Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score
- University of Brescia, Italy
Abstract
An early-warning model to predict in-hospital mortality on admission of COVID-19 patients at an emergency department (ED) was developed and validate using a Machine-Learning model. In total, 2782 patients were enrolled between March 2020 and December 2020, including 2106 patients (first wave) and 676 patients (second wave) in the COVID-19 outbreak in Italy. The first-wave patients were divided into two groups with 1474 patients used to train the model, and 632 to validate it. The 676 patients in the second wave were used to test the model. Age, 17 blood analytes and Brescia chest X-ray score were the variables processed using a Random Forests classification algorithm to build and validate the model. ROC analysis was used to assess the model performances. A web-based death-risk calculator was implemented and integrated within the Laboratory Information System of the hospital. The final score was constructed by age (the most powerful predictor), blood analytes (the strongest predictors were lactate dehydrogenase, D-dimer, Neutrophil/Lymphocyte ratio, C-reactive protein, Lymphocyte %, Ferritin std and Monocyte %), and Brescia chest X-ray score. The areas under the receiver operating characteristic curve obtained for the three groups (training, validating and testing) were 0.98, 0.83 and 0.78, respectively. The model predicts in-hospital mortality on the basis of data that can be obtained in a short time, directly at the ED on admission. It functions as a web-based calculator, providing a risk score which is easy to interpret. It can be used in the triage process to support the decision on patient allocation.
Data availability
We are unable to share the dataset as it contains sensitive personal data collected during the pandemic at Spedali Civili di Brescia. We cannot share the full data since are data from patients. Interested researchers should contact the authors for any query related to data sharing and submit a project proposal Once defined the goal of the study, and the data needed authors will submit the potential project of collaboration to the IRB of Spedali Civili di Brescia to receive approval to access a deidentified dataset. Please note that other informations related to patients can be acquired, always following approoval of IRB of Spedali Civili di Brescia, not only the ones studied in the paper.Anyway, following request to the authors, it will be possible to share processed version of the dataset ( e.g. an Excel sheet with numbers used to plot the graphs and charts of the manuscript).All code used to analyse the data can be found on GitHub at https://github.com/biostatUniBS/BS_EWS
Article and author information
Author details
Funding
Stefano Calza (PRIN 20178S4EK9)
- Stefano Calza
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Ethics
Human subjects: The Institutional review board aprpoved the study with the entry code NP4000.
Copyright
© 2021, Garrafa et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 1,016
- views
-
- 135
- downloads
-
- 23
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score
eLife 10:e70640.
https://doi.org/10.7554/eLife.70640
Further reading
-
- Biochemistry and Chemical Biology
Prions replicate via the autocatalytic conversion of cellular prion protein (PrPC) into fibrillar assemblies of misfolded PrP. While this process has been extensively studied in vivo and in vitro, non-physiological reaction conditions of fibril formation in vitro have precluded the identification and mechanistic analysis of cellular proteins, which may alter PrP self-assembly and prion replication. Here, we have developed a fibril formation assay for recombinant murine and human PrP (23-231) under near-native conditions (NAA) to study the effect of cellular proteins, which may be risk factors or potential therapeutic targets in prion disease. Genetic screening suggests that variants that increase syntaxin-6 expression in the brain (gene: STX6) are risk factors for sporadic Creutzfeldt–Jakob disease. Analysis of the protein in NAA revealed, counterintuitively, that syntaxin-6 is a potent inhibitor of PrP fibril formation. It significantly delayed the lag phase of fibril formation at highly sub-stoichiometric molar ratios. However, when assessing toxicity of different aggregation time points to primary neurons, syntaxin-6 prolonged the presence of neurotoxic PrP species. Electron microscopy and super-resolution fluorescence microscopy revealed that, instead of highly ordered fibrils, in the presence of syntaxin-6 PrP formed less-ordered aggregates containing syntaxin-6. These data strongly suggest that the protein can directly alter the initial phase of PrP self-assembly and, uniquely, can act as an ‘anti-chaperone’, which promotes toxic aggregation intermediates by inhibiting fibril formation.
-
- Biochemistry and Chemical Biology
Proteasomes are essential molecular machines responsible for the degradation of proteins in eukaryotic cells. Altered proteasome activity has been linked to neurodegeneration, auto-immune disorders and cancer. Despite the relevance for human disease and drug development, no method currently exists to monitor proteasome composition and interactions in vivo in animal models. To fill this gap, we developed a strategy based on tagging of proteasomes with promiscuous biotin ligases and generated a new mouse model enabling the quantification of proteasome interactions by mass spectrometry. We show that biotin ligases can be incorporated in fully assembled proteasomes without negative impact on their activity. We demonstrate the utility of our method by identifying novel proteasome-interacting proteins, charting interactomes across mouse organs, and showing that proximity-labeling enables the identification of both endogenous and small-molecule-induced proteasome substrates.
