Overlapping Delta and Omicron Outbreaks During the COVID-19 Pandemic: Dynamic Panel Data Estimates

Abstract

Background: The Omicron variant of SARS-CoV-2 is more transmissible than prior variants of concern (VOCs). It has caused the largest outbreaks in the pandemic, with increases in mortality and hospitalizations. Early data on the spread of Omicron were captured in countries with relatively low case counts, so it was unclear how the arrival of Omicron would impact the trajectory of the pandemic in countries already experiencing high levels of community transmission of Delta.

Objective: The objective of this study is to quantify and explain the impact of Omicron on pandemic trajectories and how they differ between countries that were or were not in a Delta outbreak at the time Omicron occurred.

Methods: We used SARS-CoV-2 surveillance and genetic sequence data to classify countries into 2 groups: those that were in a Delta outbreak (defined by at least 10 novel daily transmissions per 100,000 population) when Omicron was first sequenced in the country and those that were not. We used trend analysis, survival curves, and dynamic panel regression models to compare outbreaks in the 2 groups over the period from November 1, 2021, to February 11, 2022. We summarized the outbreaks in terms of their peak rate of SARS-CoV-2 infections and the duration of time the outbreaks took to reach the peak rate.

Results: Countries that were already in an outbreak with predominantly Delta lineages when Omicron arrived took longer to reach their peak rate and saw greater than a twofold increase (2.04) in the average apex of the Omicron outbreak compared to countries that were not yet in an outbreak.

Conclusions: These results suggest that high community transmission of Delta at the time of the first detection of Omicron was not protective, but rather preluded larger outbreaks in those countries. Outbreak status may reflect a generally susceptible population, due to overlapping factors, including climate, policy, and individual behavior. In the absence of strong mitigation measures, arrival of a new, more transmissible variant in these countries is therefore more likely to lead to larger outbreaks. Alternately, countries with enhanced surveillance programs and incentives may be more likely to both exist in an outbreak status and detect more cases during an outbreak, resulting in a spurious relationship. Either way, these data argue against herd immunity mitigating future outbreaks with variants that have undergone significant antigenic shifts.

Keywords: Arellano-Bond estimator; B.1.1.529; COVID-19; Delta; Omicron variant of concern; SARS-CoV-2; disease transmission metrics; dynamic panel data; outbreak; stringency index; surveillance.

Figure 1

Map of Delta and Omicron outbreaks. Note that countries in red were in an outbreak on December 15, 2022, as defined by a daily rate of at least 10 novel SARS-CoV-2 transmissions per 100,000 population. Countries in orange were not in an outbreak but displayed 7 consecutive days of an increase in the rate of novel SARS-CoV-2 transmissions per 100,000 population.

Figure 2

Time from arrival of Omicron until peak of outbreak. Note: Countries are considered censored if their peak speed occurred on the final day of the sample period. The cross hashes in the figure denote these censor points.

Figure 3

Peak of outbreak as a function of speed at Omicron arrival. Note: Not depicted, but included in the trend line calculation, is the outlier country of Israel, which reached a peak speed of 1177.3 daily novel transmissions per 100,000 population, up from a speed of 5.3 when Omicron was first sequenced in the country. The peak speed in Israel was approximately 4.5 SDs above the mean for all countries.

Figure 4

Outbreaks in Canada and the United States. Note: The vertical lines indicate the date Omicron was first sequenced in each country. The solid and dashed lines correspond to those of each country in the legend.

Figure 5

The evolution of Delta and Omicron VOCs in Canada and the United States. Note: The y axis denotes the total number of sequences for each VOC on a given date. VOCs other than Delta and Omicron were too infrequent to depict on the plot. VOC: variant of concern.

Figure 6

Outbreaks in Armenia, Azerbaijan, and Georgia. Note: The vertical lines indicate the date Omicron was first sequenced in each country. The solid and dashed lines correspond to those of each country in the legend.

Figure 7

Outbreaks in Kazakhstan and Russia. Note: The vertical lines indicate the date Omicron was first sequenced in each country. The solid and dashed lines correspond to those of each country in the legend.

Figure 8

Outbreaks in Israel, Jordan, and Lebanon. Note: The vertical lines indicate the date Omicron was first sequenced in each country. The solid, dashed, and dotted lines correspond to those of each country in the legend.

Figure 9

Time from arrival of Omicron until peak of outbreak by hemisphere. Note: Countries are included in the Northern Hemisphere group if their geographical area lies entirely in the Northern Hemisphere. All other countries are included in the Southern Hemisphere group.