Viral dynamics of acute SARS-CoV-2 infection and applications to diagnostic and public health strategies

Abstract

SARS-CoV-2 infections are characterized by viral proliferation and clearance phases and can be followed by low-level persistent viral RNA shedding. The dynamics of viral RNA concentration, particularly in the early stages of infection, can inform clinical measures and interventions such as test-based screening. We used prospective longitudinal quantitative reverse transcription PCR testing to measure the viral RNA trajectories for 68 individuals during the resumption of the 2019-2020 National Basketball Association season. For 46 individuals with acute infections, we inferred the peak viral concentration and the duration of the viral proliferation and clearance phases. According to our mathematical model, we found that viral RNA concentrations peaked an average of 3.3 days (95% credible interval [CI] 2.5, 4.2) after first possible detectability at a cycle threshold value of 22.3 (95% CI 20.5, 23.9). The viral clearance phase lasted longer for symptomatic individuals (10.9 days [95% CI 7.9, 14.4]) than for asymptomatic individuals (7.8 days [95% CI 6.1, 9.7]). A second test within 2 days after an initial positive PCR test substantially improves certainty about a patient's infection stage. The effective sensitivity of a test intended to identify infectious individuals declines substantially with test turnaround time. These findings indicate that SARS-CoV-2 viral concentrations peak rapidly regardless of symptoms. Sequential tests can help reveal a patient's progress through infection stages. Frequent, rapid-turnaround testing is needed to effectively screen individuals before they become infectious.

Fig 1. Illustration of the analysis pipeline.

Combined anterior nares and oropharyngeal swabs were tested using a RT-qPCR assay to generate longitudinal Ct values (“Raw data”; red points) for each person. Using a statistical model (see S6 Fig for a schematic of the model), we estimated Ct trajectories consistent with the data, represented by the thin lines under the “Model fits” heading. These produced posterior probability distributions for the peak Ct value, the duration of the proliferation phase (first potential detectability of infection to peak Ct), and the duration of the clearance phase (peak Ct to resolution of acute infection) for each person. We estimated population means for these quantities (under the heading “Population estimates”). The model fits also allowed us to determine how frequently a given Ct value or pair of Ct values within a 5-unit window (blue bars, under the heading “Predicting infection from Ct”) was associated with the proliferation phase, the clearance phase, or a persistent infection. Finally, the model fits allowed us to measure the “effective sensitivity” of a test for predicting future infectiousness. The schematic illustration titled “Measuring effective sensitivity” depicts the relationship between testing lags and the ability to detect infectious individuals at a gathering. The illustrated viral trajectory surpasses the infectiousness threshold (dotted line) at the time of the gathering (vertical grey bar), so unless this individual is screened by a pre-gathering test, he or she would attend the event while infectious. One day prior to the gathering, the individual’s infection could be detected by either a rapid test or a PCR test. Two days prior to the event, the individual’s infection could be detected by a PCR test but not by a rapid test. Three days prior to the event, neither test would detect the individual’s infection. Ct, cycle threshold; LOD, limit of detection; RT-qPCR, quantitative reverse transcription polymerase chain reaction.

Fig 2. Reported cycle threshold (Ct) values with individual-level piecewise linear fits.

Ct values (points) for the 46 acute infections aligned by the date when the minimum Ct was recorded for each individual. Lines depict the best-fit piecewise linear regression lines for each individual with breakpoint at day 0. Red points/lines represent individuals who reported symptoms, and blue points/lines represent individuals who did not report symptoms. Five positive tests were omitted that occurred >20 days prior to the individual’s minimum Ct value, all of which had Ct > 35. The vertical axis on the right-hand side gives the conversion from Ct values to RNA concentration. Underlying data are available at https://github.com/gradlab/CtTrajectories/tree/main/figure_data/Fig2 [10].

Fig 3. Peak cycle threshold (Ct) value and infection stage duration distributions according to symptoms reported at time of diagnosis.

Posterior distributions obtained from 2,000 simulated draws from the posterior distributions for mean peak Ct value (A), mean duration of the proliferation stage (first potential infection detectability to peak Ct) (B), mean duration of the clearance stage (peak Ct to resolution of acute RNA shedding) (C), and total duration of acute shedding (D) across the 46 individuals with an acute infection. The distributions are separated according to whether the person reported symptoms (red, 13 individuals) or did not report symptoms (blue, 33 individuals). The mean Ct trajectory corresponding to the mean values for peak Ct, proliferation duration, and clearance duration for symptomatic versus asymptomatic individuals is depicted in (E) (solid lines), where shading depicts the 90% credible intervals. Underlying data are available at https://github.com/gradlab/CtTrajectories/tree/main/output/params_df_split.csv [10].

Fig 4. Relationship between single/paired cycle threshold (Ct) values and infection stage.

Probability that a given Ct value lying within a 5-unit window (horizontal axis) corresponds to an acute infection (A and C) or to the proliferation phase of infection assuming an acute infection (B and D). (A) and (B) depict the predictive probabilities for a single Ct value, while (C) and (D) depict the predictive probabilities for a positive test paired with a subsequent test with either lower (red) or higher (blue) Ct. The curves are locally estimated scatterplot smoothing (LOESS) curves to better visualize the patterns. Error bars represent the 90% Wald confidence interval. Underlying data are available at https://github.com/gradlab/CtTrajectories/tree/main/figure_data/Fig4 [10].

Fig 5. Effective sensitivity and expected number of infectious attendees at an event, for tests with varying sensitivity.

(A) Effective sensitivity for a test with limit of detection of 40 Ct and 1% sampling error probability (red) and limit of detection of 35 Ct and 5% sampling error probability (blue). (B) Number of infectious individuals expected to attend an event of size 1,000 assuming a population prevalence of 2% infectious individuals for a test with limit of detection of 40 Ct and 1% sampling error probability (red) and limit of detection of 35 Ct and 5% sampling error probability (blue). Shaded bands represent 90% prediction intervals generated from the quantiles of 1,000 simulated events and capture uncertainty both in the number of infectious individuals who would arrive at the event in the absence of testing and in the probability that the test successfully identifies infectious individuals. The dashed line depicts the expected number of infectious individuals who would attend the gathering in the absence of testing. Underlying data are available at https://github.com/gradlab/CtTrajectories/tree/main/figure_data/Fig5 [10].