Health Security and Malaria: A Neural Network iOS Intelligent Platform to Create and Implement Seek and Destroy Integrated Larval Source Management (ILSM) Policies

Abstract

Malaria continues to be a burden to the healthcare system in Uganda and represents a regional and global health security issue. According to a 2019 WHO report, there are an estimated 18 million reported cases and over 15,000 estimated deaths in Uganda. This is an estimate as the real numbers of cases and deaths that have not been reported are likely to be much higher. 90% of the current >43 million inhabitants remain at risk of malaria, and it remains the leading cause of death, particularly among children, according to a Target Malaria Report (Kayondo in Target Malaria, Uganda Report, 2021). With an already strained healthcare system, malaria cases continue to comprise between 30 and 50% of all outpatient services and between 15 and 20% of hospitalizations. An intelligence–location based, AI machine learning, UAV classifier in an interactive, iOS, intelligent, cell phone, application (app) platform was employed to provide precise georeferenced, ArcGIS classified, real time, imaged, land use land cover (LULC) data of seasonal, georeferenced, sentinel site, malaria mosquito, Anopheles, [gambiae s.l., arabiensis s.s. and funestus s.l.]. breeding sites in an intervention agro-pastureland village site in the Gulu district of Uganda. Thereafter we continued to signature drone map all treated sub-county, entomological, district-level, capture point, intervention sites every 7–14 days to establish if new foci have occurred and treated those habitats. In so doing, we were able to ascertain valuable seasonal, entomological information [e.g., abiotic constraints such as temperature and habitat drying temporal sample frames for swamps/lagoons, transient pools and man-made holes] for optimally real time treating [Macro Seek and Destroy (S&D) i.e., real time, targeted, drone larviciding] sentinel site, productive, sub-county, district-level, seasonal, aquatic, Anopheline foci [e.g., a sewage pond in a turbid swamp during the rainy season, a puddle less than one meter that contains An. gambiae s.l. larvae along a commercial, pre-flooded, rural farmland road, An. arabiensis s.s. post-harvested tillers etc. We tested the hypothesis that a real time, environmentally friendly, larval habitat alteration [i.e., Macro S&D] could reduce aquatic, vector, larval, habitat density and blood parasite levels in treated and not suspected malaria patients at an agro-pastureland, malarious, intervention site. Another hypothesis we tested was timely malaria diagnosis and treatment [Micro S&D] is associated with low population parasitemia and lower malaria incidences. In 31 days, post-Macro S&D intervention, there was zero vector density, indoor, adult, female, Anopheles count as ascertained by pyrethrum spray catch at the intervention site. After a mean average of 62 days, blood parasite levels revealed a mean 0 count in timely diagnosed suspected and treated malaria patients. Implementing a real time Macro and Micro S&D intervention tool along with other existing tools [insecticide-treated mosquito nets (ITNs) indoor residual spraying of insecticides (Lin et al. in IEEE Int Conf Comput Vis (ICCV) 2017:2999–3007, 2017)] and proper policy measures [i.e., control and the strategies recommended by WHO such as bed-net distribution behavior change interventions including information, education, communication campaigns] in an entomological district-level intervention site can lower seasonal malaria prevalence either through timely modification of aquatic, Anopheles, larval habitats or through precisely targeted larvicide interventions. to achieve them. This chapter presents an innovative approach to managing and eradicating malaria thereby supporting solutions to a major global health security issue.