Cargando…

Predicting sepsis using deep learning across international sites: a retrospective development and validation study

BACKGROUND: When sepsis is detected, organ damage may have progressed to irreversible stages, leading to poor prognosis. The use of machine learning for predicting sepsis early has shown promise, however international validations are missing. METHODS: This was a retrospective, observational, multi-c...

Descripción completa

Detalles Bibliográficos
Autores principales: Moor, Michael, Bennett, Nicolas, Plečko, Drago, Horn, Max, Rieck, Bastian, Meinshausen, Nicolai, Bühlmann, Peter, Borgwardt, Karsten
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425671/
https://www.ncbi.nlm.nih.gov/pubmed/37588623
http://dx.doi.org/10.1016/j.eclinm.2023.102124
_version_ 1785089888241057792
author Moor, Michael
Bennett, Nicolas
Plečko, Drago
Horn, Max
Rieck, Bastian
Meinshausen, Nicolai
Bühlmann, Peter
Borgwardt, Karsten
author_facet Moor, Michael
Bennett, Nicolas
Plečko, Drago
Horn, Max
Rieck, Bastian
Meinshausen, Nicolai
Bühlmann, Peter
Borgwardt, Karsten
author_sort Moor, Michael
collection PubMed
description BACKGROUND: When sepsis is detected, organ damage may have progressed to irreversible stages, leading to poor prognosis. The use of machine learning for predicting sepsis early has shown promise, however international validations are missing. METHODS: This was a retrospective, observational, multi-centre cohort study. We developed and externally validated a deep learning system for the prediction of sepsis in the intensive care unit (ICU). Our analysis represents the first international, multi-centre in-ICU cohort study for sepsis prediction using deep learning to our knowledge. Our dataset contains 136,478 unique ICU admissions, representing a refined and harmonised subset of four large ICU databases comprising data collected from ICUs in the US, the Netherlands, and Switzerland between 2001 and 2016. Using the international consensus definition Sepsis-3, we derived hourly-resolved sepsis annotations, amounting to 25,694 (18.8%) patient stays with sepsis. We compared our approach to clinical baselines as well as machine learning baselines and performed an extensive internal and external statistical validation within and across databases, reporting area under the receiver-operating-characteristic curve (AUC). FINDINGS: Averaged over sites, our model was able to predict sepsis with an AUC of 0.846 (95% confidence interval [CI], 0.841–0.852) on a held-out validation cohort internal to each site, and an AUC of 0.761 (95% CI, 0.746–0.770) when validating externally across sites. Given access to a small fine-tuning set (10% per site), the transfer to target sites was improved to an AUC of 0.807 (95% CI, 0.801–0.813). Our model raised 1.4 false alerts per true alert and detected 80% of the septic patients 3.7 h (95% CI, 3.0–4.3) prior to the onset of sepsis, opening a vital window for intervention. INTERPRETATION: By monitoring clinical and laboratory measurements in a retrospective simulation of a real-time prediction scenario, a deep learning system for the detection of sepsis generalised to previously unseen ICU cohorts, internationally. FUNDING: This study was funded by the Personalized Health and Related Technologies (PHRT) strategic focus area of the ETH domain.
format Online
Article
Text
id pubmed-10425671
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-104256712023-08-16 Predicting sepsis using deep learning across international sites: a retrospective development and validation study Moor, Michael Bennett, Nicolas Plečko, Drago Horn, Max Rieck, Bastian Meinshausen, Nicolai Bühlmann, Peter Borgwardt, Karsten eClinicalMedicine Articles BACKGROUND: When sepsis is detected, organ damage may have progressed to irreversible stages, leading to poor prognosis. The use of machine learning for predicting sepsis early has shown promise, however international validations are missing. METHODS: This was a retrospective, observational, multi-centre cohort study. We developed and externally validated a deep learning system for the prediction of sepsis in the intensive care unit (ICU). Our analysis represents the first international, multi-centre in-ICU cohort study for sepsis prediction using deep learning to our knowledge. Our dataset contains 136,478 unique ICU admissions, representing a refined and harmonised subset of four large ICU databases comprising data collected from ICUs in the US, the Netherlands, and Switzerland between 2001 and 2016. Using the international consensus definition Sepsis-3, we derived hourly-resolved sepsis annotations, amounting to 25,694 (18.8%) patient stays with sepsis. We compared our approach to clinical baselines as well as machine learning baselines and performed an extensive internal and external statistical validation within and across databases, reporting area under the receiver-operating-characteristic curve (AUC). FINDINGS: Averaged over sites, our model was able to predict sepsis with an AUC of 0.846 (95% confidence interval [CI], 0.841–0.852) on a held-out validation cohort internal to each site, and an AUC of 0.761 (95% CI, 0.746–0.770) when validating externally across sites. Given access to a small fine-tuning set (10% per site), the transfer to target sites was improved to an AUC of 0.807 (95% CI, 0.801–0.813). Our model raised 1.4 false alerts per true alert and detected 80% of the septic patients 3.7 h (95% CI, 3.0–4.3) prior to the onset of sepsis, opening a vital window for intervention. INTERPRETATION: By monitoring clinical and laboratory measurements in a retrospective simulation of a real-time prediction scenario, a deep learning system for the detection of sepsis generalised to previously unseen ICU cohorts, internationally. FUNDING: This study was funded by the Personalized Health and Related Technologies (PHRT) strategic focus area of the ETH domain. Elsevier 2023-08-11 /pmc/articles/PMC10425671/ /pubmed/37588623 http://dx.doi.org/10.1016/j.eclinm.2023.102124 Text en © 2023 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Articles
Moor, Michael
Bennett, Nicolas
Plečko, Drago
Horn, Max
Rieck, Bastian
Meinshausen, Nicolai
Bühlmann, Peter
Borgwardt, Karsten
Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title_full Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title_fullStr Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title_full_unstemmed Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title_short Predicting sepsis using deep learning across international sites: a retrospective development and validation study
title_sort predicting sepsis using deep learning across international sites: a retrospective development and validation study
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425671/
https://www.ncbi.nlm.nih.gov/pubmed/37588623
http://dx.doi.org/10.1016/j.eclinm.2023.102124
work_keys_str_mv AT moormichael predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT bennettnicolas predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT pleckodrago predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT hornmax predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT rieckbastian predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT meinshausennicolai predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT buhlmannpeter predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy
AT borgwardtkarsten predictingsepsisusingdeeplearningacrossinternationalsitesaretrospectivedevelopmentandvalidationstudy