Evaluation of the Parasight Platform for Malaria Diagnosis

Abstract

The World Health Organization estimates that nearly 500 million malaria tests are performed annually. While microscopy and rapid diagnostic tests (RDTs) are the main diagnostic approaches, no single method is inexpensive, rapid, and highly accurate. Two recent studies from our group have demonstrated a prototype computer vision platform that meets those needs. Here we present the results from two clinical studies on the commercially available version of this technology, the Sight Diagnostics Parasight platform, which provides malaria diagnosis, species identification, and parasite quantification. We conducted a multisite trial in Chennai, India (Apollo Hospital [n ϭ 205]), and Nairobi, Kenya (Aga Khan University Hospital [n ϭ 263]), in which we compared the device to microscopy, RDTs, and PCR. For identification of malaria, the device performed similarly well in both contexts (sensitivity of 99% and specificity of 100% at the Indian site and sensitivity of 99.3% and specificity of 98.9% at the Kenyan site, compared to PCR). For species identification, the device correctly identified 100% of samples with Plasmodium vivax and 100% of samples with Plasmodium falciparum in India and 100% of samples with P. vivax and 96.1% of samples with P. falciparum in Kenya, compared to PCR. Lastly, comparisons of the device parasite counts with those of trained microscopists produced average Pearson correlation coefficients of 0.84 at the Indian site and 0.85 at the Kenyan site.

Effect of Artificial Intelligence-Based Technology in Malaria Diagnosis

“…Microscopy Mixed 12 0 0 0 12 Negative 0 42 3 5 50 pf 0 0 10 0 10 pv 0 0 0 28 28 Total 12 42 13 33 0 0 6 Negative 3 42 5 12 62 pf 1 0 8 0 9 pv 2 0 0 21 23 Total 12 42 13 33 100 The Parasight digital cytometry-based scanning and detection system for malaria has shown promising results in previous studies. 10,11 We tested it for practical feasibility in terms of accuracy, cost effectiveness and rapidity. Our study has shown that in comparison to gold standard microscopy, the digital cytometry gave similar results (in terms of accurate species detection as well) when parasite concentration was on higher side (mean 0.0515%).…”

“…At Apollo Hospital India, the device showed a Pearson correlation coefficient of 0.84, compared to microscopy (correlation coefficients of 0.98 for P. falciparum and 0.83 for P. vivax); at AKUH, the device showed a Pearson correlation coefficient of 0.85, compared to microscopy (correlation coefficients of 0.86 for P. falciparum and 0.55 for P. vivax). 10 In a study by Srivastava et al 2015 for comparison of parasite species detection by PCR and its comparison with digital cytometry. From samples found to be positive by both PCR and SightDx, SightDx speciated 73.3% of PCR P. falciparum + samples and 91.4% of PCR P. vivax + samples, as shown in Table 3.…”

Computer Vision Malaria Diagnostic Systems—Progress and Prospects

“…The SYTO family of dyes also excelled in its capacity to stain cultured malaria positive red blood cells (RBCs). Additional fluorescent-based systems have used a dye combination to achieve accurate staining such as the Parasight system which makes use of multiple dyes in the 370 and 475 nm excitation imaging ranges ( 23 – 25 ).…”

“…A platform designed by Vink et al using a live intra-vital cartridge stain is capable of analyzing 0.47 μL of blood, potentially analyzing 2.5 million RBCs, and yielding a projected LOD of 10 parasites/μL within 15 min ( 21 ). A second fluorescent system, the Parasight malaria detection device, showed an LOD of under 100 parasites/μL ( 25 ). Limits of detection on these devices should reduce with further algorithm development, though the LOD will eventually be limited by the noise floor caused by artifacts from film preparation and staining.…”

Computational approach for diagnosis of malaria through classification of malaria parasite from microscopic image of blood smear

“…Even these analysis are time consuming and leads to inaccuracy and inconsistency in some cases. The computerised approach uses digitized blood slides that will be able to improve the consistence in diagnosis [3][4][5][6][7][8][9].…”