Artificial intelligence to diagnose tropical diseases using a mobile phone

Filariasis is a common tropical infectious disease and affects more than one billion people worldwide. Depending on the parasite, it causes lymphedema, elephantiasis, itching and blindness (known as river blindness). To eliminate filariasis as a public health problem, mass administration of medications is carried out to all people living in endemic areas. Diagnosis of this disease is made by microscopic examination of a blood smear by a human expert, which is laborious and experts are not always available.

Within the framework of research into this disease, researchers from Spotlab, the National Center for Microbiology (CNM), the Carlos III Health Institute (ISCIII), the Polytechnic University of Madrid (UPM) and the Areas of Bioengineering, Biomaterials and Nanomedicine (CIBERBBN) and Infectious Diseases (CIBERINFEC) of the CIBER-ISCIII, in Spain all these entities have developed artificial intelligence algorithms to detect in the blood the presence of microfilariae, the infectious larvae that can transmit filariasis.

These algorithms distinguish the most common parasite species in Africa (Loa loa, Mansonella perstans and Wuchereria bancrofti) and Southeast Asia (Brugia spp), using a mobile phone camera connected to an optical microscope with a 3D printed adapter.

To create this system, the researchers have used 115 clinical cases and have validated the system in a clinical setting at the CNM. The system has an accuracy of around 95%.

The main authors of the study are Lin Lin, an engineer specializing in artificial intelligence and Elena Dacal who works in the clinical team, both under the supervision of the main researchers Miguel Ángel Luengo (Spotlab), José Miguel Rubio (CNM, CIBERINFEC) and María Jesús Ledesma (UPM, CIBERBBN).

Additionally, the researchers have created a mobile application called HuggingSpot, which is available on the Google App Store and allows the scientific community to download the artificial intelligence models and test them.

Smart microscope system. (Photo: Spotlab)

This innovation has enormous potential to aid the diagnosis and monitoring of filariasis, especially in resource-limited contexts, where access to specialized technicians and laboratory equipment is scarce.

The study is titled “Edge Artificial Intelligence (AI) for real-time automatic quantification of filariasis in mobile microscopy.” And it has been published in the academic journal Plos Neglected Tropical Diseases. (Source: UPM)