Prediction of COVID-19 deterioration in high-risk patients at diagnosis: an early warning score for advanced COVID-19 developed by machine learning

  • Purpose: While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization. Methods: We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16). Results: The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface. Conclusion: We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.
Author:Carolin Ellen Marianne JakobORCiDGND, Ujjwal Mukund MahajanORCiDGND, Marcus OswaldGND, Melanie StecherORCiDGND, Maximilian SchonsORCiD, Julia MayerleORCiDGND, Siegbert RiegORCiDGND, Mathias PletzORCiDGND, Uta MerleORCiDGND, Kai WilleORCiDGND, Stefan BorgmannGND, Christoph Daniel SpinnerORCiDGND, Sebastian Conrad Johannes DolffORCiDGND, Clemens Martin SchererORCiDGND, Lisa PilgramORCiDGND, Maria Madeleine RüthrichGND, Frank HansesORCiDGND, Martin HowerORCiDGND, Richard StraußGND, Steffen MaßbergORCiDGND, Ahmet Görkem ErORCiD, Norma JungORCiDGND, Jörg Janne VehreschildORCiDGND, Hans Christian StubbeORCiDGND, Lukas TomettenORCiDGND, Rainer KönigGND
Parent Title (English):Infection
Publisher:Urban & Vogel ; Springer
Place of publication:München ; Heidelberg
Document Type:Article
Date of Publication (online):2021/07/19
Date of first Publication:2021/07/19
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Contributing Corporation:The LEOSS Study group
Release Date:2022/07/11
Tag:Advanced stage; COVID-19; Complicated stage; LEOSS; Machine learning; Predictive model
Page Number:12
First Page:359
Last Page:370
Further Supplementary Information: The online version contains supplementary material available at
Open Access funding enabled and organized by Projekt DEAL. MO and RK were supported by the Federal Ministry of Education and Research (BMBF), Germany, FKZ: 01EO1502 (CSCC) and 01KI2015OA (SARSiRNA). UMM, JM and HS were supported by the PePPP center of excellence MV ESF/14-BM-A55-0045/16; ESF MV V-630-S-150-2012/132/133); Deutsche Forschungsgemeinschaft, SFB1321/1 (Project P14, 329628492), Förderprogramm für Forschung und Lehre (FöFoLe, Reg. Nr. 1028), Friedrich-Baur-Stiftung (Reg. Nr. 42/17), and Bundesministerium für Bildung und Forschung 01EK1511A. The LEOSS study was supported by the German Center for Infection Research (DZIF) and the Willy Robert Pitzer Foundation.
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 61 Medizin und Gesundheit / 610 Medizin und Gesundheit
Licence (German):License LogoCreative Commons - Namensnennung 4.0