Literature DB >> 35869954

Identifying infected patients using semi-supervised and transfer learning.

Fereshteh S Bashiri1, John R Caskey1, Anoop Mayampurath2, Nicole Dussault3, Jay Dumanian3, Sivasubramanium V Bhavani4, Kyle A Carey5, Emily R Gilbert6, Christopher J Winslow7, Nirav S Shah5,7, Dana P Edelson5, Majid Afshar1,2, Matthew M Churpek1,2.   

Abstract

OBJECTIVES: Early identification of infection improves outcomes, but developing models for early identification requires determining infection status with manual chart review, limiting sample size. Therefore, we aimed to compare semi-supervised and transfer learning algorithms with algorithms based solely on manual chart review for identifying infection in hospitalized patients.
MATERIALS AND METHODS: This multicenter retrospective study of admissions to 6 hospitals included "gold-standard" labels of infection from manual chart review and "silver-standard" labels from nonchart-reviewed patients using the Sepsis-3 infection criteria based on antibiotic and culture orders. "Gold-standard" labeled admissions were randomly allocated to training (70%) and testing (30%) datasets. Using patient characteristics, vital signs, and laboratory data from the first 24 hours of admission, we derived deep learning and non-deep learning models using transfer learning and semi-supervised methods. Performance was compared in the gold-standard test set using discrimination and calibration metrics.
RESULTS: The study comprised 432 965 admissions, of which 2724 underwent chart review. In the test set, deep learning and non-deep learning approaches had similar discrimination (area under the receiver operating characteristic curve of 0.82). Semi-supervised and transfer learning approaches did not improve discrimination over models fit using only silver- or gold-standard data. Transfer learning had the best calibration (unreliability index P value: .997, Brier score: 0.173), followed by self-learning gradient boosted machine (P value: .67, Brier score: 0.170). DISCUSSION: Deep learning and non-deep learning models performed similarly for identifying infection, as did models developed using Sepsis-3 and manual chart review labels.
CONCLUSION: In a multicenter study of almost 3000 chart-reviewed patients, semi-supervised and transfer learning models showed similar performance for model discrimination as baseline XGBoost, while transfer learning improved calibration.
© The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  AI in medicine; deep learning; machine learning; sepsis; time-series data analysis

Mesh:

Year:  2022        PMID: 35869954      PMCID: PMC9471712          DOI: 10.1093/jamia/ocac109

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   7.942


  33 in total

1.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

Authors:  Alex Graves; Jürgen Schmidhuber
Journal:  Neural Netw       Date:  2005 Jun-Jul

2.  Early detection of sepsis utilizing deep learning on electronic health record event sequences.

Authors:  Simon Meyer Lauritsen; Mads Ellersgaard Kalør; Emil Lund Kongsgaard; Katrine Meyer Lauritsen; Marianne Johansson Jørgensen; Jeppe Lange; Bo Thiesson
Journal:  Artif Intell Med       Date:  2020-02-19       Impact factor: 5.326

3.  The Development of a Machine Learning Inpatient Acute Kidney Injury Prediction Model.

Authors:  Jay L Koyner; Kyle A Carey; Dana P Edelson; Matthew M Churpek
Journal:  Crit Care Med       Date:  2018-07       Impact factor: 7.598

4.  The value of vital sign trends for detecting clinical deterioration on the wards.

Authors:  Matthew M Churpek; Richa Adhikari; Dana P Edelson
Journal:  Resuscitation       Date:  2016-02-16       Impact factor: 5.262

Review 5.  2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference.

Authors:  Mitchell M Levy; Mitchell P Fink; John C Marshall; Edward Abraham; Derek Angus; Deborah Cook; Jonathan Cohen; Steven M Opal; Jean-Louis Vincent; Graham Ramsay
Journal:  Intensive Care Med       Date:  2003-03-28       Impact factor: 17.440

6.  Incidence and Trends of Sepsis in US Hospitals Using Clinical vs Claims Data, 2009-2014.

Authors:  Chanu Rhee; Raymund Dantes; Lauren Epstein; David J Murphy; Christopher W Seymour; Theodore J Iwashyna; Sameer S Kadri; Derek C Angus; Robert L Danner; Anthony E Fiore; John A Jernigan; Greg S Martin; Edward Septimus; David K Warren; Anita Karcz; Christina Chan; John T Menchaca; Rui Wang; Susan Gruber; Michael Klompas
Journal:  JAMA       Date:  2017-10-03       Impact factor: 56.272

7.  Identifying patients with severe sepsis using administrative claims: patient-level validation of the angus implementation of the international consensus conference definition of severe sepsis.

Authors:  Theodore J Iwashyna; Andrew Odden; Jeffrey Rohde; Catherine Bonham; Latoya Kuhn; Preeti Malani; Lena Chen; Scott Flanders
Journal:  Med Care       Date:  2014-06       Impact factor: 2.983

8.  Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards.

Authors:  Matthew M Churpek; Trevor C Yuen; Christopher Winslow; David O Meltzer; Michael W Kattan; Dana P Edelson
Journal:  Crit Care Med       Date:  2016-02       Impact factor: 7.598

9.  Combining patient visual timelines with deep learning to predict mortality.

Authors:  Anoop Mayampurath; L Nelson Sanchez-Pinto; Kyle A Carey; Laura-Ruth Venable; Matthew Churpek
Journal:  PLoS One       Date:  2019-07-31       Impact factor: 3.240

Review 10.  An approach to antibiotic treatment in patients with sepsis.

Authors:  María Luisa Martínez; Erika P Plata-Menchaca; Juan Carlos Ruiz-Rodríguez; Ricard Ferrer
Journal:  J Thorac Dis       Date:  2020-03       Impact factor: 2.895

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.