Development and validation of a machine learning model to predict the use of renal replacement therapy in 14,374 patients with COVID-19
Copyright © 2023 Elsevier Inc. All rights reserved..
PURPOSE: To develop a model to predict the use of renal replacement therapy (RRT) in COVID-19 patients.
MATERIALS AND METHODS: Retrospective analysis of multicenter cohort of intensive care unit (ICU) admissions of Brazil involving COVID-19 critically adult patients, requiring ventilatory support, admitted to 126 Brazilian ICUs, from February 2020 to December 2021 (development) and January to May 2022 (validation). No interventions were performed.
RESULTS: Eight machine learning models' classifications were evaluated. Models were developed using an 80/20 testing/train split ratio and cross-validation. Thirteen candidate predictors were selected using the Recursive Feature Elimination (RFE) algorithm. Discrimination and calibration were assessed. Temporal validation was performed using data from 2022. Of 14,374 COVID-19 patients with initial respiratory support, 1924 (13%) required RRT. RRT patients were older (65 [53-75] vs. 55 [42-68]), had more comorbidities (Charlson's Comorbidity Index 1.0 [0.00-2.00] vs 0.0 [0.00-1.00]), had higher severity (SAPS-3 median: 61 [51-74] vs 48 [41-58]), and had higher in-hospital mortality (71% vs 22%) compared to non-RRT. Risk factors for RRT, such as Creatinine, Glasgow Coma Scale, Urea, Invasive Mechanical Ventilation, Age, Chronic Kidney Disease, Platelets count, Vasopressors, Noninvasive Ventilation, Hypertension, Diabetes, modified frailty index (mFI) and Gender, were identified. The best discrimination and calibration were found in the Random Forest (AUC [95%CI]: 0.78 [0.75-0.81] and Brier's Score: 0.09 [95%CI: 0.08-0.10]). The final model (Random Forest) showed comparable performance in the temporal validation (AUC [95%CI]: 0.79 [0.75-0.84] and Brier's Score, 0.08 [95%CI: 0.08-0.1]).
CONCLUSIONS: An early ML model using easily available clinical and laboratory data accurately predicted the use of RRT in critically ill patients with COVID-19. Our study demonstrates that using ML techniques is feasible to provide early prediction of use of RRT in COVID-19 patients.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:80 |
---|---|
Enthalten in: |
Journal of critical care - 80(2024) vom: 11. Jan., Seite 154480 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
França, Allan R M [VerfasserIn] |
---|
Links: |
---|
Themen: |
Acute kidney injury |
---|
Anmerkungen: |
Date Completed 22.01.2024 Date Revised 22.01.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.jcrc.2023.154480 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM365073989 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM365073989 | ||
003 | DE-627 | ||
005 | 20240122231944.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.jcrc.2023.154480 |2 doi | |
028 | 5 | 2 | |a pubmed24n1267.xml |
035 | |a (DE-627)NLM365073989 | ||
035 | |a (NLM)38016226 | ||
035 | |a (PII)S0883-9441(23)00229-0 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a França, Allan R M |e verfasserin |4 aut | |
245 | 1 | 0 | |a Development and validation of a machine learning model to predict the use of renal replacement therapy in 14,374 patients with COVID-19 |
264 | 1 | |c 2024 | |
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 22.01.2024 | ||
500 | |a Date Revised 22.01.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 Elsevier Inc. All rights reserved. | ||
520 | |a PURPOSE: To develop a model to predict the use of renal replacement therapy (RRT) in COVID-19 patients | ||
520 | |a MATERIALS AND METHODS: Retrospective analysis of multicenter cohort of intensive care unit (ICU) admissions of Brazil involving COVID-19 critically adult patients, requiring ventilatory support, admitted to 126 Brazilian ICUs, from February 2020 to December 2021 (development) and January to May 2022 (validation). No interventions were performed | ||
520 | |a RESULTS: Eight machine learning models' classifications were evaluated. Models were developed using an 80/20 testing/train split ratio and cross-validation. Thirteen candidate predictors were selected using the Recursive Feature Elimination (RFE) algorithm. Discrimination and calibration were assessed. Temporal validation was performed using data from 2022. Of 14,374 COVID-19 patients with initial respiratory support, 1924 (13%) required RRT. RRT patients were older (65 [53-75] vs. 55 [42-68]), had more comorbidities (Charlson's Comorbidity Index 1.0 [0.00-2.00] vs 0.0 [0.00-1.00]), had higher severity (SAPS-3 median: 61 [51-74] vs 48 [41-58]), and had higher in-hospital mortality (71% vs 22%) compared to non-RRT. Risk factors for RRT, such as Creatinine, Glasgow Coma Scale, Urea, Invasive Mechanical Ventilation, Age, Chronic Kidney Disease, Platelets count, Vasopressors, Noninvasive Ventilation, Hypertension, Diabetes, modified frailty index (mFI) and Gender, were identified. The best discrimination and calibration were found in the Random Forest (AUC [95%CI]: 0.78 [0.75-0.81] and Brier's Score: 0.09 [95%CI: 0.08-0.10]). The final model (Random Forest) showed comparable performance in the temporal validation (AUC [95%CI]: 0.79 [0.75-0.84] and Brier's Score, 0.08 [95%CI: 0.08-0.1]) | ||
520 | |a CONCLUSIONS: An early ML model using easily available clinical and laboratory data accurately predicted the use of RRT in critically ill patients with COVID-19. Our study demonstrates that using ML techniques is feasible to provide early prediction of use of RRT in COVID-19 patients | ||
650 | 4 | |a Multicenter Study | |
650 | 4 | |a Journal Article | |
650 | 4 | |a Acute kidney injury | |
650 | 4 | |a COVID-19 | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Outcomes | |
650 | 4 | |a Renal replacement therapy | |
650 | 4 | |a Respiratory failure | |
700 | 1 | |a Rocha, Eduardo |e verfasserin |4 aut | |
700 | 1 | |a Bastos, Leonardo S L |e verfasserin |4 aut | |
700 | 1 | |a Bozza, Fernando A |e verfasserin |4 aut | |
700 | 1 | |a Kurtz, Pedro |e verfasserin |4 aut | |
700 | 1 | |a Maccariello, Elizabeth |e verfasserin |4 aut | |
700 | 1 | |a Lapa E Silva, José Roberto |e verfasserin |4 aut | |
700 | 1 | |a Salluh, Jorge I F |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of critical care |d 1987 |g 80(2024) vom: 11. Jan., Seite 154480 |w (DE-627)NLM074731068 |x 1557-8615 |7 nnns |
773 | 1 | 8 | |g volume:80 |g year:2024 |g day:11 |g month:01 |g pages:154480 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.jcrc.2023.154480 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 80 |j 2024 |b 11 |c 01 |h 154480 |