Evaluation of a Digital Microscope for Malaria

Light microscopy, which is based on century-old technology, remains a key indicator in drug efficacy testing performed in the context of clinical trials for monitoring existing antimalarial drugs or in the context of regulatory clinical trials for registration of new drugs. It is one of the main diagnostic methods for malaria diagnosis in general, as in an ideal setting it can provide low-cost accurate diagnosis, determine the density of parasites in the blood, and accurately differentiate between different malaria parasite species, characteristics vital to the implementation of global plans for drug efficacy monitoring. Malaria rapid tests (RDTs), while useful for rapid diagnosis and case management, do not provide information on the parasite density nor the species differentiation necessary for research and drug efficacy assessment. Microscopy therefore retains key advantages over a number of newer technologies, but its reliability is severely impeded by dependence on high technical competence of the human operators as well as availability of high quality equipment and reagents. Recent studies have demonstrated frequent poor specificity and sensitivity associated with manual microscopy diagnostics in operational conditions. These drawbacks constitute a major limiting factor to effective monitoring and preservation of vital anti-malarial medicines.

Advances in digital microscopy performance and affordability have now opened the door to potentially significant improvements in the performance of malaria microscopy, overcoming serious deficiencies in current drug efficacy assessment, and more broadly in malaria diagnosis and management. Global Good (GG)/Intellectual Ventures Laboratory (IVL) sponsored by the Global Good Fund, has developed a microscope prototype consisting of low cost components to scan and capture images from Giemsa-stained thick blood films on slides. The captured images are analyzed with custom image analysis software developed at GG/IVL, using algorithms that are designed for automatic malaria diagnosis, without user input. Versions of a prototype of the device were first tested in field settings in Thailand in 2014-2015 at clinics operated by the Shoklo Malaria Research Unit (SMRU) and then again in 2016-2017. When compared to expert microscopy at SMRU, the performance of the device with respect to diagnostic sensitivity (87.8%), species identification (85.6% species correctly identified) and parasite density estimation (44% of estimates within +/-25% of reference microscopy result) corresponded to WHO Competence Level 2. The device and the accompanying image analysis algorithms have since been further developed and a new, third version of the prototype is now available for testing in diverse settings with varying malaria prevalence and user expertise.