Ményssa Cherifa1,2,3, Alice Blet3,4,5, Antoine Chambaz2,3,6, Etienne Gayat4,5, Matthieu Resche-Rigon1,2,3, Romain Pirracchio2,3,7. 1. From the Université de Paris, Paris, France. 2. Statistic and Epidemiologic Research Center Sorbonne Paris Cité, INSERM UMR-1153, ECSTRRA Team, Paris, France. 3. The ACTERREA Research Group, Université De Paris, Paris, France. 4. Department of Anesthesia Burn and Critical Care, University Hospitals Saint-Louis-Lariboisière, AP-HP, Paris, France. 5. BIOCANVAS-Cardiovascular Biomarkers, INSERM UMR-S 942, Paris, France. 6. Department of Applied Mathematics, MAP5, (UMR CNRS 8145), Université de Paris, Paris, France. 7. Department of Anesthesia and Perioperative Medicine, Zuckerberg San Francisco General Hospital, University of California San Francisco, San Francisco, California.
Abstract
BACKGROUND: Acute hypotensive episodes (AHE), defined as a drop in the mean arterial pressure (MAP) <65 mm Hg lasting at least 5 consecutive minutes, are among the most critical events in the intensive care unit (ICU). They are known to be associated with adverse outcome in critically ill patients. AHE prediction is of prime interest because it could allow for treatment adjustment to predict or shorten AHE. METHODS: The Super Learner (SL) algorithm is an ensemble machine-learning algorithm that we specifically trained to predict an AHE 10 minutes in advance. Potential predictors included age, sex, type of care unit, severity scores, and time-evolving characteristics such as mechanical ventilation, vasopressors, or sedation medication as well as features extracted from physiological signals: heart rate, pulse oximetry, and arterial blood pressure. The algorithm was trained on the Medical Information Mart for Intensive Care dataset (MIMIC II) database. Internal validation was based on the area under the receiver operating characteristic curve (AUROC) and the Brier score (BS). External validation was performed using an external dataset from Lariboisière hospital, Paris, France. RESULTS: Among 1151 patients included, 826 (72%) patients had at least 1 AHE during their ICU stay. Using 1 single random period per patient, the SL algorithm with Haar wavelets transform preprocessing was associated with an AUROC of 0.929 (95% confidence interval [CI], 0.899-0.958) and a BS of 0.08. Using all available periods for each patient, SL with Haar wavelets transform preprocessing was associated with an AUROC of 0.890 (95% CI, 0.886-0.895) and a BS of 0.11. In the external validation cohort, the AUROC reached 0.884 (95% CI, 0.775-0.993) with 1 random period per patient and 0.889 (0.768-1) with all available periods and BSs <0.1. CONCLUSIONS: The SL algorithm exhibits good performance for the prediction of an AHE 10 minutes ahead of time. It allows an efficient, robust, and rapid evaluation of the risk of hypotension that opens the way to routine use.
BACKGROUND:Acute hypotensive episodes (AHE), defined as a drop in the mean arterial pressure (MAP) <65 mm Hg lasting at least 5 consecutive minutes, are among the most critical events in the intensive care unit (ICU). They are known to be associated with adverse outcome in critically illpatients. AHE prediction is of prime interest because it could allow for treatment adjustment to predict or shorten AHE. METHODS: The Super Learner (SL) algorithm is an ensemble machine-learning algorithm that we specifically trained to predict an AHE 10 minutes in advance. Potential predictors included age, sex, type of care unit, severity scores, and time-evolving characteristics such as mechanical ventilation, vasopressors, or sedation medication as well as features extracted from physiological signals: heart rate, pulse oximetry, and arterial blood pressure. The algorithm was trained on the Medical Information Mart for Intensive Care dataset (MIMIC II) database. Internal validation was based on the area under the receiver operating characteristic curve (AUROC) and the Brier score (BS). External validation was performed using an external dataset from Lariboisière hospital, Paris, France. RESULTS: Among 1151 patients included, 826 (72%) patients had at least 1 AHE during their ICU stay. Using 1 single random period per patient, the SL algorithm with Haar wavelets transform preprocessing was associated with an AUROC of 0.929 (95% confidence interval [CI], 0.899-0.958) and a BS of 0.08. Using all available periods for each patient, SL with Haar wavelets transform preprocessing was associated with an AUROC of 0.890 (95% CI, 0.886-0.895) and a BS of 0.11. In the external validation cohort, the AUROC reached 0.884 (95% CI, 0.775-0.993) with 1 random period per patient and 0.889 (0.768-1) with all available periods and BSs <0.1. CONCLUSIONS: The SL algorithm exhibits good performance for the prediction of an AHE 10 minutes ahead of time. It allows an efficient, robust, and rapid evaluation of the risk of hypotension that opens the way to routine use.
Authors: Joo Heung Yoon; Vincent Jeanselme; Artur Dubrawski; Marilyn Hravnak; Michael R Pinsky; Gilles Clermont Journal: Crit Care Date: 2020-11-25 Impact factor: 9.097
Authors: José Castela Forte; Hubert E Mungroop; Fred de Geus; Maureen L van der Grinten; Hjalmar R Bouma; Ville Pettilä; Thomas W L Scheeren; Maarten W N Nijsten; Massimo A Mariani; Iwan C C van der Horst; Robert H Henning; Marco A Wiering; Anne H Epema Journal: Sci Rep Date: 2021-02-10 Impact factor: 4.379
Authors: Hind A Beydoun; May A Beydoun; Jordan Weiss; Rana S Gautam; Sharmin Hossain; Brook T Alemu; Alan B Zonderman Journal: Sci Rep Date: 2022-03-15 Impact factor: 4.996
Authors: Hind A Beydoun; May A Beydoun; Brook T Alemu; Jordan Weiss; Sharmin Hossain; Rana S Gautam; Alan B Zonderman Journal: Int J Environ Res Public Health Date: 2022-09-23 Impact factor: 4.614
Authors: Michael R Pinsky; Maurizio Cecconi; Michelle S Chew; Daniel De Backer; Ivor Douglas; Mark Edwards; Olfa Hamzaoui; Glenn Hernandez; Greg Martin; Xavier Monnet; Bernd Saugel; Thomas W L Scheeren; Jean-Louis Teboul; Jean-Louis Vincent Journal: Crit Care Date: 2022-09-28 Impact factor: 19.334