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.

Background: Anlotinib has been shown to prolong progression-free survival (PFS) and overall survival (OS) for non-small cell lung cancer (NSCLC). Herein we sought to analyze the effect of anlotinib in managing brain metastases (BM) and its brain-associated toxicities. Methods: The PFS and OS of anlotinib versus placebo in those with and without BM recorded at baseline were calculated and compared respectively. Time to brain progression (TTBP), a direct indicator of intracranial control, was also compared between anlotinib and placebo. All calculations were adjusted for confounding factors, including stage, histology, driver mutation type, and therapy history. Results: A total of 437 patients were included; 97 cases were recorded with BM at baseline. For patients with BM at baseline, anlotinib was associated with longer PFS (hazard ratio [HR], 0.29; 95% confidence interval [CI], 0.15–0.56) and OS (HR, 0.72; 95% CI, 0.42–1.12), presenting similar extent of improvement in those without BM (PFS: HR, 0.33; 95% CI, 0.24–0.45; OS: HR, 0.67; 95% CI, 0.50–0.91). Specifically, the intracranial objective response rate was 14.3% and the disease control rate was 85.7% in patients with BM who were treated with anlotinib. Anlotinib was associated with longer TTBP (HR, 0.11; 95% CI, 0.03–0.41; p = .001) despite all confounders. Additionally, anlotinib was associated with more neural toxicities (18.4% vs. 8.4%) and psychological symptoms (49.3% vs. 35.7%) but not with infarction or cerebral hemorrhage. Conclusion: Anlotinib can benefit patients with advanced NSCLC with BM and is highly potent in the management of intracranial lesions. Its special effect on BM and cerebral tissue merits further investigation. (ClinicalTrials.gov ID: NCT02388919).

Objective: To evaluate the spectrum of comorbidities and its impact on the clinical outcome in patients with coronavirus disease 2019 (COVID-19). Design: Retrospective case studies Setting: 575 hospitals in 31 province/autonomous regions/provincial municipalities across China Participants: 1,590 laboratory-confirmed hospitalized patients. Data were collected from November 21 ^st , 2019 to January 31 ^st , 2020. Main outcomes and measures: Epidemiological and clinical variables (in particular, comorbidities) were extracted from medical charts. The disease severity was categorized based on the American Thoracic Society guidelines for community-acquired pneumonia. The primary endpoint was the composite endpoints, which consisted of the admission to intensive care unit (ICU), or invasive ventilation, or death. The risk of reaching to the composite endpoints was compared among patients with COVID-19 according to the presence and number of comorbidities. Results: Of the 1,590 cases, the mean age was 48.9 years. 686 patients (42.7%) were females. 647 (40.7%) patients were managed inside Hubei province, and 1,334 (83.9%) patients had a contact history of Wuhan city. Severe cases accounted for 16.0% of the study population. 131 (8.2%) patients reached to the composite endpoints. 399 (25.1%) reported having at least one comorbidity. 269 (16.9%), 59 (3.7%), 30 (1.9%), 130 (8.2%), 28 (1.8%), 24 (1.5%), 21 (1.3%), 18 (1.1%) and 3 (0.2%) patients reported having hypertension, cardiovascular diseases, cerebrovascular diseases, diabetes, hepatitis B infections, chronic obstructive pulmonary disease, chronic kidney diseases, malignancy and immunodeficiency, respectively. 130 (8.2%) patients reported having two or more comorbidities. Patients with two or more comorbidities had significantly escalated risks of reaching to the composite endpoint compared with those who had a single comorbidity, and even more so as compared with those without (all P <0.05). After adjusting for age and smoking status, patients with COPD (HR 2.681, 95%CI 1.424-5.048), diabetes (HR 1.59, 95%CI 1.03-2.45), hypertension (HR 1.58, 95%CI 1.07-2.32) and malignancy (HR 3.50, 95%CI 1.60-7.64) were more likely to reach to the composite endpoints than those without. As compared with patients without comorbidity, the HR (95%CI) was 1.79 (95%CI 1.16-2.77) among patients with at least one comorbidity and 2.59 (95%CI 1.61-4.17) among patients with two or more comorbidities. Conclusion: Comorbidities are present in around one fourth of patients with COVID-19 in China, and predispose to poorer clinical outcomes. Highlights: What is already known on this topic: - Since November 2019, the rapid outbreak of coronavirus disease 2019 (COVID-19) has recently become a public health emergency of international concern. There have been 79,331 laboratory-confirmed cases and 2,595 deaths globally as of February 25 ^th , 2020 - Previous studies have demonstrated the association between comorbidities and other severe acute respiratory diseases including SARS and MERS. - No study with a nationwide representative cohort has demonstrated the spectrum of comorbidities and the impact of comorbidities on the clinical outcomes in patients with COVID-19. What this study adds: - In this nationwide study with 1,590 patients with COVID-19, comorbidities were identified in 399 patients. Comorbidities of COVID-19 mainly included hypertension, cardiovascular diseases, cerebrovascular diseases, diabetes, hepatitis B infections, chronic obstructive pulmonary disease, chronic kidney diseases, malignancy and immunodeficiency. - The presence of as well as the number of comorbidities predicted the poor clinical outcomes (admission to intensive care unit, invasive ventilation, or death) of COVID-19. - Comorbidities should be taken into account when estimating the clinical outcomes of patients with COVID-19 on hospital admission.