03723nas a2200301 4500000000100000008004100001260001600042653002100058653001300079653002800092653002000120100000900140700001200149700001200161700002500173700000900198700001000207700001100217700001100228700001500239700001100254245008200265856015300347300001400500490000600514520288700520022001403407 2024 d bElsevier BV10aMachine Learning10aZimbabwe10aTransmission risk model10aSchistosomiasis1 aLi H1 aZheng J1 aMidzi N1 aMutsaka- Makuvaza MJ1 aLv S1 aXia S1 aQian Y1 aXiao N1 aBerguist R1 aZhou X00aSchistosomiasis transmission in Zimbabwe: Modelling based on machine learning uhttps://www.sciencedirect.com/science/article/pii/S2468042724000836/pdfft?md5=0ca0fe15be3a0ff21ec6513e3e69e6d6&pid=1-s2.0-S2468042724000836-main.pdf a1081-10940 v93 a

Zimbabwe, located in Southern Africa, faces a significant public health challenge due to schistosomiasis. We investigated this issue with emphasis on risk prediction of schistosomiasis for the entire population. To this end, we reviewed available data on schistosomiasis in Zimbabwe from a literature search covering the 1980-2022 period considering the potential impact of 26 environmental and socioeconomic variables obtained from public sources. We studied the population requiring praziquantel with regard to whether or not mass drug administration (MDA) had been regularly applied. Three machine-learning algorithms were tested for their ability to predict the prevalence of schistosomiasis in Zimbabwe based on the mean absolute error (MAE), the root mean squared error (RMSE) and the coefficient of determination (R2). The findings revealed different roles of the 26 factors with respect to transmission and there were particular variations between Schistosoma haematobium and S. mansoni infections. We found that the top-five correlation factors, such as the past (rather than current) time, unsettled MDA implementation, constrained economy, high rainfall during the warmest season, and high annual precipitation were closely associated with higher S. haematobium prevalence, while lower elevation, high rainfall during the warmest season, steeper slope, past (rather than current) time, and higher minimum temperature in the coldest month were rather related to higher S. mansoni prevalence. The random forest (RF) algorithm was considered as the formal best model construction method, with MAE = 0.108; RMSE = 0.143; and R2 = 0.517 for S. haematobium, and with the corresponding figures for S. mansoni being 0.053; 0.082; and 0.458. Based on this optimal model, the current total schistosomiasis prevalence in Zimbabwe under MDA implementation was 19.8%, with that of S. haematobium at 13.8% and that of S. mansoni at 7.1%, requiring annual MDA based on a population of 3,003,928. Without MDA, the current total schistosomiasis prevalence would be 23.2%, that of S. haematobium 17.1% and that of S. mansoni prevalence at 7.4%, requiring annual MDA based on a population of 3,521,466. The study reveals that MDA alone is insufficient for schistosomiasis elimination, especially that due to S. mansoni. This study predicts a moderate prevalence of schistosomiasis in Zimbabwe, with its elimination requiring comprehensive control measures beyond the currently used strategies, including health education, snail control, population surveillance and environmental management.

 a2468-0427