Disease-course adapting machine learning prognostication models in critically ill elderly COVID-19 patients ; a multi-centre cohort study with external validation
Funding: he support of the study in France by a grant from Fondation Assistance Publique-Hôpitaux de Paris Pour la Recherche is greatly appreciated. In Norway, the study was supported by a grant from Health Region West. In addition, EOSCsecretariat.eu provided support and has received funding from the European Union's Horizon Programme call H2020-INFRAEOSC-05-2018-2019, grant agreement number 831644. This work was supported by the Forschungskommission of the Medical Faculty of Heinrich-Heine-University Düsseldorf (grant 2018-32 to GW and grant 2020-21 to RB for a Clinician Scientist Track). The complete list of COVIP collaborators is provided in Multimedia Appendix 10. ; BACKGROUND: The SARS-CoV-2 coronavirus disease (COVID-19) pandemic is challenging health care systems globally. The disease disproportionately affects the elderly population, both in terms of disease severity and mortality risk. OBJECTIVE: This study aimed to evaluate machine-learning based prognostication models for critically ill elderly COVID-19 patients, which dynamically incorporated multifaceted clinical information on the evolution of the disease. METHODS: This multi-centre cohort study obtained patient data from 151 ICUs from 26 countries (COVIP study). Different models based on the Sequential Organ Failure Assessment (SOFA), Logistic Regression (LR), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) were derived as baseline models that included admission variables only. We subsequently included clinical events and time-to-event as additional variables to derive the final models using the same algorithms and compared their performance with the baseline group. Furthermore, we derived baseline and final models on a European patient cohort and externally validated them on a non-European cohort that included Asian, African and American patients. RESULTS: In total, 1,432 elderly (≥70 years) COVID-19 positive patients were admitted to an intensive care unit. Of these 809 (56.5%) patients survived up to 30 days after admission. The average length of stay was 21.6 (±18.2) days. Final models that incorporated clinical events and time-to-event provided superior performance with AUC of 0.81 (95% CI 0.804-0.811), with respect to both, the baseline models that used admission variables only and conventional ICU prediction models (SOFA-score, p<.001). The average precision increased from 0.65 (95% CI 0.650-0.655) to 0.77 (95% CI 0.759-0.770). CONCLUSIONS: Integrating important clinical events and time-to-event information led to a superior accuracy of 30-day mortality prediction compared with models based on the admission information and conventional ICU prediction models. The present study shows that machine-learning models provide additional information and may support complex decision-making in critically ill elderly COVID-19 patients. CLINICALTRIAL: Nct04321265. ; publishersversion ; published