Tri-light Warning System for Hospitalized COVID-19 Patients]{A Tri-light Warning System for Hospitalized COVID-19 Patients: Credibility-based Risk Stratification under Data Shift (preprint)

Early warning of the novel coronavirus pneumonia (COVID-19) during the evolving pandemic waves is crucial for the timely treatment of patients and optimization of medical resource allocation. However, prior AI-based models often lack the reliability and performance validation under data distribution drifts, and are therefore problematic to be reliably utilized in real-world clinical practice. To address this challenge, we developed a tri-light warning system based on conformal prediction for rapidly stratification of COVID-19 inpatients. This system can automatically extract radiomic features from CT images and integrate clinical record information to output a prediction probability, as well as a credibility of each prediction. This system classifies patients in the general ward into red label (high risk) indicating a possible admission to ICU care, yellow label (uncertain risk) indicating closer monitoring, and green label (low risk) indicating a stable condition. The subsequent health policies can be further designed based on this system according to the specific needs of different hospitals. Extensive experiment from a multi-center cohort (n= 8,721) shows that our method is applicable to both the original strain and the variant strains of COVID-19. Given the rapid mutation rate of COVID-19, the proposed system demonstrates its potential to identify epidemiological risks early to improve patient stratification performance under data shift.

CT-based Rapid Triage of COVID-19 Patients: Risk Prediction and Progression Estimation of ICU Admission, Mechanical Ventilation, and Death of Hospitalized Patients (preprint)

The wave of COVID-19 continues to overwhelm the medical resources, especially the stressed intensive care unit (ICU) capacity and the shortage of mechanical ventilation (MV). Here we performed CT-based analysis combined with electronic health records and clinical laboratory results on Cohort 1 (n = 1662 from 17 hospitals) with prognostic estimation for the rapid stratification of PCR confirmed COVID-19 patients. These models, validated on Cohort 2 (n = 700) and Cohort 3 (n = 662) constructed from 9 external hospitals, achieved satisfying performance for predicting ICU, MV and death of COVID-19 patients (AUROC 0.916, 0.919 and 0.853), even on events happened two days later after admission (AUROC 0.919, 0.943 and 0.856). Both clinical and image features showed complementary roles in events prediction and provided accurate estimates to the time of progression (p

Correlation Study of Chest CT Features of Severe/Critical type COVID-19 with Early Renal Damage and Clinical Prognosis (preprint)

Background: Among patients with confirmed severe/critical type COVID-19, we found that although the seurm creatinine (Cr) value is in normal range, patients might have occured early renal damage. For severe/critical type COVID-19 patients, whether some chest CT features can be used to predict the early renal damage or clinical prognosis.Methods: 162 patients with severe/critical type COVID-19 were reviewed retrospectively in 13 medical centers from China. According to the level of eGFR, 162 patients were divided into three groups, group A (eGFR < 60 ml/min/1.73m2), group B (60 ml/min/1.73m2 ≤ eGFR < 90 ml/min/1.73m2 group) and group C (eGFR ≥ 90 ml/min/1.73m2). All patients’ baseline clinical characteristics, laboratory data, CT features and clinical outcomes were collected and compared. The eGFR and CT features was assessed using univariate and multivariate Cox regression.Results: Baseline clinical characteristics showed that there were significant differences in age, hypertension, cough and fatigue among groups A, B and C. Laboratory data analysis revealed significant differences between the three groups of leukocyte count, platelet count, C-reactive protein, aspartate aminotransferase, creatine kinase. Chest CT features analysis indicated that crazy-paving pattern has significant statistical difference in groups A and B compared with group C. The eGFR of patients with crazy-paving pattern was significant lower than those without crazy-paving pattern (76.73 ± 30.50 vs. 101.69 ± 18.24 ml/min/1.73m2, p < 0.001), and eGFR (OR = 0.962, 95% CI = 0.940-0.985) was the independent risk factor of crazy-paving pattern. The eGFR (HR = 0.549, 95% CI = 0.331-0.909, p = 0.020) and crazy-paving pattern (HR = 2.996, 95% CI = 1.010-8.714, p = 0.048) were independent risk factors of mortality.Conclusions: In patients with severe/critical type COVID-19, the presence of crazy-paving pattern on chest CT are more likely occured the decline of eGFR and poor clinical prognosis. The crazy-paving pattern appeared could be used as an early warning indicator of renal damage and to guide clinicians to use drugs reasonably.