Development and validation of a prognostic COVID-19 severity assessment (COSA) score and machine learning models for patient triage at a tertiary hospital.

Schöning, Verena; Liakoni, Evangelia; Baumgartner, Christine; Exadaktylos, Aristomenis K.; Hautz, Wolf E.; Atkinson, Andrew; Hammann, Felix (2021). Development and validation of a prognostic COVID-19 severity assessment (COSA) score and machine learning models for patient triage at a tertiary hospital. Journal of translational medicine, 19(1), p. 56. BioMed Central 10.1186/s12967-021-02720-w

Sch_ning__J_Translat_Med_2021.pdf - Published Version
Available under License Creative Commons: Attribution (CC-BY).

Download (993kB) | Preview


Clinical risk scores and machine learning models based on routine laboratory values could assist in automated early identification of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) patients at risk for severe clinical outcomes. They can guide patient triage, inform allocation of health care resources, and contribute to the improvement of clinical outcomes.


In- and out-patients tested positive for SARS-CoV-2 at the Insel Hospital Group Bern, Switzerland, between February 1st and August 31st ('first wave', n = 198) and September 1st through November 16th 2020 ('second wave', n = 459) were used as training and prospective validation cohort, respectively. A clinical risk stratification score and machine learning (ML) models were developed using demographic data, medical history, and laboratory values taken up to 3 days before, or 1 day after, positive testing to predict severe outcomes of hospitalization (a composite endpoint of admission to intensive care, or death from any cause). Test accuracy was assessed using the area under the receiver operating characteristic curve (AUROC).


Sex, C-reactive protein, sodium, hemoglobin, glomerular filtration rate, glucose, and leucocytes around the time of first positive testing (- 3 to + 1 days) were the most predictive parameters. AUROC of the risk stratification score on training data (AUROC = 0.94, positive predictive value (PPV) = 0.97, negative predictive value (NPV) = 0.80) were comparable to the prospective validation cohort (AUROC = 0.85, PPV = 0.91, NPV = 0.81). The most successful ML algorithm with respect to AUROC was support vector machines (median = 0.96, interquartile range = 0.85-0.99, PPV = 0.90, NPV = 0.58).


With a small set of easily obtainable parameters, both the clinical risk stratification score and the ML models were predictive for severe outcomes at our tertiary hospital center, and performed well in prospective validation.

Item Type:

Journal Article (Original Article)


04 Faculty of Medicine > Department of General Internal Medicine (DAIM) > Clinic of General Internal Medicine
04 Faculty of Medicine > Department of Haematology, Oncology, Infectious Diseases, Laboratory Medicine and Hospital Pharmacy (DOLS) > Clinic of Infectiology
04 Faculty of Medicine > Department of Intensive Care, Emergency Medicine and Anaesthesiology (DINA) > University Emergency Center

UniBE Contributor:

Schöning, Verena, Liakoni, Evangelia, Baumgartner, Christine, Exadaktylos, Aristomenis, Hautz, Wolf, Atkinson, Andrew David, Hammann, Felix


600 Technology > 610 Medicine & health




BioMed Central




Tobias Tritschler

Date Deposited:

17 Feb 2021 11:56

Last Modified:

05 Dec 2022 15:47

Publisher DOI:


PubMed ID:


Uncontrolled Keywords:

Artificial intelligence Critical illness Risk stratification SARS-CoV-2 Statistical learning




Actions (login required)

Edit item Edit item
Provide Feedback