Lung Ultrasound Score as a Predictor of Mortality in Patients With COVID-19.

Background: Lung injury is a common condition among hospitalized patients with coronavirus disease 2019 (COVID-19). However, whether lung ultrasound (LUS) score predicts all-cause mortality in patients with COVID-19 is unknown. The aim of the present study was to explore the predictive value of lung ultrasound score for mortality in patients with COVID-19. Methods: Patients with COVID-19 who underwent lung ultrasound were prospectively enrolled from three hospitals in Wuhan, China between February 2020 and March 2020. Demographic, clinical, and laboratory data were collected from digital patient records. Lung ultrasound scores were analyzed offline by two observers. Primary outcome was in-hospital mortality. Results: Of the 402 patients, 318 (79.1%) had abnormal lung ultrasound. Compared with survivors (n = 360), non-survivors (n = 42) presented with more B2 lines, pleural line abnormalities, pulmonary consolidation, and pleural effusion (all p < 0.05). Moreover, non-survivors had higher global and anterolateral lung ultrasound score than survivors. In the receiver operating characteristic analysis, areas under the curve were 0.936 and 0.913 for global and anterolateral lung ultrasound score, respectively. A cutoff value of 15 for global lung ultrasound score had a sensitivity of 92.9% and specificity of 85.3%, and 9 for anterolateral score had a sensitivity of 88.1% and specificity of 83.3% for prediction of death. Kaplan-Meier analysis showed that both global and anterolateral scores were strong predictors of death (both p < 0.001). Multivariate Cox regression analysis showed that global lung ultrasound score was an independent predictor (hazard ratio, 1.08; 95% confidence interval, 1.01-1.16; p = 0.03) of death together with age, male sex, C-reactive protein, and creatine kinase-myocardial band. Conclusion: Lung ultrasound score as a semiquantitative tool can be easily measured by bedside lung ultrasound. It is a powerful predictor of in-hospital mortality and may play a crucial role in risk stratification of patients with COVID-19.

Modality alignment contrastive learning for severity assessment of COVID-19 from lung ultrasound and clinical information.

The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19. In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data. We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.

Prognostic value of bedside lung ultrasound score in patients with COVID-19.

BACKGROUND: Bedside lung ultrasound (LUS) has emerged as a useful and non-invasive tool to detect lung involvement and monitor changes in patients with coronavirus disease 2019 (COVID-19). However, the clinical significance of the LUS score in patients with COVID-19 remains unknown. We aimed to investigate the prognostic value of the LUS score in patients with COVID-19. METHOD: The LUS protocol consisted of 12 scanning zones and was performed in 280 consecutive patients with COVID-19. The LUS score based on B-lines, lung consolidation and pleural line abnormalities was evaluated. RESULTS: The median time from admission to LUS examinations was 7 days (interquartile range [IQR] 3-10). Patients in the highest LUS score group were more likely to have a lower lymphocyte percentage (LYM%); higher levels of D-dimer, C-reactive protein, hypersensitive troponin I and creatine kinase muscle-brain; more invasive mechanical ventilation therapy; higher incidence of ARDS; and higher mortality than patients in the lowest LUS score group. After a median follow-up of 14 days [IQR, 10-20 days], 37 patients developed ARDS, and 13 died. Patients with adverse outcomes presented a higher rate of bilateral involvement; more involved zones and B-lines, pleural line abnormalities and consolidation; and a higher LUS score than event-free survivors. The Cox models adding the LUS score as a continuous variable (hazard ratio [HR]: 1.05, 95% confidence intervals [CI] 1.02 ~ 1.08; P < 0.001; Akaike information criterion [AIC] = 272; C-index = 0.903) or as a categorical variable (HR 10.76, 95% CI 2.75 ~ 42.05; P = 0.001; AIC = 272; C-index = 0.902) were found to predict poor outcomes more accurately than the basic model (AIC = 286; C-index = 0.866). An LUS score cut-off > 12 predicted adverse outcomes with a specificity and sensitivity of 90.5% and 91.9%, respectively. CONCLUSIONS: The LUS score devised by our group performs well at predicting adverse outcomes in patients with COVID-19 and is important for risk stratification in COVID-19 patients.