3D CT-Inclusive Deep-Learning Model to Predict Mortality, ICU Admittance, and Intubation in COVID-19 Patients

Abstract

Chest CT is a useful initial exam in patients with coronavirus disease 2019 (COVID-19) for assessing lung damage. AI-powered predictive models could be useful to better allocate resources in the midst of the pandemic. Our aim was to build a deep-learning (DL) model for COVID-19 outcome prediction inclusive of 3D chest CT images acquired at hospital admission. This retrospective multicentric study included 1051 patients (mean age 69, SD = 15) who presented to the emergency department of three different institutions between 20th March 2020 and 20th January 2021 with COVID-19 confirmed by real-time reverse transcriptase polymerase chain reaction (RT-PCR). Chest CT at hospital admission were evaluated by a 3D residual neural network algorithm. Training, internal validation, and external validation groups included 608, 153, and 290 patients, respectively. Images, clinical, and laboratory data were fed into different customizations of a dense neural network to choose the best performing architecture for the prediction of mortality, intubation, and intensive care unit (ICU) admission. The AI model tested on CT and clinical features displayed accuracy, sensitivity, specificity, and ROC-AUC, respectively, of 91.7%, 90.5%, 92.4%, and 95% for the prediction of patient’s mortality; 91.3%, 91.5%, 89.8%, and 95% for intubation; and 89.6%, 90.2%, 86.5%, and 94% for ICU admission (internal validation) in the testing cohort. The performance was lower in the validation cohort for mortality (71.7%, 55.6%, 74.8%, 72%), intubation (72.6%, 74.7%, 45.7%, 64%), and ICU admission (74.7%, 77%, 46%, 70%) prediction. The addition of the available laboratory data led to an increase in sensitivity for patient’s mortality (66%) and specificity for intubation and ICU admission (50%, 52%, respectively), while the other metrics maintained similar performance results. We present a deep-learning model to predict mortality, ICU admittance, and intubation in COVID-19 patients. Key Points • 3D CT-based deep learning model predicted the internal validation set with high accuracy, sensibility and specificity (> 90%) mortality, ICU admittance, and intubation in COVID-19 patients. • The model slightly increased prediction results when laboratory data were added to the analysis, despite data imbalance. However, the model accuracy dropped when CT images were not considered in the analysis, implying an important role of CT in predicting outcomes.

Potential diagnostic application of a novel deep learning- based approach for COVID-19

“…Di Napoli et al 68 also conducted a study using 3D convolutional layers to analyze 3D CT volumes of COVID-19 patients. However, their primary goal differs from ours, as their study is centered on predicting outcomes such as mortality, intubation, and ICU admission among COVID-19 patients, rather than identifying COVID-19 cases.…”

A Novel Automatic Algorithm to Support Lung Ultrasound Non-Expert Physicians in Interstitial Pneumonia Evaluation: A Single-Center Study

“…Diagnostic evaluation is the main clinical application for AI, ranging from pathology to imaging [13,14,[17][18][19][20]. Several authors have studied the impact of ultrasound on clinical management and patient outcomes in recent years, in particular since the COVID-19 pandemic [21][22][23].…”

Artificial Intelligence and Interstitial Lung Disease: Diagnosis and Prognosis

“…With the COVID-19 pandemic and given the central role of chest imaging in diagnosis and prognosis, the development of algorithms tackling diffuse parenchymal disease has exploded. Innumerable research groups have delivered remarkable results for the detection, characterisation, and prognosis of COVID-19 pneumonia 51,52 . The pandemic has also spurred data availability and exchange, thus facilitating research in the field.…”

“…Innumerable research groups have delivered remarkable results for the detection, characterisation, and prognosis of COVID-19 pneumonia. 51 , 52 The pandemic has also spurred data availability and exchange, thus facilitating research in the field. In contrast, the investigation of ILDs by means of AI is still a minor area.…”