1
|
Villar J, González-Martín JM, Hernández-González J, Armengol MA, Fernández C, Martín-Rodríguez C, Mosteiro F, Martínez D, Sánchez-Ballesteros J, Ferrando C, Domínguez-Berrot AM, Añón JM, Parra L, Montiel R, Solano R, Robaglia D, Rodríguez-Suárez P, Gómez-Bentolila E, Fernández RL, Szakmany T, Steyerberg EW, Slutsky AS. Predicting ICU Mortality in Acute Respiratory Distress Syndrome Patients Using Machine Learning: The Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Study. Crit Care Med 2023; 51:1638-1649. [PMID: 37651262 DOI: 10.1097/ccm.0000000000006030] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/02/2023]
Abstract
OBJECTIVES To assess the value of machine learning approaches in the development of a multivariable model for early prediction of ICU death in patients with acute respiratory distress syndrome (ARDS). DESIGN A development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts. SETTING A network of multidisciplinary ICUs. PATIENTS A total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS We developed and tested prediction models in 1,000 ARDS patients. We performed logistic regression analysis following variable selection by a genetic algorithm, random forest and extreme gradient boosting machine learning techniques. Potential predictors included demographics, comorbidities, ventilatory and oxygenation descriptors, and extrapulmonary organ failures. Risk modeling identified some major prognostic factors for ICU mortality, including age, cancer, immunosuppression, Pa o2 /F io2 , inspiratory plateau pressure, and number of extrapulmonary organ failures. Together, these characteristics contained most of the prognostic information in the first 24 hours to predict ICU mortality. Performance with machine learning methods was similar to logistic regression (area under the receiver operating characteristic curve [AUC], 0.87; 95% CI, 0.82-0.91). External validation in an independent cohort of 303 ARDS patients confirmed that the performance of the model was similar to a logistic regression model (AUC, 0.91; 95% CI, 0.87-0.94). CONCLUSIONS Both machine learning and traditional methods lead to promising models to predict ICU death in moderate/severe ARDS patients. More research is needed to identify markers for severity beyond clinical determinants, such as demographics, comorbidities, lung mechanics, oxygenation, and extrapulmonary organ failure to guide patient management.
Collapse
Affiliation(s)
- Jesús Villar
- CIBER de Enfermedades Respiratorias, Instituto de Salud Carlos III, Madrid, Spain
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
- Li Ka Shing Knowledge Institute at St. Michael's Hospital, Toronto, ON, Canada
| | - Jesús M González-Martín
- CIBER de Enfermedades Respiratorias, Instituto de Salud Carlos III, Madrid, Spain
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | | | - Miguel A Armengol
- Big Data Department, PMC-FPS, Regional Ministry of Health and Consumer Affairs, Sevilla, Spain
| | - Cristina Fernández
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | | | - Fernando Mosteiro
- Intensive Care Unit, Hospital Universitario de A Coruña, La Coruña, Spain
| | - Domingo Martínez
- Intensive Care Unit, Hospital Universitario Virgen de Arrixaca, Murcia, Spain
| | | | - Carlos Ferrando
- Surgical Intensive Care Unit, Department of Anesthesia, Hospital Clinic, IDIBAPS, Barcelona, Spain
| | | | - José M Añón
- Intensive Care Unit, Hospital Universitario La Paz, IdiPaz, Madrid, Spain
| | - Laura Parra
- Intensive Care Unit, Hospital Clínico Universitario de Valladolid, Valladolid, Spain
| | - Raquel Montiel
- Intensive Care Unit, Hospital Universitario NS de Candelaria, Santa Cruz de Tenerife, Spain
| | - Rosario Solano
- Intensive Care Unit, Hospital Virgen de La Luz, Cuenca, Spain
| | - Denis Robaglia
- Intensive Care Unit, Hospital Universitario Fundación Jiménez Díaz, Madrid, Spain
| | - Pedro Rodríguez-Suárez
- CIBER de Enfermedades Respiratorias, Instituto de Salud Carlos III, Madrid, Spain
- Thoracic Surgery, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | | | - Rosa L Fernández
- CIBER de Enfermedades Respiratorias, Instituto de Salud Carlos III, Madrid, Spain
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | - Tamas Szakmany
- Department of Intensive Care Medicine & Anesthesia, Aneurin Bevan University Health Board, Newport, United Kingdom
- Cardiff University, Cardiff, United Kingdom
| | - Ewout W Steyerberg
- Department Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands
| | - Arthur S Slutsky
- Li Ka Shing Knowledge Institute at St. Michael's Hospital, Toronto, ON, Canada
- Division of Critical Care Medicine, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
2
|
Villar J, González-Martín JM, Ambrós A, Mosteiro F, Martínez D, Fernández L, Soler JA, Parra L, Solano R, Soro M, Del Campo R, González-Luengo RI, Civantos B, Montiel R, Pita-García L, Vidal A, Añón JM, Ferrando C, Díaz-Domínguez FJ, Mora-Ordoñez JM, Fernández MM, Fernández C, Fernández RL, Rodríguez-Suárez P, Steyerberg EW, Kacmarek RM. Stratification for Identification of Prognostic Categories In the Acute RESpiratory Distress Syndrome (SPIRES) Score. Crit Care Med 2021; 49:e920-e930. [PMID: 34259448 DOI: 10.1097/ccm.0000000000005142] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
OBJECTIVES To develop a scoring model for stratifying patients with acute respiratory distress syndrome into risk categories (Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score) for early prediction of death in the ICU, independent of the underlying disease and cause of death. DESIGN A development and validation study using clinical data from four prospective, multicenter, observational cohorts. SETTING A network of multidisciplinary ICUs. PATIENTS One-thousand three-hundred one patients with moderate-to-severe acute respiratory distress syndrome managed with lung-protective ventilation. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS The study followed Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines for prediction models. We performed logistic regression analysis, bootstrapping, and internal-external validation of prediction models with variables collected within 24 hours of acute respiratory distress syndrome diagnosis in 1,000 patients for model development. Primary outcome was ICU death. The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score was based on patient's age, number of extrapulmonary organ failures, values of end-inspiratory plateau pressure, and ratio of Pao2 to Fio2 assessed at 24 hours of acute respiratory distress syndrome diagnosis. The pooled area under the receiver operating characteristic curve across internal-external validations was 0.860 (95% CI, 0.831-0.890). External validation in a new cohort of 301 acute respiratory distress syndrome patients confirmed the accuracy and robustness of the scoring model (area under the receiver operating characteristic curve = 0.870; 95% CI, 0.829-0.911). The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score stratified patients in three distinct prognostic classes and achieved better prediction of ICU death than ratio of Pao2 to Fio2 at acute respiratory distress syndrome onset or at 24 hours, Acute Physiology and Chronic Health Evaluation II score, or Sequential Organ Failure Assessment scale. CONCLUSIONS The Stratification for identification of Prognostic categories In the acute RESpiratory distress syndrome score represents a novel strategy for early stratification of acute respiratory distress syndrome patients into prognostic categories and for selecting patients for therapeutic trials.
Collapse
Affiliation(s)
- Jesús Villar
- CIBER de Enfermedades Respiratorias, Instituto Salud Carlos III, Madrid, Spain
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | - Jesús M González-Martín
- Division of Biostatistics, Research Unit, Hospital Universitario Dr. Negrín, Las Palmas, Spain
| | - Alfonso Ambrós
- Intensive Care Unit, Hospital General Universitario de Ciudad Real, Ciudad Real, Spain
| | - Fernando Mosteiro
- Intensive Care Unit, Hospital Universitario A Coruña, La Coruña, Spain
| | - Domingo Martínez
- Intensive Care Unit, Hospital Universitario Virgen de Arrixaca, Murcia, Spain
| | - Lorena Fernández
- Intensive Care Unit, Hospital Universitario Río Hortega, Valladolid, Spain
| | - Juan A Soler
- Intensive Care Unit, Hospital Universitario Virgen de Arrixaca, Murcia, Spain
| | - Laura Parra
- Intensive Care Unit, Hospital Clínico Universitario de Valladolid, Valladolid, Spain
| | - Rosario Solano
- Intensive Care Unit, Hospital Virgen de la Luz, Cuenca, Spain
| | - Marina Soro
- Department of Anesthesiology, Hospital Clínico Universitario de Valencia, Valencia, Spain
| | - Rafael Del Campo
- Intensive Care Unit, Hospital General Universitario de Ciudad Real, Ciudad Real, Spain
| | | | - Belén Civantos
- Intensive Care Unit, Hospital Universitario La Paz, IdiPAZ, Madrid, Spain
| | - Raquel Montiel
- Intensive Care Unit, Hospital Universitario NS de Candelaria, Santa Cruz de Tenerife, Spain
| | - Lidia Pita-García
- Intensive Care Unit, Hospital Universitario A Coruña, La Coruña, Spain
| | - Anxela Vidal
- Intensive Care Unit, Fundación Hospital Universitario Jiménez Díaz, Madrid, Spain
| | - José M Añón
- CIBER de Enfermedades Respiratorias, Instituto Salud Carlos III, Madrid, Spain
- Intensive Care Unit, Hospital Universitario La Paz, IdiPAZ, Madrid, Spain
| | - Carlos Ferrando
- CIBER de Enfermedades Respiratorias, Instituto Salud Carlos III, Madrid, Spain
- Department of Anesthesiology and Critical Care, Hospital Clinic, Institut D'investigació August Pi i Sunyer, Barcelona, Spain
| | | | - Juan M Mora-Ordoñez
- Intensive Care Unit, Hospital Regional Universitario de Málaga Carlos Haya, Málaga, Spain
| | - M Mar Fernández
- Intensive Care Unit, Hospital Universitario Mutua Terrassa, Terrassa, Barcelona, Spain
| | - Cristina Fernández
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | - Rosa L Fernández
- CIBER de Enfermedades Respiratorias, Instituto Salud Carlos III, Madrid, Spain
- Research Unit, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | - Pedro Rodríguez-Suárez
- Department of Thoracic Surgery, Hospital Universitario Dr. Negrín, Las Palmas de Gran Canaria, Spain
| | - Ewout W Steyerberg
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands
- Department of Public Health, Erasmus MC, Rotterdam, The Netherlands
| | - Robert M Kacmarek
- Department of Respiratory Care, Massachusetts General Hospital, Boston, MA
- Department of Anesthesiology, Harvard University, Boston, MA
| |
Collapse
|