Performance of the BD-FACS Presto for CD4 count and hemoglobin measurement in a district hospital and rural laboratory in Ghana

Abstract

Introduction: In Ghana, initiation of Antiretroviral Therapy (ART) is recommended for all patients with an HIV diagnosis, regardless of CD4+ T-cell count. However, measurement of CD4 count remains an important metric for identifying patients with advanced HIV disease, and assessing a person's overall immune status, which informs the decision to offer opportunistic infection screening and prophylaxis. Access to CD4+ T cell count in rural health facilities remains a major challenge in Ghana and other resource-limited settings. This study aimed to validate the accuracy of the BD FACSPresto near-patient device for measurement of CD4 count and hemoglobin concentration against the FACSCount (CD4) and Sysmex (hemoglobin) diagnostic machines when operated in both a district hospital and rural laboratory, serving a network of health posts in Ashanti Region, Ghana.

Methodology: In the first phase of the study, patients were recruited from a district hospital, and both venous and capillary blood samples were tested using the FACSCount and Sysmex as reference tests and compared to results of the FACSPresto performed in the clinic laboratory at the district hospital. In the second phase, patients were recruited from both the hospital and from rural health clinics, and samples were tested using the FACSPresto at a rural laboratory. Sensitivity and specificity among samples categorized into different clinically relevant CD4 count ranges were calculated, along with correlation between the Presto and the reference measurements, and mean and relative bias with limits of agreement.

Results: The FACSPresto was successfully operated in both clinical settings. A total of 59 samples in the first phase and 48 samples in the second phase were included. Positive bias was observed when comparing CD4 count measured by BD FACSPresto to FACSCount in the district hospital (bias = 44, LOA -72,160) and in the rural laboratory setting (bias = 74, LOA -96, 244). In addition, capillary blood samples were shown to give higher measures when compared to venous blood samples from the same participant. All results were statistically significant (p<0.05) apart from hemoglobin measurement in venous blood in the rural laboratory. Correlation coefficients were high for CD4 count measures and lower for hemoglobin measures.

Conclusion: Overall, the Presto gave higher estimates of CD4 count compared to FACSCount, and hemoglobin measurements were higher than from Sysmex. Samples of capillary blood in turn gave higher results for both measurements compared to venous blood, consistent with previous analyses. These findings should be considered when selecting CD4 count machines for use at the point of care, especially in remote areas where capillary blood sampling may be preferable, but are likely balanced by device's ease of use, portability, and ability to expand access to services. These results are some of the first to demonstrate the accuracy of the FACSPresto in West Africa and show that this device can be successfully operated in a very rural lab setting and may therefore assist to provide CD4 count and hemoglobin concentration measurement to populations in need.

Fig 1. Study recruitment for phase 1 and 2.

Participants were recruited sequentially from both the district hospital (DH) and the rural laboratory. In phase 1, all samples were analyzed in the DH from DH patients, and in phase 2, samples came from both DH and rural laboratory patients and all were analyzed in the rural laboratory.

Fig 2. Bland-Altman plots comparing absolute CD4 count and hemoglobin measurements from venous or capillary blood samples as measured with Presto was operated in the district hospital (phase 1) or the rural laboratory (phase 2).

Dotted lines indicate the lower and upper limits of agreement and the solid line indicates the bias.