Cargando…

Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features

The emergence of the COVID-19 pandemic over a relatively brief interval illustrates the need for rapid data-driven approaches to facilitate clinical decision making. We examined a machine learning process to predict inpatient mortality among COVID-19 patients using clinical and chest radiographic da...

Descripción completa

Detalles Bibliográficos
Autores principales: Nguyen, Xuan V., Dikici, Engin, Candemir, Sema, Ball, Robyn L., Prevedello, Luciano M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9326627/
https://www.ncbi.nlm.nih.gov/pubmed/35894016
http://dx.doi.org/10.3390/tomography8040151
_version_ 1784757331481853952
author Nguyen, Xuan V.
Dikici, Engin
Candemir, Sema
Ball, Robyn L.
Prevedello, Luciano M.
author_facet Nguyen, Xuan V.
Dikici, Engin
Candemir, Sema
Ball, Robyn L.
Prevedello, Luciano M.
author_sort Nguyen, Xuan V.
collection PubMed
description The emergence of the COVID-19 pandemic over a relatively brief interval illustrates the need for rapid data-driven approaches to facilitate clinical decision making. We examined a machine learning process to predict inpatient mortality among COVID-19 patients using clinical and chest radiographic data. Modeling was performed with a de-identified dataset of encounters prior to widespread vaccine availability. Non-imaging predictors included demographics, pre-admission clinical history, and past medical history variables. Imaging features were extracted from chest radiographs by applying a deep convolutional neural network with transfer learning. A multi-layer perceptron combining 64 deep learning features from chest radiographs with 98 patient clinical features was trained to predict mortality. The Local Interpretable Model-Agnostic Explanations (LIME) method was used to explain model predictions. Non-imaging data alone predicted mortality with an ROC-AUC of 0.87 ± 0.03 (mean ± SD), while the addition of imaging data improved prediction slightly (ROC-AUC: 0.91 ± 0.02). The application of LIME to the combined imaging and clinical model found HbA1c values to contribute the most to model prediction (17.1 ± 1.7%), while imaging contributed 8.8 ± 2.8%. Age, gender, and BMI contributed 8.7%, 8.2%, and 7.1%, respectively. Our findings demonstrate a viable explainable AI approach to quantify the contributions of imaging and clinical data to COVID mortality predictions.
format Online
Article
Text
id pubmed-9326627
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93266272022-07-28 Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features Nguyen, Xuan V. Dikici, Engin Candemir, Sema Ball, Robyn L. Prevedello, Luciano M. Tomography Article The emergence of the COVID-19 pandemic over a relatively brief interval illustrates the need for rapid data-driven approaches to facilitate clinical decision making. We examined a machine learning process to predict inpatient mortality among COVID-19 patients using clinical and chest radiographic data. Modeling was performed with a de-identified dataset of encounters prior to widespread vaccine availability. Non-imaging predictors included demographics, pre-admission clinical history, and past medical history variables. Imaging features were extracted from chest radiographs by applying a deep convolutional neural network with transfer learning. A multi-layer perceptron combining 64 deep learning features from chest radiographs with 98 patient clinical features was trained to predict mortality. The Local Interpretable Model-Agnostic Explanations (LIME) method was used to explain model predictions. Non-imaging data alone predicted mortality with an ROC-AUC of 0.87 ± 0.03 (mean ± SD), while the addition of imaging data improved prediction slightly (ROC-AUC: 0.91 ± 0.02). The application of LIME to the combined imaging and clinical model found HbA1c values to contribute the most to model prediction (17.1 ± 1.7%), while imaging contributed 8.8 ± 2.8%. Age, gender, and BMI contributed 8.7%, 8.2%, and 7.1%, respectively. Our findings demonstrate a viable explainable AI approach to quantify the contributions of imaging and clinical data to COVID mortality predictions. MDPI 2022-07-13 /pmc/articles/PMC9326627/ /pubmed/35894016 http://dx.doi.org/10.3390/tomography8040151 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Nguyen, Xuan V.
Dikici, Engin
Candemir, Sema
Ball, Robyn L.
Prevedello, Luciano M.
Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title_full Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title_fullStr Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title_full_unstemmed Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title_short Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features
title_sort mortality prediction analysis among covid-19 inpatients using clinical variables and deep learning chest radiography imaging features
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9326627/
https://www.ncbi.nlm.nih.gov/pubmed/35894016
http://dx.doi.org/10.3390/tomography8040151
work_keys_str_mv AT nguyenxuanv mortalitypredictionanalysisamongcovid19inpatientsusingclinicalvariablesanddeeplearningchestradiographyimagingfeatures
AT dikiciengin mortalitypredictionanalysisamongcovid19inpatientsusingclinicalvariablesanddeeplearningchestradiographyimagingfeatures
AT candemirsema mortalitypredictionanalysisamongcovid19inpatientsusingclinicalvariablesanddeeplearningchestradiographyimagingfeatures
AT ballrobynl mortalitypredictionanalysisamongcovid19inpatientsusingclinicalvariablesanddeeplearningchestradiographyimagingfeatures
AT prevedellolucianom mortalitypredictionanalysisamongcovid19inpatientsusingclinicalvariablesanddeeplearningchestradiographyimagingfeatures