Measuring the impact of nonpharmaceutical interventions on the SARS-CoV-2 pandemic at a city level: An agent-based computational modelling study of the City of Natal

Abstract

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic hit almost all cities in Brazil in early 2020 and lasted for several months. Despite the effort of local state and municipal governments, an inhomogeneous nationwide response resulted in a death toll amongst the highest recorded globally. To evaluate the impact of the nonpharmaceutical governmental interventions applied by different cities-such as the closure of schools and businesses in general-in the evolution and epidemic spread of SARS-CoV-2, we constructed a full-sized agent-based epidemiological model adjusted to the singularities of particular cities. The model incorporates detailed demographic information, mobility networks segregated by economic segments, and restricting bills enacted during the pandemic period. As a case study, we analyzed the early response of the City of Natal-a midsized state capital-to the pandemic. Although our results indicate that the government response could be improved, the restrictive mobility acts saved many lives. The simulations show that a detailed analysis of alternative scenarios can inform policymakers about the most relevant measures for similar pandemic surges and help develop future response protocols.

Fig 1. Timeline of agent’s health state progression through a SARS-CoV-2 infection.

(A) Possible daily transitions of one agent starting from Susceptible up to Dead or Immune. Sequences of the same state represent average time without change. (B) The evolution of the state of 10,000 agents, with age and sex distribution suited to the City of Natal, turned into Incubated at day zero. The simulation assumes illimited ICU bed availability.

Fig 2. High diversity of contact networks.

Layers and sub-layers are complex networks composed of agents (blue dots) and social interactions (lines). Representative layers (Home and Transportation) and sub-layers (Catholic churches, Public Elementary Schools and Services) display different characteristics as high connectivity, coverage and a small world topology. All the information about connections is available in Table 3.

Fig 3. Epidemiological data on the first wave of the Covid-19 pandemic in the City of Natal, Brazil.

(A) The daily number of confirmed cases with a total of 26,371 cases and a peak of 552 new cases in one day (red line), and the estimated daily number of external cases with a total of 3,957 cases with a peak of 76 new cases (blue line and area). (B) Estimated ICU beds available (silver dashed line) and utilized (black dashed line) during the first wave. Numbers for Natal are estimated as 46.68% of the metropolitan region data.

Fig 4. Sensitivity analysis indicates an inhomogeneous impact of different transmission networks in the outbreak progression.

The difference in the total number of deaths with a reduction of P_{contamination} from 1.7 to 1.5 in all layers, in each layer or sub-layer. Graphics represent median (bar), quartiles (line), absolute median difference to high-value simulation and relative difference to a reduction of P_{contamination} value in all layers.

Fig 5. Baseline simulation from the agent model provides a good fit for epidemiological data on the first wave of the SARS-CoV-2 epidemic in the City of Natal, Brazil.

(A) Daily and (B) accumulated deaths during the first wave of the SARS-CoV-2 outbreak in the City of Natal (from the end of February to the beginning of October) from simulation (blue) and actual reports (black). Vertical lines indicate the dates of publication of governmental decrees. (C and D) The accumulated number of infections originated in each layer or sub-layer. Simulation data from (A to D) were reported as median and quartiles (5%, 25%, 75%, 95%) from 500 runs. (E) Model-predicted ICU requirement (solid purple line, median) and excess (purple area) from estimated daily availability (silver dashed line) and the actual estimated occupation (black line) of ICU beds for the City of Natal.

Fig 6. Simulation of different scenarios reveals a significant impact of the school closure decree on March 17th, 2020.

Results for a baseline scenario altered for the condition that schools were never closed (#1, A), closed at the end of the semester (#2, B) and closed with a delay from the original decree’s publication date (#3, C). The total number of additional deaths in each scenario is the difference between the simulation outcome and the reported number. For scenario #3, the delay in weeks is colour-coded, and the additional number of deaths is shown in an insert. See Fig 5 for panel description.

Fig 7. Simulation of different scenarios reveals a moderate and sub-optimal impact of the business closure decree on March 25th, 2020.

Results for a baseline scenario altered for the condition that workplaces were never closed (#4, A), closed effectively (#5, B) and closed effectively with a delay from the original decree’s publication date (#6, C). The total number of lives saved in each scenario is the difference between the reported number of deaths and the simulation outcome. For scenario #6, the delay in weeks is colour-coded, and the additional number of lives saved is shown in an insert. See Fig 5 for panel description.

Fig 8. Simulation of different scenarios reveals a moderate and sub-optimal impact of the worship venues closure decree on March 25th, 2020.

Results for a baseline scenario altered for the condition that worship venues were never closed (#7, A), closed effectively (#8, B) and closed effectively with a delay from the original decree’s publication date (#9, C). The total number of lives saved in each scenario is the difference between the reported number of deaths and the simulation outcome. For scenario #9, the delay in weeks is colour-coded, and the additional number of lives saved is shown in an insert. See Fig 5 for panel description.

Fig 9. Simulation of a scenario without any decree implies a catastrophic scenario.

Results for a baseline scenario altered for the condition that no decree was ever published. Panels from A to F, as in Fig 5.