Artificial intelligence-based CT metrics used in predicting clinical outcome of COVID-19 in young and middle-aged adults.

BACKGROUND: Currently, most researchers mainly analyzed coronavirus disease 2019 (COVID-19) pneumonia visually or qualitatively, probably somewhat time-consuming and not precise enough. PURPOSE: This study aimed to excavate more information, such as differences in distribution, density, and severity of pneumonia lesions between males and females in a specific age group using artificial intelligence (AI)-based computed tomography (CT) metrics. Besides, these metrics were incorporated into a clinical regression model to predict the short-term outcome. MATERIALS AND METHODS: The clinical, laboratory information and a series of HRCT images from 49 patients, aged from 20 to 50 years and confirmed with COVID-19, were collected. The volumes and percentages of infection (POIs) among bilateral lungs and each bronchopulmonary segment were extracted using uAI-Discover-NCP software (version R001). The POI in three HU ranges (i.e., <-300, -300-49, and ≥50 HU representing ground-glass opacity [GGO], mixed opacity, and consolidation) were also extracted. Hospital stay was predicted with several POI after adjusting days from illness onset to admission, leucocytes, lymphocytes, C-reactive protein, age, and gender using a multiple linear regression model. A total of 91 patients aged 20-50 from public database were selected. RESULTS: Right lower lobes had the highest POI, followed by left lower lobes, right upper lobes, middle lobes, and left upper lobes. The distributions in lung lobes and segments were different between the sexes. Men had a higher total POI and GGO of the lungs, but less consolidation than women in initial CT (all p < 0.05). The total POI, percentage of consolidation on initial CT, and changed POI were positively correlated with hospital stay in the model. A total of 91 patients aged 20-50 years in the public database were selected, and AI segmentation was performed. The POI of the lower lobes was obviously higher than that in the upper lobes; the POI of each segment of the right upper lobe in the males was higher than that in the females, which was consistent with the result of the 49 patients previously. CONCLUSION: Both men and women had characteristic distributions in lung lobes and bronchopulmonary segments. AI-based CT quantitative metrics can provide more precise information regarding lesion distribution and severity to predict clinical outcome.

Effectiveness of Contact Tracing, Mask Wearing and Prompt Testing on Suppressing COVID-19 Resurgences in Megacities: An Individual-Based Modelling Study (preprint)

Background: Secondary waves of COVID-19 loom in many countries as strict physical distancing measures have been lifted. Since megacities have been hardest hit by the disease, science-based guidelines of non-pharmaceutical interventions are still in need for post-epidemic management in ‘business as usual’ cities before vaccines are widely available. This study aims to investigate the combined effects of contact tracing, mask wearing, and prompt testing on minimizing the risk of next COVID-19 waves in megacities. Methods: We integrated 5·8 million mobile phone users’ trajectory records into a spatially explicit individual-based model for simulating COVID-19 spread among 4·5 million households, 230 thousand workplaces (including schools), and other public places in 0.6 million buildings in Shenzhen city, China, which has been gradually reopened. Government interventions were incorporated to reconstruct the actual course of the 1st wave epidemic. After validated by empirical data, the model was used to assess the probability of resurgences if sporadic cases occurred in a fully reopened city under different scenarios of contact tracing settings (household, work, school, and public place), mask use, and test-seeking behavior along with receding public vigilance. Findings: Our model well predicted the spatiotemporal dynamics of the 1st wave epidemic in Shenzhen, by age distribution of symptomatic cases, and household secondary attack rate (11·02%). After city reopens, our results show a 50% chance or less of suppressing disease resurgence if not implementing contact tracing. Tracing household contacts, in combination with mandatory (100% compliance) mask use and prompt testing could limit the probability of next outbreak under 5%. If contact tracing can be expanded to work/class group members, the public compliance of masking and testing can be relaxed to 80% and 40%, respectively, to achieve the same suppression target. Further scaled-up contact tracing that includes casual contacts can suppress resurgences with a low compliance to mask use (40%) and prompt testing (20%-40%). Interpretation: To minimize the risk of resurgence in a reopened city, the local government is expected to spare no efforts to trace close contacts in household, workplace and school for a confirmed case. The authorities should promote mask use in a public space and encourage people with COVID-19-like symptoms to testing within two days after illness onset, along with measures such as sick leave compensation and extensive temperature screening in public places.Funding Statement: National Scientific Foundation of China, R & D project of key areas in Guangdong Province, Bill & Melinda Gates Foundation, Joint Engineering Research Center for Health Big Data Intelligent Analysis TechnologyDeclaration of Interests: We declare no competing interests.

Effectiveness of Contact Tracing, Mask Wearing and Prompt Testing on Suppressing COVID-19 Resurgences in Megacities: An Individual-Based Modelling Study (preprint)

Background: As COVID-19 resurges in many countries, science-based guidelines of non-pharmaceutical interventions are still in need for post-epidemic management in ‘business as usual’ cities before vaccines are widely available. This study aims to investigate the combined effects of contact tracing, mask wearing, and prompt testing on minimizing the risk of next COVID-19 waves caused by sporadic outbreaks in megacities.Methods: We integrated large-scale mobile phone tracking data into a spatially explicit individual-based model to simulate COVID-19 spread among 11.2 million individuals in Shenzhen City, China. Government interventions were incorporated to reconstruct the actual course of the 1st wave epidemic. After validated by empirical data, the model was used to assess the probability of resurgences if sporadic cases occurred in a fully reopened city under different scenarios of contact tracing settings (household, work, school, and public place), mask use, and test-seeking behavior along with receding public vigilance.Results: Our model well predicted the spatiotemporal dynamics of the 1st wave epidemic in Shenzhen, by age distribution of symptomatic cases, and household secondary attack rate (11·02%). After city reopens, our results show a 50% chance or less of suppressing disease resurgence if not implementing contact tracing. Tracing household contacts, in combination with mandatory (100% compliance) mask use and prompt testing could limit the probability of next outbreak under 5%. If contact tracing can be expanded to work/class group members, the public compliance of masking and testing can be relaxed to 80% and 40%, respectively, to achieve the same suppression target. Further scaled-up contact tracing that includes casual contacts can suppress resurgences with a low compliance to mask use (40%) and prompt testing (20%-40%). Conclusions: To minimize the risk of resurgence in a reopened city, the local government is expected to spare no efforts to trace close contacts in household, workplace and school for a confirmed case. The authorities should promote mask use in a public space and encourage people with COVID-19-like symptoms to testing within two days after illness onset, along with measures such as sick leave compensation and extensive temperature screening in public places.

Artificial intelligence-based CT metrics in relation with clinical outcome of COVID-19 in young and middle-aged adults (preprint)

Purposes: Currently, most researchers mainly analyzed COVID-19 pneumonia visually or qualitatively, probably somewhat time-consuming and not precise enough. This study aimed to excavate more information, such as differences in distribution, density, and severity of pneumonia lesions between males and females in a specific age group using artificial intelligence (AI)-based CT metrics. Besides, these metrics were incorporated into a clinical regression model to predict the short-term outcome.Methods: The clinical, laboratory information and a series of HRCT images from 49 patients, aged from 20 to 50 years and confirmed with COVID-19, were collected. The volumes and percentages of infection (POI) among bilateral lungs and each bronchopulmonary segment were extracted using uAI-Discover-NCP software (version R001). The POI in three HU ranges, (i.e. <-300, -300~49 and ≥50 HU representing ground-glass opacity (GGO), mixed opacity and consolidation), were also extracted. Hospital stay was predicted with several POIs after adjusting days from illness onset to admission, leucocytes, lymphocytes, c-reactive protein, age and gender using a multiple linear regression model.Results: Right lower lobes had the highest POI, followed by left lower lobes, right upper lobes, middle lobes and left upper lobes. The distributions in lung lobes and segments were different between the sexes. Men had a higher total POI and GGO of the lungs, but less consolidation than women in initial CT (all p<0.05). The total POI, percentage of consolidation on initial CT and changed POI were positively correlated with hospital stay in the model.Conclusion: Both men and women had characteristic distributions in lung lobes and bronchopulmonary segments. AI-based CT quantitative metrics can provide more precise information regarding lesion distribution and severity to predict clinical outcome.