Machine learning-based prediction of hypotension following emergency intubation

Introduction Post-intubation hypotension (PIH) is a frequent complication of emergency endotracheal intubation and is associated with increased mortality. Early identification of high-risk patients remains challenging, and existing prediction tools demonstrate moderate accuracy. Objective We aim to identify predictors of PIH and develop machine learning models for pre-intubation risk stratification. Methods We conducted a multicentre retrospective study across 3 Mayo Clinic hospitals, including 600 adults undergoing urgent intubation in the intensive care unit. PIH was defined by mean arterial pressure<65 mm Hg, systolic blood pressure (SBP)<80 mm Hg or ≥40% decline or vasopressor initiation/escalation within 30 min. Three model frameworks were developed: Shock Indices (SIs), Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ Failure Assessment (SOFA), incorporating demographic, haemodynamic, laboratory and sedation variables. Various machine learning algorithms were applied to analyse the three models. Results PIH occurred in 46% of patients included in the study. In the SIs model, stepwise logistic regression achieved an area under the curve (AUC) of 0.76. The APACHE II framework showed the strongest performance, with random forest achieving an ROC AUC of 0.82 and the ensemble model demonstrating the highest overall discrimination (Receiver operator Curve [ROC] AUC 0.83) with favourable accuracy and F1 metrics. The SOFA framework showed moderate performance, with an ensemble ROC AUC of 0.73. Key predictors included pre-intubation vasopressor use, SBP, platelet count and haematological parameters. Conclusions Machine learning models using routinely available pre-intubation data showed potential to predict PIH in this retrospective proof-of-concept study. These findings support further development of anticipatory artificial intelligence-driven risk stratification in critical care, but the models should not be considered ready for bedside implementation until they undergo prospective validation in larger, independent and more diverse cohorts.