Abstract 17867: Dynamic Prediction of Patient Outcomes During Ongoing Cardiopulmonary Resuscitation

PurposeThe probability of ROSC and subsequent favorable outcomes may change dynamically during ACLS.HypothesisWe hypothesized that the probabilities of achieving ROSC and subsequent clinical outcomes (1-week and 1-month survival and neurologic recovery) can be simultaneously estimated as a function of initial patient conditions and the duration of ACLS during an ongoing resuscitation.MethodsAdult (≥18 years), non-traumatic OHCA patients without prehospital ROSC were included. Utstein variables and initial arterial blood gas (ABG) measurements were used as predictors. Incidence of ROSC during the first thirty minutes of ACLS was modelled using spline-based parametric survival analysis. Conditional probabilities of subsequent outcomes after ROSC (1-week and 1-month survival and 6-month neurologic recovery) were modelled using multivariable logistic regression. The ROSC and conditional probability models were then combined to estimate both the chance of achieving ROSC and subsequent outcomes by providing k additional minutes of effort from the jth minute of an ongoing resuscitation.Results727 patients were analyzed. Baseline hazard function of ROSC showed rapidly increasing resuscitability peaking at the 11th minute with a rapid decrease afterwards. The conditional probabilities of subsequent outcomes after ROSC were also dependent on the resuscitation duration with odds ratio for 1-week and 1-month survival and neurologic recovery 0.93 (95% CI0.90-0.96, p