Inter-rater Variability in Malaria Microscopy at the LEKMA Hospital, Ghana

Abstract

Background: Malaria remains a major cause of morbidity and mortality worldwide and particularly in sub-Saharan Africa where it is endemic. As such, it is important that a proper diagnosis is made before treatment is initiated. Malaria parasite count plays a key role in the diagnosis and management of malaria. Variations in ratings by laboratory personnel can impact negatively on the treatment regimen for malaria-infected patients. The study is thus aimed at evaluating and comparing the proficiency and parasitaemia counts by two different categories of laboratory staff at the LEKMA Hospital, Ghana.

Materials and methods: A total of 200 confirmed malaria-positive samples were used in the study. Six thick and thin films were prepared from each sample and uniquely labelled. Two of the six slides were given to two WHO-accredited malaria microscopists to examine and report their respective parasite count/μl (parasite count/WBC × 8000). These were used as the reference for the two categories of laboratory staffs: rater A being diploma holders (Technical Officers referred to as untrained rater) and rater B being degree holders (Medical Laboratory Scientist referred to as trained rater) at the LEKMA Hospital.

Results: In comparison to the expected outcome, the parasite count by the rater group A (190 (151-239)]) and the rater group B (177 (140-224)) demonstrated significant positive correlation (r = 0.995, p < 0.0001 vs. r = 0.995, p < 0.0001, respectively) with the expected outcome in the cases of heavy parasitaemia. A statistically significant difference (p < 0.05) between counts by the different raters in low parasitemia was observed in this study. A persistent nosedive inter-rater agreement from k = 0.82 to k = 0.40 with increasing density cutoff was observed in this study.

Conclusion: The study observed that the degree of inter-rater agreement of parasite density count by various categories of laboratory personnel is almost perfect. However, the parasite count between raters varied significantly with very low levels of parasitemia but better correlated with heavy parasitemia.

Figure 1

Trained and untrained rater difference in parasite density/μl.

Figure 2

Bland-Altman plot demonstrating the agreement between the expected parasite density and parasite density from rater A (parasite density values are log-transformed).

Figure 3

Bland-Altman plot demonstrating the agreement between expected parasite density and parasite density from rater B (parasite density values are log-transformed).

Figure 4

Bland-Altman plot demonstrating the agreement between parasite density of rater A and B (parasite density values are log-transformed).