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.

Thoracic surgery and COVID-19: changes and managements during the pandemic.

BACKGROUND: Several articles have been published about the reorganization of surgical activity during the coronavirus disease 2019 (COVID-19) pandemic but little is known about the operative volume, distribution of cases, or capacity of The Department of Thoracic Surgery to deliver surgical services in the time of COVID-19. METHODS: A retrospective operative logbook review was completed in department of thoracic in a designated COVID-19 hospital. We reviewed and analyzed the operative logbook and discussed our countermeasures during the outbreak. A prediction model was established to discuss the time consuming about delayed surgeries during the pandemic. RESULTS: One thousand two hundred and seventy-five operation records were collected. The thoracic surgeries of this year has decreased (43.4%) during the Wuhan lockdown. From Jan 23rd to Apr 8th in 2020, there were 461 surgeries performed in The Department of Thoracic in our hospital with 0 cases of nosocomial COVID-19 infection. Prediction model showed that it will take 6 weeks to solve the backlog if department can reach the 85% of maximum of operations per week. CONCLUSIONS: An understanding of operative case volume and distribution is essential in facilitating targeted interventions to strengthen surgical capacity in the time of COVID-19. A proper guideline is imperative to ensure access to safe, timely surgical care. By developing a scientific and effective management of hospital, it is possible to ensure optimal surgical safety during this crisis. Regular updates and a further study include multicenter is required. CLINICAL TRIAL REGISTRY NUMBER: ChiCTR2000034346.

Clinical characteristics and outcomes of hospitalised patients with COVID-19 treated in Hubei (epicentre) and outside Hubei (non-epicentre): a nationwide analysis of China.

BACKGROUND: During the outbreak of coronavirus disease 2019 (COVID-19), consistent and considerable differences in disease severity and mortality rate of patients treated in Hubei province compared to those in other parts of China have been observed. We sought to compare the clinical characteristics and outcomes of patients being treated inside and outside Hubei province, and explore the factors underlying these differences. METHODS: Collaborating with the National Health Commission, we established a retrospective cohort to study hospitalised COVID-19 cases in China. Clinical characteristics, the rate of severe events and deaths, and the time to critical illness (invasive ventilation or intensive care unit admission or death) were compared between patients within and outside Hubei. The impact of Wuhan-related exposure (a presumed key factor that drove the severe situation in Hubei, as Wuhan is the epicentre as well the administrative centre of Hubei province) and the duration between symptom onset and admission on prognosis were also determined. RESULTS: At the data cut-off (31 January 2020), 1590 cases from 575 hospitals in 31 provincial administrative regions were collected (core cohort). The overall rate of severe cases and mortality was 16.0% and 3.2%, respectively. Patients in Hubei (predominantly with Wuhan-related exposure, 597 (92.3%) out of 647) were older (mean age 49.7 versus 44.9 years), had more cases with comorbidity (32.9% versus 19.7%), higher symptomatic burden, abnormal radiologic manifestations and, especially, a longer waiting time between symptom onset and admission (5.7 versus 4.5 days) compared with patients outside Hubei. Patients in Hubei (severe event rate 23.0% versus 11.1%, death rate 7.3% versus 0.3%, HR (95% CI) for critical illness 1.59 (1.05-2.41)) have a poorer prognosis compared with patients outside Hubei after adjusting for age and comorbidity. However, among patients outside Hubei, the duration from symptom onset to hospitalisation (mean 4.4 versus 4.7 days) and prognosis (HR (95%) 0.84 (0.40-1.80)) were similar between patients with or without Wuhan-related exposure. In the overall population, the waiting time, but neither treated in Hubei nor Wuhan-related exposure, remained an independent prognostic factor (HR (95%) 1.05 (1.01-1.08)). CONCLUSION: There were more severe cases and poorer outcomes for COVID-19 patients treated in Hubei, which might be attributed to the prolonged duration of symptom onset to hospitalisation in the epicentre. Future studies to determine the reason for delaying hospitalisation are warranted.

Comorbidity and its impact on 1590 patients with COVID-19 in China: a nationwide analysis.

BACKGROUND: The coronavirus disease 2019 (COVID-19) outbreak is evolving rapidly worldwide. OBJECTIVE: To evaluate the risk of serious adverse outcomes in patients with COVID-19 by stratifying the comorbidity status. METHODS: We analysed data from 1590 laboratory confirmed hospitalised patients from 575 hospitals in 31 provinces/autonomous regions/provincial municipalities across mainland China between 11 December 2019 and 31 January 2020. We analysed the composite end-points, which consisted of admission to an intensive care unit, invasive ventilation or death. The risk of reaching the composite end-points was compared according to the presence and number of comorbidities. RESULTS: The mean age was 48.9 years and 686 (42.7%) patients were female. Severe cases accounted for 16.0% of the study population. 131 (8.2%) patients reached the composite end-points. 399 (25.1%) reported having at least one comorbidity. The most prevalent comorbidity was hypertension (16.9%), followed by diabetes (8.2%). 130 (8.2%) patients reported having two or more comorbidities. After adjusting for age and smoking status, COPD (HR (95% CI) 2.681 (1.424-5.048)), diabetes (1.59 (1.03-2.45)), hypertension (1.58 (1.07-2.32)) and malignancy (3.50 (1.60-7.64)) were risk factors of reaching the composite end-points. The hazard ratio (95% CI) was 1.79 (1.16-2.77) among patients with at least one comorbidity and 2.59 (1.61-4.17) among patients with two or more comorbidities. CONCLUSION: Among laboratory confirmed cases of COVID-19, patients with any comorbidity yielded poorer clinical outcomes than those without. A greater number of comorbidities also correlated with poorer clinical outcomes.