Using machine learning of clinical data to diagnose COVID-19: a systematic review and meta-analysis
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
Background
The recent Coronavirus Disease 2019 (COVID-19) pandemic has placed severe stress on healthcare systems worldwide, which is amplified by the critical shortage of COVID-19 tests.
Methods
In this study, we propose to generate a more accurate diagnosis model of COVID-19 based on patient symptoms and routine test results by applying machine learning to reanalyzing COVID-19 data from 151 published studies. We aim to investigate correlations between clinical variables, cluster COVID-19 patients into subtypes, and generate a computational classification model for discriminating between COVID-19 patients and influenza patients based on clinical variables alone.
Results
We discovered several novel associations between clinical variables, including correlations between being male and having higher levels of serum lymphocytes and neutrophils. We found that COVID-19 patients could be clustered into subtypes based on serum levels of immune cells, gender, and reported symptoms. Finally, we trained an XGBoost model to achieve a sensitivity of 92.5% and a specificity of 97.9% in discriminating COVID-19 patients from influenza patients.
Conclusions
We demonstrated that computational methods trained on large clinical datasets could yield ever more accurate COVID-19 diagnostic models to mitigate the impact of lack of testing. We also presented previously unknown COVID-19 clinical variable correlations and clinical subgroups.
Article activity feed
-
-
SciScore for 10.1101/2020.06.24.20138859: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources 4,1 Literature search and inclusion criteria for studies: Patient clinical data were manually curated from a PubMed search with the keyword “COVID-19.” A total of 1,439 publications, dating from January 17, 2020 to March 23, 2020, were reviewed. PubMedsuggested: (PubMed, RRID:SCR_004846)Results from OddPub: Thank you for sharing your data.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Despite promising results, several limitations exist for our study, all of which stem from the lack of large-scale clinical data. First, our …
SciScore for 10.1101/2020.06.24.20138859: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources 4,1 Literature search and inclusion criteria for studies: Patient clinical data were manually curated from a PubMed search with the keyword “COVID-19.” A total of 1,439 publications, dating from January 17, 2020 to March 23, 2020, were reviewed. PubMedsuggested: (PubMed, RRID:SCR_004846)Results from OddPub: Thank you for sharing your data.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Despite promising results, several limitations exist for our study, all of which stem from the lack of large-scale clinical data. First, our sample size is severely limited because most clinical reports published do not publish individual-level patient data. Second, data on influenza signs and symptoms are equally inaccessible. We were only able to locate data for patients with H1N1 influenza A, which is not one of the active strains in the current influenza season. Third, many of our data sources are case studies that focused on specific cohorts of COVID-19 patients. This increases the chance of us capturing a patient population that is not representative of the general population, although this is an inherent risk of sampling. We anticipate that as more data are made openly available in the weeks and months to come, we will be able to build a more robust computational model. Therefore, we intend to provide the model we constructed as a computational framework for computation-aided diagnosis of COVID-19 data rather than a ready-to-use model. We also encourage researchers around the world to release de-identified patient data to aid in data mining and machine learning efforts against COVID-19.
Results from TrialIdentifier: No clinical trial numbers were referenced.
Results from Barzooka: We did not find any issues relating to the usage of bar graphs.
Results from JetFighter: We did not find any issues relating to colormaps.
Results from rtransparent:- Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
- Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
- No protocol registration statement was detected.
-
