Abstract
Purpose
As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients’ electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction.
Method
We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction.
Results
For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort.
Conclusion
The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.
【저자키워드】 mechanical ventilation, intensive care unit, lactate dehydrogenase, Computed tomography, ground-glass opacity, oxygen saturation, reverse-transcription polymerase chain reaction, White blood cell, Platelet, hemoglobin, Electronic health records, Generalized linear model, Hounsfield unit, institutional review board, ICUIntensive Care Unit, coronavirus disease of 2019, LDHlactate dehydrogenase, CIconfidence interval, confidence interval, CTComputed Tomography, ESRerythrocyte sedimentation rate, erythrocyte sedimentation rate, AUCarea under the curve, area under the curve, IRBinstitutional review board, GGOground-glass opacity, EHRElectronic health records, COVID-19Coronavirus disease of 2019, TORTotal opacity ratio, Total opacity ratio, CRConsolidation ratio, Consolidation ratio, GLMGeneralized linear model, WBCWhite blood cell, PLTPlatelet, SpO2Oxygen saturation, RT-PCRReverse-transcription polymerase chain reaction, MVMechanical ventilation, GPUGraphics processing unit, Graphics processing unit, HUHounsfield unit, HgbHemoglobin, MODSMultiple Organ Dysfunction Score, Multiple Organ Dysfunction Score, SOFASequential Organ Failure Assessment, Sequential Organ Failure Assessment, hs-CRPHigh-sensitivity C-reactive protein, High-sensitivity C-reactive protein, 【초록키워드】 COVID-19, coronavirus disease, Stratification, Biomarker, Biomarkers, Prognosis, deep learning, severity, risk, Lung infection, Electronic health record, outcomes, Cohort, Patient, death, age, dataset, vital sign, WBC, predictor, prognostic, GLM, consolidation, predict, Analysis, AUC, EHR, confirmed case, Medical resources, SpO2, laboratory data, cohorts, Final, correlation coefficient, Deep Learning Method, regions, 95 % CI, Result, caused, indicated, conducted, applied, 【제목키워드】 Prognosis, Electronic health record, Analysis, COVID-19 patient,