Valsecchi, Maria Grazia

Abstract Rationale Cardiovascular instability/collapse is a common peri-intubation event in patients who are critically ill. Objectives To identify potentially modifiable variables associated with peri-intubation cardiovascular instability/collapse (i.e., systolic arterial pressure <65 mm Hg [once] or <90 mm Hg for >30 minutes; new/increased vasopressor requirement; fluid bolus >15 ml/kg, or cardiac arrest). Methods INTUBE (International Observational Study to Understand the Impact and Best Practices of Airway Management In Critically Ill Patients) was a multicenter prospective cohort study of patients who were critically ill and undergoing tracheal intubation in a convenience sample of 197 sites from 29 countries across five continents from October 1, 2018, to July 31, 2019. Measurements and Main Results A total of 2,760 patients were included in this analysis. Peri-intubation cardiovascular instability/collapse occurred in 1,199 out of 2,760 patients (43.4%). Variables associated with this event were older age (odds ratio [OR], 1.02; 95% confidence interval [CI], 1.02–1.03), higher heart rate (OR, 1.008; 95% CI, 1.004–1.012), lower systolic blood pressure (OR, 0.98; 95% CI, 0.98–0.99), lower oxygen saturation as measured by pulse oximetry/Fi O2 before induction (OR, 0.998; 95% CI, 0.997–0.999), and the use of propofol as an induction agent (OR, 1.28; 95% CI, 1.05–1.57). Patients with peri-intubation cardiovascular instability/collapse were at a higher risk of ICU mortality with an adjusted OR of 2.47 (95% CI, 1.72–3.55), P < 0.001. The inverse probability of treatment weighting method identified the use of propofol as the only factor independently associated with cardiovascular instability/collapse (OR, 1.23; 95% CI, 1.02–1.49). When administered before induction, vasopressors (OR, 1.33; 95% CI, 0.84–2.11) or fluid boluses (OR, 1.17; 95% CI, 0.96–1.44) did not reduce the incidence of cardiovascular instability/collapse. Conclusions Peri-intubation cardiovascular instability/collapse was associated with an increased risk of both ICU and 28-day mortality. The use of propofol for induction was identified as a modifiable intervention significantly associated with cardiovascular instability/collapse. Clinical trial registered with clinicaltrials.gov (NCT03616054).

AbstractBackground & AimsMachine learning (ML) provides new approaches for prognostication through the identification of novel subgroups of patients. We explored whether ML could support disease sub‐phenotyping and risk stratification in primary biliary cholangitis (PBC).MethodsML was applied to an international dataset of PBC patients. The dataset was split into a derivation cohort (training set) and a validation cohort (validation set), and key clinical features were analysed. The outcome was a composite of liver‐related death or liver transplantation. ML and standard survival analysis were performed.ResultsThe training set was composed of 11,819 subjects, while the validation set was composed of 1,069 subjects. ML identified four clusters of patients characterized by different phenotypes and long‐term prognosis. Cluster 1 (n = 3566) included patients with excellent prognosis, whereas Cluster 2 (n = 3966) consisted of individuals at worse prognosis differing from Cluster 1 only for albumin levels around the limit of normal. Cluster 3 (n = 2379) included young patients with florid cholestasis and Cluster 4 (n = 1908) comprised advanced cases. Further sub‐analyses on the dynamics of albumin within the normal range revealed that ursodeoxycholic acid‐induced increase of albumin >1.2 x lower limit of normal (LLN) is associated with improved transplant‐free survival.ConclusionsUnsupervised ML identified four novel groups of PBC patients with different phenotypes and prognosis and highlighted subtle variations of albumin within the normal range. Therapy‐induced increase of albumin >1.2 x LLN should be considered a treatment goal.