Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance

Abstract Acute kidney injury (AKI) is a major complication after cardiothoracic surgery. Early prediction of AKI could prompt preventive measures, but is challenging in the clinical routine. One important reason is that the amount of postoperative data is too massive and too high-dimensional to be e...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nina Rank, Boris Pfahringer, Jörg Kempfert, Christof Stamm, Titus Kühne, Felix Schoenrath, Volkmar Falk, Carsten Eickhoff, Alexander Meyer
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/f075b261cadc4b909376e8bceccb2f25
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f075b261cadc4b909376e8bceccb2f25
record_format	dspace
spelling	oai:doaj.org-article:f075b261cadc4b909376e8bceccb2f252021-12-02T16:23:11ZDeep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance10.1038/s41746-020-00346-82398-6352https://doaj.org/article/f075b261cadc4b909376e8bceccb2f252020-10-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-00346-8https://doaj.org/toc/2398-6352Abstract Acute kidney injury (AKI) is a major complication after cardiothoracic surgery. Early prediction of AKI could prompt preventive measures, but is challenging in the clinical routine. One important reason is that the amount of postoperative data is too massive and too high-dimensional to be effectively processed by the human operator. We therefore sought to develop a deep-learning-based algorithm that is able to predict postoperative AKI prior to the onset of symptoms and complications. Based on 96 routinely collected parameters we built a recurrent neural network (RNN) for real-time prediction of AKI after cardiothoracic surgery. From the data of 15,564 admissions we constructed a balanced training set (2224 admissions) for the development of the RNN. The model was then evaluated on an independent test set (350 admissions) and yielded an area under curve (AUC) (95% confidence interval) of 0.893 (0.862–0.924). We compared the performance of our model against that of experienced clinicians. The RNN significantly outperformed clinicians (AUC = 0.901 vs. 0.745, p < 0.001) and was overall well calibrated. This was not the case for the physicians, who systematically underestimated the risk (p < 0.001). In conclusion, the RNN was superior to physicians in the prediction of AKI after cardiothoracic surgery. It could potentially be integrated into hospitals’ electronic health records for real-time patient monitoring and may help to detect early AKI and hence modify the treatment in perioperative care.Nina RankBoris PfahringerJörg KempfertChristof StammTitus KühneFelix SchoenrathVolkmar FalkCarsten EickhoffAlexander MeyerNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-12 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Nina Rank Boris Pfahringer Jörg Kempfert Christof Stamm Titus Kühne Felix Schoenrath Volkmar Falk Carsten Eickhoff Alexander Meyer Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
description	Abstract Acute kidney injury (AKI) is a major complication after cardiothoracic surgery. Early prediction of AKI could prompt preventive measures, but is challenging in the clinical routine. One important reason is that the amount of postoperative data is too massive and too high-dimensional to be effectively processed by the human operator. We therefore sought to develop a deep-learning-based algorithm that is able to predict postoperative AKI prior to the onset of symptoms and complications. Based on 96 routinely collected parameters we built a recurrent neural network (RNN) for real-time prediction of AKI after cardiothoracic surgery. From the data of 15,564 admissions we constructed a balanced training set (2224 admissions) for the development of the RNN. The model was then evaluated on an independent test set (350 admissions) and yielded an area under curve (AUC) (95% confidence interval) of 0.893 (0.862–0.924). We compared the performance of our model against that of experienced clinicians. The RNN significantly outperformed clinicians (AUC = 0.901 vs. 0.745, p < 0.001) and was overall well calibrated. This was not the case for the physicians, who systematically underestimated the risk (p < 0.001). In conclusion, the RNN was superior to physicians in the prediction of AKI after cardiothoracic surgery. It could potentially be integrated into hospitals’ electronic health records for real-time patient monitoring and may help to detect early AKI and hence modify the treatment in perioperative care.
format	article
author	Nina Rank Boris Pfahringer Jörg Kempfert Christof Stamm Titus Kühne Felix Schoenrath Volkmar Falk Carsten Eickhoff Alexander Meyer
author_facet	Nina Rank Boris Pfahringer Jörg Kempfert Christof Stamm Titus Kühne Felix Schoenrath Volkmar Falk Carsten Eickhoff Alexander Meyer
author_sort	Nina Rank
title	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
title_short	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
title_full	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
title_fullStr	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
title_full_unstemmed	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
title_sort	deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/f075b261cadc4b909376e8bceccb2f25
work_keys_str_mv	AT ninarank deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT borispfahringer deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT jorgkempfert deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT christofstamm deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT tituskuhne deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT felixschoenrath deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT volkmarfalk deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT carsteneickhoff deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance AT alexandermeyer deeplearningbasedrealtimepredictionofacutekidneyinjuryoutperformshumanpredictiveperformance
_version_	1718384207211790336

Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance

Ejemplares similares