Machine learning to predict vasopressin responsiveness in patients with septic shock

Abstract

Study Objectives The objective of this study was to develop and externally validate a model to predict adjunctive vasopressin response in patients with septic shock being treated with norepinephrine for bedside use in the intensive care unit. Design This was a retrospective analysis of two adult tertiary intensive care unit septic shock populations. Setting Barnes‐Jewish Hospital (BJH) from 2010 to 2017 and Beth Israel Deaconess Medical Center (BIDMC) from 2001 to 2012. Patients Two septic shock populations (548 BJH patients and 464 BIDMC patients) that received vasopressin as second‐line vasopressor. Intervention Patients who were vasopressin responsive were compared with those who were nonresponsive. Vasopressin response was defined as survival with at least a 20% decrease in maximum daily norepinephrine requirements by one calendar day after vasopressin initiation, without a third‐line vasopressor. Measurements Two supervised machine learning models (gradient‐boosting machine [XGBoost] and elastic net penalized logistic regression [EN]) were trained in 1000 bootstrap replications of the BJH data and externally validated in the BIDMC data to predict vasopressin responsiveness. Main Results Vasopressin responsiveness was similar among each cohort (BJH 45% and BIDMC 39%). Mortality was lower for vasopressin responders compared with nonresponders in the BJH (51% vs. 73%) and BIDMC (45% vs. 83%) cohorts, respectively. Both models demonstrated modest discrimination in the training (XGBoost area under receiver operator curve [AUROC] 0.61 [95% confidence interval (CI) 0.61–0.61], EN 0.59 [95% CI 0.58–0.59]) and external validation (XGBoost 0.68 [95% CI 0.63–0.73], EN 0.64 [95% CI 0.59–0.69]) datasets. Conclusion Vasopressin nonresponsiveness is common and associated with increased mortality. The models' modest performances highlight the complexity of septic shock and indicate that more research will be required before clinical decision support tools can aid in anticipating patient‐specific responsiveness to vasopressin.

Initiating angiotensin II at lower vasopressor doses in vasodilatory shock: an exploratory post-hoc analysis of the ATHOS-3 clinical trial

“…Catecholamines and vasopressin have traditionally been the initial vasopressors administered in patients with persistent hypotension in spite of fluid therapy [ 4 ]. However, these agents alone may be inadequate to achieve and maintain hemodynamic goals [ 5 ]; indeed, vasopressin achieves target hemodynamic goals in less than 50% of patients [ 18 – 20 ]. Escalation of vasopressor dosage in patients with persistent hypotension is thus common, and although dosing thresholds in outcomes research vary, exposure to high dosages of vasopressors has consistently portended grave prognosis in observational studies [ 21 ].…”

Vasopressin Response and Clinical Trajectory in Septic Shock Patients

“…17 We also only evaluated one definition of vasopressin response when several definitions exist in the literature. 6,18–23 Future studies should evaluate the predictive accuracy of various vasopressin response definitions for patient-centered outcomes. Further, because we did not conduct a formal a priori power analysis, our sample size may be inadequate to detect clinically important differences in clinical outcomes.…”

Sepsis and acute respiratory failure in patients with cancer: how can we improve care and outcomes even further?

“…Recently, Benzoni et al extended temperature trajectory subphenotyping to oncology patients with neutropenia, validating these four subgroups’ prognostic value and observing that corticosteroids appear to influence subphenotype membership [95 ▪ ]. Important next steps to build on this work should test the extent to which oncologic sepsis subphenotypes respond differentially to corticosteroids [96,97], granulocyte colony-stimulating factor [92], and fluid/vasopressor resuscitative strategies [98–101]. These advances pair well with ongoing efforts to differentiate mimics of oncologic sepsis, including cytokine release syndrome and hemophagocytic lymphohistiocytosis [102,103].…”

“…These authors have extended this approach to encompass multivariable trajectories of clinical vital signs, including evidence that certain subphenotypes respond differentially to balanced crystalloids versus normal saline during early resuscitation [ ]. Important next steps to build on this work should test the extent to which oncologic sepsis subphenotypes respond differentially to corticosteroids [96,97], granulocyte colony-stimulating factor [92], and fluid/vasopressor resuscitative strategies [98][99][100][101]. These advances pair well with ongoing efforts to differentiate mimics of oncologic sepsis, including cytokine release syndrome and hemophagocytic lymphohistiocytosis [102,103].…”