Computer Science News
CS AI-Robotics Malaria Diagnosis System Capitalises on 10 Years of Interdisciplinary Research
UCL Computer Science is celebrating its decade-long collaboration with the College of Medicine of the University of Ibadan (COMUI), Nigeria, to carry out life-saving clinical-, life- and computer science research into the development of fast and accurate automated malaria diagnosis devices.
This is particularly significant, since 25 of April 2018 is also the World Health Organisation’s (WHO) World Malaria Day. The theme of this year’s campaign is ‘Ready to Beat Malaria’, underscoring the collective energy and commitment of the global malaria research, aid and funding communities, to unite around the common goal of a world free of malaria.
Up to eighty-five percent of the clinical malaria cases occur in sub Saharan Africa with about 90% mortality in the <5 years age group due to severe malaria syndromes and control of malaria remains a major public health issue in sub-Saharan Africa developing countries.
Access to effective malaria diagnosis is a challenge faced by all developing countries where malaria is endemic. Human-microscopic examination of blood smears remains the ‘gold standard’ for malaria diagnosis and despite its major drawbacks; other non-microscopic methodologies have not been able to outperform it.
This has prompted Global Health organisations to emphasise the urgent need for tools to overcome the deficiencies of human-operated optical-microscopy malaria diagnosis and other non-microscopic tests.
Enter the Fast Accurate and Scalable malaria (FASt-Mal) diagnosis device. A multidisciplinary team led by Delmiro Fernandez-Reyes, Reader in Digital Health & Intelligent Systems at UCL Computer Science, Mandayam A. Srinivasan, John Shawe-Taylor and Iasonas Kokkinos (UCL Department of Computer Science) and Biobele J. Brown, Ikeoluwa Lagunju and Olugbemiro Sodeinde (COMUI Department of Paediatrics), is researching this to produce a novel fast robotic-automated computational system capable of reliably diagnosing malaria in sub-Saharan West-Africa.
In 2017, the team was awarded a £1.5 million EPSRC Global Challenges Research Fund (GCRF). The funding is being used to carry out engineering (robotics), computational research (computer vision and machine learning) and digital health clinical research (paediatric infectious diseases) to design, implement, deploy and test an artificial intelligence driven automated system capable of tackling the challenges posed by human-operated light-microscopy currently used in the diagnosis of malaria.
After a decade of research, it is clear that the next leap to tackle several developmental challenges (including malaria) can be made possible through the application of engineering and computational sciences. Current work on FASt-Mal is a case in point; AI and data-sciences can harness data collected over a decade and provide robotic accurate solutions for malaria diagnosis and other interventions that will be fundamental for malaria control in the region.