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

Abstract

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.

SARS-CoV-2 infection in chronic kidney disease patients with pre-existing dialysis: description across different pandemic intervals and effect on disease course (mortality)

“…Our multivariable analysis confirmed already known risk factors also for patients suffering from CKD, such as age, chronic heart failure, coronary artery disease and an active oncological disease [ 23 – 25 ], which was described for the whole LEOSS cohort [ 18 , 26 – 28 ] and which we published in a smaller CKD cohort previously [ 8 ]. In contrast, broadly accepted risk factors, such as male sex, hypertension or diabetes mellitus failed to present as additional risk factors in our model, which might be due to the overall high prevalence in our cohort.…”

Specific Risk Factors for Fatal Outcome in Critically Ill COVID-19 Patients: Results from a European Multicenter Study

“…Our study could serve as a starting point for the development of a risk score that is specific to critically ill COVID-19 patients. Once such a score has been validated, it would be of high interest to compare its performance with scores for COVID-19 developed by others [36,57,58], and with classic ICU mortality scores such as SAPS, SOFA, or NEWS2 [59].…”

“…Ethical standards for the admission to an intensive care unit (ICU) in case of limited resources have been published [34]. Numerous efforts have been made to predict the occurrence of critical illness for COVID-19 patients [35], typically at an early stage of the disease [36]. However, studies describing specific medical risk factors for already critically ill patients suffering from severe COVID-19 and a corresponding risk score are lacking to date.…”

Machine Learning Based Prediction of COVID-19 Mortality Suggests Repositioning of Anticancer Drug for Treating Severe Cases

“…To our knowledge, this is the first ML based mortality model based on such (notionally) representative German data. Notably, ML models predicting alternative endpoints using LEOSS have been published recently (Jakob et al 2021;Werfel et al 2021).…”