Predicting ICU Mortality in Acute Respiratory Distress Syndrome Patients Using Machine Learning : The Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Study
Copyright © 2023 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved..
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.
Errataetall: |
CommentIn: Crit Care Med. 2023 Dec 1;51(12):1814-1816. - PMID 37971334 |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:51 |
---|---|
Enthalten in: |
Critical care medicine - 51(2023), 12 vom: 01. Dez., Seite 1638-1649 |
Sprache: |
Englisch |
---|
Links: |
---|
Themen: |
Journal Article |
---|
Anmerkungen: |
Date Completed 28.11.2023 Date Revised 27.03.2024 published: Print-Electronic CommentIn: Crit Care Med. 2023 Dec 1;51(12):1814-1816. - PMID 37971334 Citation Status MEDLINE |
---|
doi: |
10.1097/CCM.0000000000006030 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM361491077 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM361491077 | ||
003 | DE-627 | ||
005 | 20240329000019.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1097/CCM.0000000000006030 |2 doi | |
028 | 5 | 2 | |a pubmed24n1353.xml |
035 | |a (DE-627)NLM361491077 | ||
035 | |a (NLM)37651262 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Villar, Jesús |e verfasserin |4 aut | |
245 | 1 | 0 | |a Predicting ICU Mortality in Acute Respiratory Distress Syndrome Patients Using Machine Learning |b The Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Study |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 28.11.2023 | ||
500 | |a Date Revised 27.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a CommentIn: Crit Care Med. 2023 Dec 1;51(12):1814-1816. - PMID 37971334 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved. | ||
520 | |a 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) | ||
520 | |a DESIGN: A development, testing, and external validation study using clinical data from four prospective, multicenter, observational cohorts | ||
520 | |a SETTING: A network of multidisciplinary ICUs | ||
520 | |a PATIENTS: A total of 1,303 patients with moderate-to-severe ARDS managed with lung-protective ventilation | ||
520 | |a INTERVENTIONS: None | ||
520 | |a 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) | ||
520 | |a 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 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Multicenter Study | |
650 | 4 | |a Observational Study | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a González-Martín, Jesús M |e verfasserin |4 aut | |
700 | 1 | |a Hernández-González, Jerónimo |e verfasserin |4 aut | |
700 | 1 | |a Armengol, Miguel A |e verfasserin |4 aut | |
700 | 1 | |a Fernández, Cristina |e verfasserin |4 aut | |
700 | 1 | |a Martín-Rodríguez, Carmen |e verfasserin |4 aut | |
700 | 1 | |a Mosteiro, Fernando |e verfasserin |4 aut | |
700 | 1 | |a Martínez, Domingo |e verfasserin |4 aut | |
700 | 1 | |a Sánchez-Ballesteros, Jesús |e verfasserin |4 aut | |
700 | 1 | |a Ferrando, Carlos |e verfasserin |4 aut | |
700 | 1 | |a Domínguez-Berrot, Ana M |e verfasserin |4 aut | |
700 | 1 | |a Añón, José M |e verfasserin |4 aut | |
700 | 1 | |a Parra, Laura |e verfasserin |4 aut | |
700 | 1 | |a Montiel, Raquel |e verfasserin |4 aut | |
700 | 1 | |a Solano, Rosario |e verfasserin |4 aut | |
700 | 1 | |a Robaglia, Denis |e verfasserin |4 aut | |
700 | 1 | |a Rodríguez-Suárez, Pedro |e verfasserin |4 aut | |
700 | 1 | |a Gómez-Bentolila, Estrella |e verfasserin |4 aut | |
700 | 1 | |a Fernández, Rosa L |e verfasserin |4 aut | |
700 | 1 | |a Szakmany, Tamas |e verfasserin |4 aut | |
700 | 1 | |a Steyerberg, Ewout W |e verfasserin |4 aut | |
700 | 1 | |a Slutsky, Arthur S |e verfasserin |4 aut | |
700 | 0 | |a Predicting Outcome and STratifiCation of severity in ARDS (POSTCARDS) Network |e verfasserin |4 aut | |
700 | 1 | |a Ambrós, Alfonso |e investigator |4 oth | |
700 | 1 | |a Del Campo, Rafael |e investigator |4 oth | |
700 | 1 | |a Bueno-González, Ana |e investigator |4 oth | |
700 | 1 | |a Hornos-López, Carmen |e investigator |4 oth | |
700 | 1 | |a Pita-García, Lidia |e investigator |4 oth | |
700 | 1 | |a Díaz-Lamas, Ana M |e investigator |4 oth | |
700 | 1 | |a Arrojo, Regina |e investigator |4 oth | |
700 | 1 | |a Soler, Juan A |e investigator |4 oth | |
700 | 1 | |a Conesa-Cayuela, Luís A |e investigator |4 oth | |
700 | 1 | |a Del Saz-Ortiz, Ana M |e investigator |4 oth | |
700 | 1 | |a Capilla, Lucia |e investigator |4 oth | |
700 | 1 | |a Fernández, Lorena |e investigator |4 oth | |
700 | 1 | |a Blanco, Jesús |e investigator |4 oth | |
700 | 1 | |a Muriel, Arturo |e investigator |4 oth | |
700 | 1 | |a Blanco-Schweizer, Pablo |e investigator |4 oth | |
700 | 1 | |a Aldecoa, César |e investigator |4 oth | |
700 | 1 | |a Rico-Feijoo, Jesús |e investigator |4 oth | |
700 | 1 | |a Pérez, Alba |e investigator |4 oth | |
700 | 1 | |a Martín-Alfonso, Silvia |e investigator |4 oth | |
700 | 1 | |a Domínguez, Ana M |e investigator |4 oth | |
700 | 1 | |a Díaz-Domínguez, Francisco J |e investigator |4 oth | |
700 | 1 | |a González-Luengo, Raúl I |e investigator |4 oth | |
700 | 1 | |a Carriedo, Demetrio |e investigator |4 oth | |
700 | 1 | |a Soro, Marina |e investigator |4 oth | |
700 | 1 | |a Belda, Javier |e investigator |4 oth | |
700 | 1 | |a Gutiérrez, Andrea |e investigator |4 oth | |
700 | 1 | |a Aguilar, Gerardo |e investigator |4 oth | |
700 | 1 | |a Ferrando, Carlos |e investigator |4 oth | |
700 | 1 | |a Civantos, Belén |e investigator |4 oth | |
700 | 1 | |a Hernández, Mónica |e investigator |4 oth | |
700 | 1 | |a Andaluz, David |e investigator |4 oth | |
700 | 1 | |a Nogales, Leonor |e investigator |4 oth | |
700 | 1 | |a Parrilla, Dácil |e investigator |4 oth | |
700 | 1 | |a Peinado, Eduardo |e investigator |4 oth | |
700 | 1 | |a Pérez-Méndez, Lina |e investigator |4 oth | |
700 | 1 | |a González-Higueras, Elena |e investigator |4 oth | |
700 | 1 | |a Vidal, Anxela |e investigator |4 oth | |
700 | 1 | |a Pérez, César |e investigator |4 oth | |
700 | 1 | |a Kacmarek, Robert M |e investigator |4 oth | |
773 | 0 | 8 | |i Enthalten in |t Critical care medicine |d 1973 |g 51(2023), 12 vom: 01. Dez., Seite 1638-1649 |w (DE-627)NLM000002631 |x 1530-0293 |7 nnns |
773 | 1 | 8 | |g volume:51 |g year:2023 |g number:12 |g day:01 |g month:12 |g pages:1638-1649 |
856 | 4 | 0 | |u http://dx.doi.org/10.1097/CCM.0000000000006030 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 51 |j 2023 |e 12 |b 01 |c 12 |h 1638-1649 |