Is it possible to (reliably) diagnose malaria with a noninvasive device/smartphone app?

Question

Today, I was made aware of a research project made by Ugandan CS students who claim to have built a smartphone app together with a device called a "matiscope" that

[...] uses a red light to penetrate the skin [of a finger inserted into the device] and detect the red blood cells [...and] used light-scattering technology to determine the scatter patterns of both normal and infected cells

in order to detect an infection with Malaria.

Now this device sounds a lot like a simple oximeter, and the claims put forth in that article are rather vacuous, i. e.

[...] they test no less than 50 patients a day for malaria and receive eight to 10 positive results.

without saying anything about whether those results were accurate. But even if they were, my guess would be that changes in oxygen saturation caused by a severe bout of malaria would far outweigh any possible changes in light absorption caused by Plasmodium parasites. But I'm curious anyway.

A quick PubMed search has turned up nothing, but maybe I've been using the wrong search terms - is there any evidence available that such a device/app could in fact work?

The students have won the "Women's Empowerment Award" from Microsoft's Imagine Cup in 2013, which is wonderful, but the website doesn't have any additional information, either.

Answer 1

There are two questions. One is whether it's possible to diagnose malaria with a non-invasive device, and two whether that device could involve a smartphone with software.

It's clearly possible to non-invasively diagnose cerebral malaria by examining the retina using either direct or indirect ophthalmoscopy [1]

A retinopathy consisting of two unique features - patchy retinal whitening and focal changes of vessel color - is highly specific for encephalopathy of malarial etiology. White-centered retinal hemorrhages are a common but less specific feature.

The technique these students are using is most likely that described in this paper (full text) [2]

We investigated the backward light scattering pattern of healthy and malaria (Plasmodium falciparum) parasitized red blood cells. The spectrum could clearly distinguish between predominant ring stage infected blood cells and healthy blood cells. Further, we found that infected samples mixed with different stages of P. falciparum showed different signals, suggesting that even variance in parasite stages could also be detected by the spectrum. These results together with the backward scattering technique suggest the potential of non-invasive diagnosis of malaria through light scattering of blood cells near the surface of human body, such as using eyes or skin surface.

Likely the app just analyses the data from the device which does the light scattering.

[1] Beare NA, Lewallen S, Taylor TE, Molyneux ME. Redefining cerebral malaria by including malaria retinopathy. Future Microbiol. 2011 Mar;6(3):349-55. doi: 10.2217/fmb.11.3. Review. PubMed PMID: 21449844; PubMed Central PMCID: PMC3139111.

[2] Lee S, Lu W. Using elastic light scattering of red blood cells to detect infection of malaria parasite. IEEE Trans Biomed Eng. 2012 Jan;59(1):150-5. doi: 10.1109/TBME.2011.2168398. Epub 2011 Sep 15. PubMed PMID: 21926010.