ABSTRACT
During the highly infectious pandemic of coronavirus disease 2019 (COVID-19), artificial intelligence (AI) has provided support in addressing challenges and accelerating achievements in controlling this public health crisis. It has been applied in fields varying from outbreak forecasting to patient management and drug/vaccine development. In this paper, we specifically review the current status of AI-based approaches for patient management. Limitations and challenges still exist, and further needs are highlighted.
ABSTRACT
Background: Accumulating evidence has revealed that coronavirus disease 2019 (COVID-19) patients may be complicated with myocardial injury during hospitalization. However, data regarding persistent cardiac involvement in patients who recovered from COVID-19 are limited. Our goal is to further explore the sustained impact of COVID-19 during follow-up, focusing on the cardiac involvement in the recovered patients. Methods: In this prospective observational follow-up study, we enrolled a total of 40 COVID-19 patients (20 with and 20 without cardiac injury during hospitalization) who were discharged from Zhongnan Hospital of Wuhan University for more than 6 months, and 27 patients (13 with and 14 without cardiac injury during hospitalization) were finally included in the analysis. Clinical information including self-reported symptoms, medications, laboratory findings, Short Form 36-item scores, 6-min walk test, clinical events, electrocardiogram assessment, echocardiography measurement, and cardiac magnetic resonance imaging was collected and analyzed. Results: Among 27 patients finally included, none of patients reported any obvious cardiopulmonary symptoms at the 6-month follow-up. There were no statistically significant differences in terms of the quality of life and exercise capacity between the patients with and without cardiac injury. No significant abnormalities were detected in electrocardiogram manifestations in both groups, except for nonspecific ST-T changes, premature beats, sinus tachycardia/bradycardia, PR interval prolongation, and bundle-branch block. All patients showed normal cardiac structure and function, without any statistical differences between patients with and without cardiac injury by echocardiography. Compared with patients without cardiac injury, patients with cardiac injury exhibited a significantly higher positive proportion in late gadolinium enhancement sequences [7/13 (53.8%) vs. 1/14 (7.1%), p = 0.013], accompanied by the elevation of circulating ST2 level [median (interquartile range) = 16.6 (12.1, 22.5) vs. 12.5 (9.5, 16.7); p = 0.044]. Patients with cardiac injury presented higher levels of aspartate aminotransferase, creatinine, high-sensitivity troponin I, lactate dehydrogenase, and N-terminal pro-B-type natriuretic peptide than those without cardiac injury, although these indexes were within the normal range for all recovered patients at the 6-month follow-up. Among patients with cardiac injury, patients with positive late gadolinium enhancement presented higher cardiac biomarker (high-sensitivity troponin I) and inflammatory factor (high-sensitivity C-reactive protein) on admission than the late gadolinium enhancement-negative subgroup. Conclusions: Our preliminary 6-month follow-up study with a limited number of patients revealed persistent cardiac involvement in 29.6% (8/27) of recovered patients from COVID-19 after discharge. Patients with cardiac injury during hospitalization were more prone to develop cardiac fibrosis during their recovery. Among patients with cardiac injury, those with relatively higher cardiac biomarkers and inflammatory factors on admission appeared more likely to have cardiac involvement in the convalescence phase.
ABSTRACT
PURPOSE: To describe the radiological features of coronavirus disease 19 (COVID-19) and to explore the significant signs that indicate severity of disease. MATERIALS AND METHODS: We collected data retrospectively of 180 cases of COVID-19, from 15 January 2020 to 31 March 2020, from both the Wuhan Zhongnan and Beijing Ditan Hospitals, including 103 cases of mild and 77 cases of severe pneumonia. All patients had their first chest computed tomography scan within five days of symptom onset. The dandelion sign was defined by a focal ground glass opacity (GGO) with a central thickening of the airway wall, and the focal crazy paving sign was defined by a focal GGO with thickening of the interlobular septa. RESULTS: Consolidation presented in only 4.9% (5/103) of the mild pneumonia cases, which was significantly lower than that in severe pneumonia cases (70.1% 54/77), p < .001). Multifocal distribution and pure GGOs were observed more frequently in severe cases of pneumonia (p < .05). The dandelion sign was present in 86.4% (89/103) of the mild pneumonia cases, significantly more frequent than those with severe pneumonia (13.0% [10/77], p < .001). The focal crazy paving sign presented in 65.0% (67/103) of the mild pneumonia cases and was significantly more frequent than in severe cases (23.4% [18/77], p < .001). The hospital stay duration of the mild pneumonia group (13.6 ± 7.2 days) was significantly shorter than the severe pneumonia group (26.6 ± 11.7 days, p < .001). CONCLUSIONS: Consolidation, pure GGO and multifocal distribution on a CT scan were associated with severe COVID-19. The dandelion and focal crazy paving signs indicate mild COVID-19.