Performance of local light microscopy and the ParaScreen Pan/Pf rapid diagnostic test to detect malaria in health centers in Northwest Ethiopia

Abstract

Background: Diagnostic tests are recommended for suspected malaria cases before treatment, but comparative performance of microscopy and rapid diagnostic tests (RDTs) at rural health centers has rarely been studied compared to independent expert microscopy.

Methods: Participants (N = 1997) with presumptive malaria were recruited from ten health centers with a range of transmission intensities in Amhara Regional State, Northwest Ethiopia during October to December 2007. Microscopy and ParaScreen Pan/Pf® RDT were done immediately by health center technicians. Blood slides were re-examined later at a central laboratory by independent expert microscopists.

Results: Of 1,997 febrile patients, 475 (23.8%) were positive by expert microscopists, with 57.7% P. falciparum, 24.6% P. vivax and 17.7% mixed infections. Sensitivity of health center microscopists for any malaria species was >90% in five health centers (four of which had the highest prevalence), >70% in nine centers and 44% in one site with lowest prevalence. Specificity for health center microscopy was very good (>95%) in all centers. For ParaScreen RDT, sensitivity was ≥90% in three centers, ≥70% in six and <60% in four centers. Specificity was ≥90% in all centers except one where it was 85%.

Conclusions: Health center microscopists performed well in nine of the ten health centers; while for ParaScreen RDT they performed well in only six centers. Overall the accuracy of local microscopy exceeded that of RDT for all outcomes. This study supports the introduction of RDTs only if accompanied by appropriate training, frequent supervision and quality control at all levels. Deficiencies in RDT use at some health centers must be rectified before universal replacement of good routine microscopy with RDTs. Maintenance and strengthening of good quality microscopy remains a priority at health center level.

Figure 1. Location of health centers included in the study in Amhara National Regional State, Northwest Ethiopia.

Figure 2. Flowchart of health center technician microscopy and ParaScreen RDT results compared to expert microscopy.

Figure 3. Test positive rate by health center.

Figure 4. Malaria slide positivity rate in relation to altitude.

Figure 5. Sensitivity and specificity of local health centre microscopy and RDT compared to expert microscopy for the outcome ‘positive for any malaria species’, by health center.

TP =  true positive; FP = false positive; FN = false negative; TN = true negative.

Figure 6. Summary receiver operator characteristic curve (SROC) for local health centre microscopy and RDT compared to expert microscopy for the outcome ‘positive for any malaria species’.

Figure 7. Sensitivity and specificity of local health centre microscopy and RDT compared to expert microscopy for the outcome ‘positive for P.falciparum or mixed infection’, by health center.

TP = true positive; FP = false positive; FN = false negative; TN = true negative.

Figure 8. Summary receiver operator characteristic curve (SROC) for local health centre microscopy and RDT compared to expert microscopy for the outcome ‘positive for P.falciparum or mixed infection’.

Figure 9. Sensitivity and specificity of local health centre microscopy and RDT compared to expert microscopy for the outcome ‘P.vivax or PAN only’, by health center.

TP = true positive; FP = false positive; FN = false negative; TN = true negative.

Figure 10. Summary receiver operator characteristic curve (SROC) for local health centre microscopy and RDT compared to expert microscopy for the outcome ‘P.vivax or PAN only’.