Supporting elimination of lymphatic filariasis in Samoa by predicting locations of residual infection using machine learning and geostatistics

Abstract

The global elimination of lymphatic filariasis (LF) is a major focus of the World Health Organization. One key challenge is locating residual infections that can perpetuate the transmission cycle. We show how a targeted sampling strategy using predictions from a geospatial model, combining random forests and geostatistics, can improve the sampling efficiency for identifying locations with high infection prevalence. Predictions were made based on the household locations of infected persons identified from previous surveys, and environmental variables relevant to mosquito density. Results show that targeting sampling using model predictions would have allowed 52% of infections to be identified by sampling just 17.7% of households. The odds ratio for identifying an infected individual in a household at a predicted high risk compared to a predicted low risk location was 10.2 (95% CI 4.2–22.8). This study provides evidence that a ‘one size fits all’ approach is unlikely to yield optimal results when making programmatic decisions based on model predictions. Instead, model assumptions and definitions should be tailored to each situation based on the objective of the surveillance program. When predictions are used in the context of the program objectives, they can result in a dramatic improvement in the efficiency of locating infected individuals.

Lymphatic filariasis epidemiology in Samoa in 2018: Geographic clustering and higher antigen prevalence in older age groups

“…household members, adult males) and high prevalence locations. Heterogeneity (clustering) observed between and within PSUs and households also leads to consideration of different sampling strategies including spatially explicit sampling and prediction [ 42 ], adaptive or snowball sampling [ 43 ], the use of markers that are potentially more sensitive than Ag or Mf (e.g. anti-filarial antibodies [ 27 , 41 , 44 ]), molecular xenomonitoring of mosquitoes [ 45 – 48 ], or combinations of these.…”

“…Follow-up surveys will assess the impact of two rounds of triple-drug MDA on transmission. Other surveillance strategies being investigated in Samoa include spatial sampling strategies [ 42 ] and molecular xenomonitoring.…”

Lymphatic Filariasis Epidemiology in Samoa in 2018: Geographic Clustering and Higher Antigen Prevalence in Older Age Groups

“…household members, adult males) and high prevalence locations. Heterogeneity (clustering) observed between and within PSUs and households also leads to consideration of different sampling strategies including spatially explicit sampling and prediction [43], adaptive or snowball sampling [44], and the use of markers that are potentially more sensitive than Ag or Mf e.g. anti-filarial antibodies [32,42,45], molecular xenomonitoring of mosquitoes [46-49], or combinations of these.…”

“…Follow-up surveys will assess the impact of two rounds of triple-drug MDA on transmission. Other surveillance strategies being investigated in Samoa include spatial sampling strategies [43] and molecular xenomonitoring.…”

The Importance of Partnership in the Rollout of Triple-Drug Therapy to Eliminate Lymphatic Filariasis in the Pacific

“…5,7 A series of studies has also demonstrated persistent transmission of LF in some of these countries, and research partners have provided continuous feedback to relevant health ministries/departments to emphasize the critical importance of intensifying and sustaining LF interventions to relevant health ministries/departments. [8][9][10][11][12][13][14][15][16] All these factors combined have made the development of a new strategy to accelerate LF elimination crucial.…”