Machine learning identifies ICU outcome predictors in a multicenter COVID-19 cohort.
Harry MaguniaSimone LedererRaphael VerbuechelnBryant Joseph GilotMichael KoeppenHelene A HaeberleValbona MirakajPascal HofmannGernot MarxJohannes BickenbachBoris NoheMichael LayClaudia SpiesAndreas EdelFridtjof SchiefenhövelTim RahmelChristian PutensenTimur SellmannThea KochTimo BrandenburgerDetlef Kindgen-MillesThorsten BrennerMarc BergerKai ZacharowskiElisabeth AdamMatthias PoschOnnen MoererChristian S ScheerDaniel SeddingMarkus A WeigandFalk FichtnerCarla NauFlorian PrätschThomas WiesmannChristian KochGerhard SchneiderTobias LahmerAndreas StraubAndreas MeiserManfred WeissBettina JungwirthFrank WapplerPatrick MeybohmJohannes HerrmannNisar MalekOliver KohlbacherStephanie BiergansPeter RosenbergerPublished in: Critical care (London, England) (2021)
Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration "ClinicalTrials" (clinicaltrials.gov) under NCT04455451.
Keyphrases