Routine diagnostic specimens collected from patients on ART as part of the South African national antiretroviral programme in and around Cape Town were studied. Samples were processed according to the local standard operating procedure, briefly outlined as follows: On arrival at the laboratory, patient and sample information, including date and time of collection are captured on the laboratory information system and samples are centrifuged for 10 minutes at relative centrifugal force (RCF) 3,273g. They are then transferred to the bench where HIV VL testing on primary tube EDTA or PPT samples is performed on the Roche Cobas AmpliPrep, Cobas TaqMan (CAP/CTM) version 2.0 assay. Using a 1 mL input, this assay has a dynamic range from 20 to 10 000 000 copies/mL (1.3–7 log₁₀). The delay between sample collection and initial VL testing is recorded as time to test 1. The result of test 1 was reported as the final result for the purpose of patient management. Thereafter, the samples were de-identified and assigned a separate study number. Further testing was not part of routine laboratory process.

Immediately after plasma was aspirated from the primary tube for test one (and the testing process began), the primary tubes were visually inspected. Those with sufficient (>1 mL) residual plasma were selected and stored at 4°C, 20°C or 30°C for a pre-determined interval of 72, 96 or 168 hours. Approximately 30% of PPT and 20% of EDTA samples had enough residual plasma for a second test. After storage at the specified temperature and time, primary tubes were re-centrifuged (3,273g for 10 minutes), 1mL of residual plasma was manually pipetted from the tube and the VL was repeated. The second VL result was captured as test 2. A figure illustrating the study plan is included in supplementary digital content, S1 Fig.

In a second set of experiments, routine diagnostic samples were processed as before, but re-centrifugation prior to the second test was omitted. These samples were also subjected to delayed testing with different storage conditions as above so the impact of repeat centrifugation was separately assessed. 37 EDTA samples (32 of which were undetectable in test 1) and 46 PPT samples (of which 29 were undetectable) were tested.

Data were analysed using Stata Version 12.0 (Stata Corporation, College Station, Texas, USA). For analysis, samples with an undetectable VL (LDL, or lower than detectable limits) on test 1 or test 2, were assigned a value of 1 copy/mL. Samples with a detectable VL, but less than 20 copies/mL, were assigned a value of 19 copies/mL. Samples with a VL >20 copies/mL were assigned the value reported by the analyser. The impact of delayed testing, storage temperature and repeat centrifugation were assessed in three separate analyses. First, the VL change among samples with a detectable test 1 VL (>20 copies/ml) were assessed. The proportion of instances where the test 2 VL was within 0.5 log₁₀ copies/mL of test 1 for each storage temperature and time category was determined. This cut off was selected because in clinical practice, only VL changes >0.5log copies per ml are considered clinically significant [12]. The primary stability estimate was the median change in VL after the 72, 96 and 168 hour intervals and variability in this change was expressed in interquartile ranges. In addition, the proportion of instances where the test 2 VL result was within 0.5 log10 copies/mL of test 1 for each storage temperature and time category was determined. Results of samples collected in PPT tubes and EDTA tubes were analysed separately. Second, samples with undetectable RNA in test 1 were assessed to determine reproducibility of measurement. Finally, repeat VL measurements in an additional set of samples that was not re-centrifuged prior to retest was analysed separately.

Ethics approval for the study was obtained from the University of Cape Town Human Research Ethics Committee, reference number HREC 159/2019.

For the main study, 1194 routine diagnostic samples, including 608 samples collected in EDTA and 586 in PPT tubes were studied. 441 (36.9%) of samples had undetectable VL on first test. in the remaining 753 samples, the viral load in test 1 was detectable and ranged between 19 –>1,000,000 copies/mL. A breakdown of the first test VL measurements is given in Table 1.

In 665 (55%) samples the first VL was performed within 24 hours of sample collection. For the remaining 529 samples, the first test was performed between 1–7 days of sample collection. Delayed testing mostly occurred in samples referred from distant laboratories, or due to technical problems with instrumentation in the laboratory.

In the experiment where repeat centrifugation was omitted prior to repeat VL testing, 83 samples (37 EDTA and 46 PPT) were tested.

Overall, 86.6% (95%CI 83.7–89.2%) of all test 2 VL results were within 0.5 log copies/mL of test 1. This VL concordance rate was similar, at 84.0% (95%CI 79.7–87.7%) for the subset of samples where the first VL test had been performed within 24 hours of sample collection (within the current recommended optimal testing interval). As no significant differences were detected between the 2 data sets, only the results of the complete data set are reported here. A viral load concordance rate of 90.3% (95%CI 86.9–93.1%) was observed for the PPT samples overall, whereas the 2 VL readings were within 0.5 log copies/mL in 81.4% (95% CI 76.1–85.9%) for EDTA samples. There was no rising trend in the proportion of samples with a viral load difference of >0.5log copies/mL between tests 1 and 2, with increasing time or temperature of storage. (Fig 1) Variability was slightly greater in samples in EDTA tubes, but otherwise trends were similar (as determined by median and IQR of log viral load change in the different time/temperature storage categories).

Fig 2 illustrates changes in log VL at each storage temperature and time point. For samples stored at 4°C, a median VL decrease was consistent for both sample types (EDTA and PPT) and over time, but the net effect was small, with all the interquartile ranges well within 0.5 log copies/ml compared to the initial VL results. At 20°C the trend was less apparent with some testing intervals resulting in slight increase, while others remained similar to original testing. Once again the VL changes were not significant, as none of the interquartile ranges cross the 0.5log difference line. In samples stored at 30°C, median values were mostly higher than baseline values. (Median log copies/ml differences for each sample category are given in supplementary digital content, S1 Table.) Greater variability was observed in samples collected in EDTA tubes, in particular the 72 hour samples at 20°C and 168 hour samples at 30°C.

WHO guidelines for management of patients on ART advise a level of >1000 copies/mL as the threshold indicative of treatment failure [13]. Thus the study results were analysed according to whether the difference between tests 1 and 2 was great enough to result in misclassification of a patient’s status (failure vs suppression). Of 1194 samples tested, a potential misclassification may have occurred in 14 (8 EDTA and 6 PPT) instances, or 1.17% samples. The discordant results are listed in supplemental digital content, S2 Table. In 10 the initial VL (range 1–890 copies/ml) increased to between 1000–70086 copies/mL and in 4 samples the level (range 1674–2940 copies/ml) decreased on repeat to between 500–846 copies/mL.

The stability of samples that were RNA negative at test one was also tested. 441 samples (195 PPT and 246 EDTA) had undetectable RNA at test one. On retesting after storage, the VL in 79.1% of samples remained undetectable or <20 copies/mL. In the 20.9% of samples that had a detectable value on the 2^nd test, RNA levels were mostly low. Overall, in 14.7% of samples the second viral load was <100 copies/mL, in 5.7% it was 101–500 copies/mL and in 0.4% > 500 copies/mL. Though no statistical test was used to confirm this, the proportion of samples that had a detectable viral load on 2^nd test did not appear to be affected by storage time, temperature or type of collection tube. Fig 3(A) and 3(B).

When repeat centrifugation was omitted just prior to the 2^nd test, the RNA level in test 2 increased substantially in some samples. (Fig 4(A)) This was observed in both EDTA and PPT samples and was evident by 48 hours after (prior) centrifugation. The VL remained within 0.5 log copies/mL in test 2 in only 41 of the 83 (49%) samples tested in this experiment. Of note 29 of 57 samples with initially undetectable HIV RNA had detectable RNA in the 2^nd test: 10 (17.5%) were < 100 copies/ml, 12 (21%) were 101–500 copies/ml, 1 (1.8%) was 501–1000 copies/ml and 6 (10.5%) were >1000 copies/ml. (Fig 4(B)) Overall, the median increase was 0.63 log copies/mL (range 0.00–4.13) in test 2.

Despite the limitations that could increase the variance in VL between test 1 and 2, viral RNA in samples stored in primary tubes is remarkably stable under sub-optimal storage conditions. Samples stored for up to a week reliably differentiated between ART-suppressed and failing patients in 98.83% of instances. The impact of the delay on EDTA and PPT tubes were largely equivalent, although there was slightly more variability with EDTA samples. Re-centrifugation prior to repeat testing is very important to minimise inadvertent detection of cell associated viral nucleic acids which falsely elevates the viral load in some samples. Low RNA levels (<2 log copies/mL) in sub-optimally stored samples should be interpreted with caution as this could be due to cell-associated viral nucleic acids rather than true treatment failure.