Artificial intelligence for stepwise diagnosis and monitoring of COVID-19.

BACKGROUND: Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course. METHODS: CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models. RESULTS: A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available. INTERPRETATION: The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization. KEY POINTS: • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.

Early triage of critically ill COVID-19 patients using deep learning.

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

Effect and safety of Chinese herbal medicine granules in patients with severe coronavirus disease 2019 in Wuhan, China: a retrospective, single-center study with propensity score matching.

BACKGROUND: Chinese herbal medicine (CHM) has been used for severe illness caused by coronavirus disease 2019 (COVID-19), but its treatment effects and safety are unclear. PURPOSE: This study reviews the effect and safety of CHM granules in the treatment of patients with severe COVID-19. METHODS: We conducteda single-center, retrospective study on patients with severe COVID-19 in a designated hospital in Wuhan from January 15, 2020 to March 30, 2020. The propensity score matching (PSM) was used to assess the effect and safety of the treatment using CHM granules. The ratio of patients who received treatment with CHM granules combined with usual care and those who received usual care alone was 1:1. The primary outcome was the time to clinical improvement within 28 days, defined as the time taken for the patients' health to show improvement by decline of two categories (from the baseline) on a modified six-category ordinal scale, or to be dischargedfrom the hospital before Day 28. RESULTS: Using PSM, 43 patients (45% male) aged 65.6 (57-70) yearsfrom each group were exactly matched. No significant difference was observed in clinical improvement of patients treated with CHM granules compared with those who received usual (p = 0.851). However, the use of CHM granules reduced the 28-day mortality (p = 0.049) and shortened the duration of fever (4 days vs. 7 days, p = 0.002). The differences in the duration of cough and dyspnea and the difference in lung lesion ratio on computerized tomography scans were not significant.Commonly,patients in the CHM group had an increased D-dimer level (p = 0.036). CONCLUSION: Forpatients with severe COVID-19, CHM granules, combined with usual care, showed no improvement beyond usual care alone. However, the use of CHM granules reduced the 28-day mortality rate and the time to fever alleviation. Nevertheless, CHM granules may be associated with high risk of fibrinolysis.

Erratum to hydrogen/oxygen mixed gas inhalation improves disease severity and dyspnea in patients with Coronavirus disease 2019 in a recent multicenter, open-label clinical trial.

[This corrects the article DOI: 10.21037/jtd-2020-057.].

Effect of Recombinant Human Granulocyte Colony-Stimulating Factor for Patients With Coronavirus Disease 2019 (COVID-19) and Lymphopenia: A Randomized Clinical Trial.

Importance: Lymphopenia is common and correlates with poor clinical outcomes in patients with coronavirus disease 2019 (COVID-19). Objective: To determine whether a therapy that increases peripheral blood leukocyte and lymphocyte cell counts leads to clinical improvement in patients with COVID-19. Design, Setting and Participants: Between February 18 and April 10, 2020, we conducted an open-label, multicenter, randomized clinical trial at 3 participating centers in China. The main eligibility criteria were pneumonia, a blood lymphocyte cell count of 800 per µL (to convert to ×109/L, multiply by 0.001) or lower, and no comorbidities. Severe acute respiratory syndrome coronavirus 2 infection was confirmed with reverse-transcription polymerase chain reaction testing. Exposures: Usual care alone, or usual care plus 3 doses of recombinant human granulocyte colony-stimulating factor (rhG-CSF, 5 µg/kg, subcutaneously at days 0-2). Main Outcomes and Measures: The primary end point was the time from randomization to improvement of at least 1 point on a 7-category disease severity score. Results: Of 200 participants, 112 (56%) were men and the median (interquartile range [IQR]) age was 45 (40-55) years. There was random assignment of 100 patients (50%) to the rhG-CSF group and 100 (50%) to the usual care group. Time to clinical improvement was similar between groups (rhG-CSF group median of 12 days (IQR, 10-16 days) vs usual care group median of 13 days (IQR, 11-17 days); hazard ratio, 1.28; 95% CI, 0.95-1.71; P = .06). For secondary end points, the proportion of patients progressing to acute respiratory distress syndrome, sepsis, or septic shock was lower in the rhG-CSF group (rhG-CSF group, 2% vs usual care group, 15%; difference, -13%; 95%CI, -21.4% to -5.4%). At 21 days, 2 patients (2%) had died in the rhG-CSF group compared with 10 patients (10%) in the usual care group (hazard ratio, 0.19; 95%CI, 0.04-0.88). At day 5, the lymphocyte cell count was higher in the rhG-CSF group (rhG-CSF group median of 1050/µL vs usual care group median of 620/µL; Hodges-Lehmann estimate of the difference in medians, 440; 95% CI, 380-490). Serious adverse events, such as sepsis or septic shock, respiratory failure, and acute respiratory distress syndrome, occurred in 29 patients (14.5%) in the rhG-CSF group and 42 patients (21%) in the usual care group. Conclusion and Relevance: In preliminary findings from a randomized clinical trial, rhG-CSF treatment for patients with COVID-19 with lymphopenia but no comorbidities did not accelerate clinical improvement, but the number of patients developing critical illness or dying may have been reduced. Larger studies that include a broader range of patients with COVID-19 should be conducted. Trial Registration: Chinese Clinical Trial Registry: ChiCTR2000030007.

Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19.

Importance: Early identification of patients with novel coronavirus disease 2019 (COVID-19) who may develop critical illness is of great importance and may aid in delivering proper treatment and optimizing use of resources. Objective: To develop and validate a clinical score at hospital admission for predicting which patients with COVID-19 will develop critical illness based on a nationwide cohort in China. Design, Setting, and Participants: Collaborating with the National Health Commission of China, we established a retrospective cohort of patients with COVID-19 from 575 hospitals in 31 provincial administrative regions as of January 31, 2020. Epidemiological, clinical, laboratory, and imaging variables ascertained at hospital admission were screened using Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression to construct a predictive risk score (COVID-GRAM). The score provides an estimate of the risk that a hospitalized patient with COVID-19 will develop critical illness. Accuracy of the score was measured by the area under the receiver operating characteristic curve (AUC). Data from 4 additional cohorts in China hospitalized with COVID-19 were used to validate the score. Data were analyzed between February 20, 2020 and March 17, 2020. Main Outcomes and Measures: Among patients with COVID-19 admitted to the hospital, critical illness was defined as the composite measure of admission to the intensive care unit, invasive ventilation, or death. Results: The development cohort included 1590 patients. the mean (SD) age of patients in the cohort was 48.9 (15.7) years; 904 (57.3%) were men. The validation cohort included 710 patients with a mean (SD) age of 48.2 (15.2) years, and 382 (53.8%) were men and 172 (24.2%). From 72 potential predictors, 10 variables were independent predictive factors and were included in the risk score: chest radiographic abnormality (OR, 3.39; 95% CI, 2.14-5.38), age (OR, 1.03; 95% CI, 1.01-1.05), hemoptysis (OR, 4.53; 95% CI, 1.36-15.15), dyspnea (OR, 1.88; 95% CI, 1.18-3.01), unconsciousness (OR, 4.71; 95% CI, 1.39-15.98), number of comorbidities (OR, 1.60; 95% CI, 1.27-2.00), cancer history (OR, 4.07; 95% CI, 1.23-13.43), neutrophil-to-lymphocyte ratio (OR, 1.06; 95% CI, 1.02-1.10), lactate dehydrogenase (OR, 1.002; 95% CI, 1.001-1.004) and direct bilirubin (OR, 1.15; 95% CI, 1.06-1.24). The mean AUC in the development cohort was 0.88 (95% CI, 0.85-0.91) and the AUC in the validation cohort was 0.88 (95% CI, 0.84-0.93). The score has been translated into an online risk calculator that is freely available to the public (http://118.126.104.170/). Conclusions and Relevance: In this study, a risk score based on characteristics of COVID-19 patients at the time of admission to the hospital was developed that may help predict a patient's risk of developing critical illness.