Literature DB >> 35554875

External validation of a deep-learning model to predict severe acute kidney injury based on urine output changes in critically ill patients.

Francesca Alfieri1, Andrea Ancona1, Giovanni Tripepi2, Vincenzo Randazzo3, Annunziata Paviglianiti3, Eros Pasero3, Luigi Vecchi4, Cristina Politi2, Valentina Cauda5, Riccardo Maria Fagugli6.   

Abstract

OBJECTIVES: The purpose of this study was to externally validate algorithms (previously developed and trained in two United States populations) aimed at early detection of severe oliguric AKI (stage 2/3 KDIGO) in intensive care units patients.
METHODS: The independent cohort was composed of 10'596 patients from the university hospital ICU of Amsterdam (the "AmsterdamUMC database") admitted to their intensive care units. In this cohort, we analysed the accuracy of algorithms based on logistic regression and deep learning methods. The accuracy of investigated algorithms had previously been tested with electronic intensive care unit (eICU) and MIMIC-III patients.
RESULTS: The deep learning model had an area under the ROC curve (AUC) of 0,907 (± 0,007SE) with a sensitivity and specificity of 80% and 89%, respectively, for identifying oliguric AKI episodes. Logistic regression models had an AUC of 0,877 (± 0,005SE) with a sensitivity and specificity of 80% and 81%, respectively. These results were comparable to those obtained in the two US populations upon which the algorithms were previously developed and trained.
CONCLUSION: External validation on the European sample confirmed the accuracy of the algorithms, previously investigated in the US population. The models show high accuracy in both the European and the American databases even though the two cohorts differ in a range of demographic and clinical characteristics, further underlining the validity and the generalizability of the two analytical approaches.
© 2022. The Author(s).

Entities:  

Keywords:  Acute kidney injury; Artificial intelligence; KDIGO; eAlert

Mesh:

Year:  2022        PMID: 35554875      PMCID: PMC9585008          DOI: 10.1007/s40620-022-01335-8

Source DB:  PubMed          Journal:  J Nephrol        ISSN: 1121-8428            Impact factor:   4.393


  19 in total

Review 1.  International Society of Nephrology's 0by25 initiative for acute kidney injury (zero preventable deaths by 2025): a human rights case for nephrology.

Authors:  Ravindra L Mehta; Jorge Cerdá; Emmanuel A Burdmann; Marcello Tonelli; Guillermo García-García; Vivekanand Jha; Paweena Susantitaphong; Michael Rocco; Raymond Vanholder; Mehmet Sukru Sever; Dinna Cruz; Bertrand Jaber; Norbert H Lameire; Raúl Lombardi; Andrew Lewington; John Feehally; Fredric Finkelstein; Nathan Levin; Neesh Pannu; Bernadette Thomas; Eliah Aronoff-Spencer; Giuseppe Remuzzi
Journal:  Lancet       Date:  2015-03-13       Impact factor: 79.321

2.  AKIpredictor, an online prognostic calculator for acute kidney injury in adult critically ill patients: development, validation and comparison to serum neutrophil gelatinase-associated lipocalin.

Authors:  Marine Flechet; Fabian Güiza; Miet Schetz; Pieter Wouters; Ilse Vanhorebeek; Inge Derese; Jan Gunst; Isabel Spriet; Michaël Casaer; Greet Van den Berghe; Geert Meyfroidt
Journal:  Intensive Care Med       Date:  2017-01-27       Impact factor: 17.440

3.  Oliguria is an early predictor of higher mortality in critically ill patients.

Authors:  Etienne Macedo; Rakesh Malhotra; Josée Bouchard; Susan K Wynn; Ravindra L Mehta
Journal:  Kidney Int       Date:  2011-06-29       Impact factor: 10.612

4.  Furosemide stress test as a predictive marker of acute kidney injury progression or renal replacement therapy: a systemic review and meta-analysis.

Authors:  Jia-Jin Chen; Chih-Hsiang Chang; Yen-Ta Huang; George Kuo
Journal:  Crit Care       Date:  2020-05-07       Impact factor: 9.097

5.  Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care.

Authors:  Zhongheng Zhang; Kwok M Ho; Yucai Hong
Journal:  Crit Care       Date:  2019-04-08       Impact factor: 9.097

Review 6.  Role of the Furosemide Stress Test in Renal Injury Prognosis.

Authors:  Armando Coca; Carmen Aller; Jimmy Reinaldo Sánchez; Ana Lucía Valencia; Elena Bustamante-Munguira; Juan Bustamante-Munguira
Journal:  Int J Mol Sci       Date:  2020-04-27       Impact factor: 5.923

7.  The urine output definition of acute kidney injury is too liberal.

Authors:  Azrina Md Ralib; John W Pickering; Geoffrey M Shaw; Zoltán H Endre
Journal:  Crit Care       Date:  2013-06-20       Impact factor: 9.097

8.  The eICU Collaborative Research Database, a freely available multi-center database for critical care research.

Authors:  Tom J Pollard; Alistair E W Johnson; Jesse D Raffa; Leo A Celi; Roger G Mark; Omar Badawi
Journal:  Sci Data       Date:  2018-09-11       Impact factor: 6.444

9.  Definition of hourly urine output influences reported incidence and staging of acute kidney injury.

Authors:  Jennifer C Allen; David S Gardner; Henry Skinner; Daniel Harvey; Andrew Sharman; Mark A J Devonald
Journal:  BMC Nephrol       Date:  2020-01-15       Impact factor: 2.388

10.  A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients.

Authors:  Francesca Alfieri; Andrea Ancona; Giovanni Tripepi; Dario Crosetto; Vincenzo Randazzo; Annunziata Paviglianiti; Eros Pasero; Luigi Vecchi; Valentina Cauda; Riccardo Maria Fagugli
Journal:  J Nephrol       Date:  2021-04-26       Impact factor: 3.902

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.