confirmed COVID-19 and (b) reported the prevalence of acute bacterial infection. Content Data were extracted by a single reviewer and cross-checked by a second reviewer. The main outcome was the proportion of COVID-19 patients with an acute bacterial infection. Any bacteria detected from non-respiratory-tract or non-bloodstream sources were excluded. Of 1308 studies screened, 24 were eligible and included in the rapid review representing 3338 patients with COVID-19 evaluated for acute bacterial infection. In the meta-analysis, bacterial co-infection (estimated on presentation) was identified in 3.5% of patients (95%CI 0.4–6.7%) and secondary bacterial infection in 14.3% of patients (95%CI 9.6–18.9%). The overall proportion of COVID-19 patients with bacterial infection was 6.9% (95%CI 4.3–9.5%). Bacterial infection was more common in critically ill patients (8.1%, 95%CI 2.3–13.8%). The majority of patients with COVID-19 received antibiotics (71.9%, 95%CI 56.1 to 87.7%). Implications Bacterial co-infection is relatively infrequent in hospitalized patients with COVID-19. The majority of these patients may not require empirical antibacterial treatment.

                Author and article information

                Comput Biol Med
                Comput Biol Med
                Computers in Biology and Medicine
                Published by Elsevier Ltd.
                21 May 2022
                21 May 2022
                : 105659
                [a ]Pharmaceutical Sciences Postgraduate Program, Universidade Federal Do Paraná, Curitiba, Brazil
                [b ]Department of Forest Engineering and Technology, Universidade Federal Do Paraná, Curitiba, Brazil
                [c ]Department of Pharmacy, Universidade Federal Do Paraná, Curitiba, Brazil
                [d ]H&TRC- Health & Technology Research Center, ESTeSL, Escola Superior de Tecnologia da Saúde, Instituto Politécnico de Lisboa, Lisbon, Portugal
                Author notes
                []Corresponding author. Department of Pharmacy, Universidade Federal do Paraná, Campus III, Av. Pref. Lothário Meissner, 632, Jardim Botânico, Curitiba, PR, 80210, Brazil.
                S0010-4825(22)00451-6 105659
                © 2022 Published by Elsevier Ltd.

                Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.

                : 20 February 2022
                : 11 May 2022
                : 18 May 2022

                covid 19,fatality,severity,diagnosis,biomarker,machine learning
                covid 19, fatality, severity, diagnosis, biomarker, machine learning


                Comment on this article