Next Article in Journal
Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease
Previous Article in Journal
Neurocognitive Mechanisms Underlying Internet/Smartphone Addiction: A Preliminary fMRI Study
 
 
Article

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

1
Laboratory for Augmented Intelligence in Imaging, Department of Radiology, The Ohio State University College of Medicine, Columbus, OH 43210, USA
2
The Jackson Laboratory, Bar Harbor, ME 04609, USA
*
Authors to whom correspondence should be addressed.
Current Affiliation: Department of Computer Engineering, Eskişehir Technical University, Eskişehir 26555, Turkey.
Academic Editor: Benjamin M. Ellingson
Tomography 2022, 8(4), 1791-1803; https://doi.org/10.3390/tomography8040151
Received: 11 May 2022 / Revised: 4 July 2022 / Accepted: 7 July 2022 / Published: 13 July 2022
(This article belongs to the Section Artificial Intelligence in Medical Imaging)
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. View Full-Text
Keywords: COVID; computer-aided diagnosis/prognosis; chest radiographs; multi-modal analysis; transfer learning; machine learning; explainable AI COVID; computer-aided diagnosis/prognosis; chest radiographs; multi-modal analysis; transfer learning; machine learning; explainable AI
Show Figures

Figure 1

MDPI and ACS Style

Nguyen, X.V.; Dikici, E.; Candemir, S.; Ball, R.L.; Prevedello, L.M. Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features. Tomography 2022, 8, 1791-1803. https://doi.org/10.3390/tomography8040151

AMA Style

Nguyen XV, Dikici E, Candemir S, Ball RL, Prevedello LM. Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features. Tomography. 2022; 8(4):1791-1803. https://doi.org/10.3390/tomography8040151

Chicago/Turabian Style

Nguyen, Xuan V., Engin Dikici, Sema Candemir, Robyn L. Ball, and Luciano M. Prevedello. 2022. "Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features" Tomography 8, no. 4: 1791-1803. https://doi.org/10.3390/tomography8040151

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop