Feature importance:Opening a soil-transmitted helminth machine learning model via SHAP

作     者：Carlos Matias Scavuzzo Juan Manuel Scavuzzo Micaela Natalia Campero Melaku Anegagrie Aranzazu Amor Aramendia Agustín Benito Victoria Periago 

作者机构：Instituto de Altos Estudios Espaciales Mario GulichUnivesidad Nacional de Cordoba-Comisi
on Nacional de Actividades Espaciales
Argentina Fundacion Mundo SanoMadridSpain National Centre for Tropical MedicineInstitute of Health Carlos IIIMadridSpain Fundacion Mundo SanoBuenos AiresArgentina Consejo Nacional de Investigaciones Científicasy Tecnicas(CONICET)Buenos AiresArgentina 

出 版 物：《Infectious Disease Modelling》 (传染病建模（英文）)

年 卷 期：2022年第7卷第1期

页      面：262-276页

学科分类：1204[管理学-公共管理] 1004[医学-公共卫生与预防医学(可授医学、理学学位)] 1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 0701[理学-数学] 10[医学] 

基　　金：funded by Fundacion Mundo Sano and Instituto de Salud Carlos III 

主　　题：Shap Shapley Machine learning Remote sensing Hookworm Ethiopia 

摘      要：In the field of landscape epidemiology,the contribution of machine learning(ML)to modeling of epidemiological risk scenarios presents itself as a good *** study aims to break with theblack boxparadigm that underlies the application of automatic learning techniques by using SHAP to determine the contribution of each variable in ML models applied to geospatial health,using the prevalence of hookworms,intestinal parasites,in Ethiopia,where they are widely distributed;the country bears the third-highest burden of hookworm in Sub-Saharan *** software was used,a very popular ML model,to fit and analyze the *** Python SHAP library was used to understand the importance in the trained model,of the variables for *** description of the contribution of these variables on a particular prediction was obtained,using different types of plot *** results show that the ML models are superior to the classical statistical models;not only demonstrating similar results but also explaining,by using the SHAP package,the influence and interactions between the variables in the generated *** analysis provides information to help understand the epidemiological problem presented and provides a tool for similar studies.