Alexander Henzi1, Gian-Reto Kleger2, Matthias P Hilty3,4, Pedro D Wendel Garcia3,4, Johanna F Ziegel1. 1. Institute of Mathematical Statistics and Actuarial Science, University of Bern, Bern, Switzerland. 2. Division of Intensive Care Medicine, Cantonal Hospital, St.Gallen, Switzerland. 3. The RISC-19-ICU Registry Board, University of Zurich, Zürich, Switzerland. 4. Institute of Intensive Care Medicine, University Hospital of Zürich, Zürich, Switzerland.
Abstract
RATIONALE: The COVID-19 pandemic induces considerable strain on intensive care unit resources. OBJECTIVES: We aim to provide early predictions of individual patients' intensive care unit length of stay, which might improve resource allocation and patient care during the on-going pandemic. METHODS: We developed a new semiparametric distributional index model depending on covariates which are available within 24h after intensive care unit admission. The model was trained on a large cohort of acute respiratory distress syndrome patients out of the Minimal Dataset of the Swiss Society of Intensive Care Medicine. Then, we predict individual length of stay of patients in the RISC-19-ICU registry. MEASUREMENTS: The RISC-19-ICU Investigators for Switzerland collected data of 557 critically ill patients with COVID-19. MAIN RESULTS: The model gives probabilistically and marginally calibrated predictions which are more informative than the empirical length of stay distribution of the training data. However, marginal calibration was worse after approximately 20 days in the whole cohort and in different subgroups. Long staying COVID-19 patients have shorter length of stay than regular acute respiratory distress syndrome patients. We found differences in LoS with respect to age categories and gender but not in regions of Switzerland with different stress of intensive care unit resources. CONCLUSION: A new probabilistic model permits calibrated and informative probabilistic prediction of LoS of individual patients with COVID-19. Long staying patients could be discovered early. The model may be the basis to simulate stochastic models for bed occupation in intensive care units under different casemix scenarios.
RATIONALE: The COVID-19 pandemic induces considerable strain on intensive care unit resources. OBJECTIVES: We aim to provide early predictions of individual patients' intensive care unit length of stay, which might improve resource allocation and patient care during the on-going pandemic. METHODS: We developed a new semiparametric distributional index model depending on covariates which are available within 24h after intensive care unit admission. The model was trained on a large cohort of acute respiratory distress syndromepatients out of the Minimal Dataset of the Swiss Society of Intensive Care Medicine. Then, we predict individual length of stay of patients in the RISC-19-ICU registry. MEASUREMENTS: The RISC-19-ICU Investigators for Switzerland collected data of 557 critically illpatients with COVID-19. MAIN RESULTS: The model gives probabilistically and marginally calibrated predictions which are more informative than the empirical length of stay distribution of the training data. However, marginal calibration was worse after approximately 20 days in the whole cohort and in different subgroups. Long staying COVID-19patients have shorter length of stay than regular acute respiratory distress syndromepatients. We found differences in LoS with respect to age categories and gender but not in regions of Switzerland with different stress of intensive care unit resources. CONCLUSION: A new probabilistic model permits calibrated and informative probabilistic prediction of LoS of individual patients with COVID-19. Long staying patients could be discovered early. The model may be the basis to simulate stochastic models for bed occupation in intensive care units under different casemix scenarios.
Authors: Pedro David Wendel-Garcia; André Moser; Yok-Ai Que; Matthias Peter Hilty; Marie-Madlen Jeitziner; Hernán Aguirre-Bermeo; Pedro Arias-Sanchez; Janina Apolo; Ferran Roche-Campo; Diego Franch-Llasat; Gian-Reto Kleger; Claudia Schrag; Urs Pietsch; Miodrag Filipovic; Sascha David; Klaus Stahl; Souad Bouaoud; Amel Ouyahia; Patricia Fodor; Pascal Locher; Martin Siegemund; Nuria Zellweger; Sara Cereghetti; Peter Schott; Gianfilippo Gangitano; Maddalena Alessandra Wu; Mario Alfaro-Farias; Gerardo Vizmanos-Lamotte; Hatem Ksouri; Nadine Gehring; Emanuele Rezoagli; Fabrizio Turrini; Herminia Lozano-Gómez; Andrea Carsetti; Raquel Rodríguez-García; Bernd Yuen; Anja Baltussen Weber; Pedro Castro; Jesus Oscar Escos-Orta; Alexander Dullenkopf; Maria C Martín-Delgado; Theodoros Aslanidis; Marie-Helene Perez; Frank Hillgaertner; Samuele Ceruti; Marilene Franchitti Laurent; Julien Marrel; Riccardo Colombo; Marcus Laube; Alberto Fogagnolo; Michael Studhalter; Tobias Wengenmayer; Emiliano Gamberini; Christian Buerkle; Philipp K Buehler; Stefanie Keiser; Muhammed Elhadi; Jonathan Montomoli; Philippe Guerci; Thierry Fumeaux; Reto A Schuepbach; Stephan M Jakob Journal: Crit Care Date: 2022-07-04 Impact factor: 19.334
Authors: Dina A Alabbad; Abdullah M Almuhaideb; Shikah J Alsunaidi; Kawther S Alqudaihi; Fatimah A Alamoudi; Maha K Alhobaishi; Naimah A Alaqeel; Mohammed S Alshahrani Journal: Inform Med Unlocked Date: 2022-04-14