Malaria is currently the leading cause of death in Uganda. There are over 20 million infections every year. Global initiatives in malaria control have significantly decreased the burden of the disease of the past decade, but have remained relatively stagnant over the past few years. Rapid diagnostic tests (RDTs) have long been the accepted method of diagnosis for malaria. Recent genetic mutations in the DNA of malaria parasites have increased the number of individuals who have received a false negative diagnosis. Accompanying this growing risk of mutating parasites are other common shortcomings of RDTs such as low density infections and non-falciparum species infections.

Our team aims to revolutionize the method of malaria detection by using a machine learning algorithm to automate the detection of malaria parasites in thick and thin smear blood slides. It is our aim that our algorithm will successfully detect the type of parasite, level of parasitemia, and life-cycle stage for the parasite. This information will dictate the level of treatment required to ensure the patient’s safety. The device includes both hardware and software components; the machine learning algorithm will be implemented through a fully automatic microscopy system in collaboration with Manu Prakash’s lab at Stanford University. The solution will be implemented at Tier 4 health clinics and hospitals in Uganda, where common light microscopes are already available. With the help of the Ugandan Ministry of Health, Johns Hopkins School of Public Health, and others we believe that this will be a highly-scalable implemented solution across Africa.

Team Members

[foreach 357]

• [if 397 not_equal=””][/if 397][395]

[/foreach 357]

Project Mentors, Sponsors, and Partners

• Dr. Soumyadipta Acharya

• Dr. Youseph Yazdi

• Geoffrey Oguma

• Dr. Manu Prakash

• Hongquan Li

• Dr. Matthew Ippolito

• Dr. Benjamin Haeffele

• Winnie Kansiime

• Annet Joselyn Atuhairwe

• Dr. Catherine Maiteki

Course Faculty

[foreach 429]

• [if 433 not_equal=””][/if 433][431]

[/foreach 429]

Project Links

Additional Project Information