{"title":"使用 XGBoost 回归和 SHAP 方法分析 2018 年捷克共和国多种死因的相关因素","authors":"Bety Ukolova, Boris Burcin","doi":"10.54694/dem.0331","DOIUrl":null,"url":null,"abstract":"This study focuses on the factors that are associated with recording multiple causes as the cause of death in Czechia. An XGBoost multiple regression is used in the analysis and its results are interpreted with SHAP values. The most significant factors associated with the number of causes of death, ranked in order of importance, are the place of death, the region, and the underlying cause of death. Age and autopsy also contribute, albeit to a lesser extent. Several important interactions were identified as well.","PeriodicalId":507690,"journal":{"name":"Demografie","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analýza faktorů asociovaných s vícečetnými příčinami smrti v Česku v roce 2018 pomocí XGBoost regrese a metody SHAP\",\"authors\":\"Bety Ukolova, Boris Burcin\",\"doi\":\"10.54694/dem.0331\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study focuses on the factors that are associated with recording multiple causes as the cause of death in Czechia. An XGBoost multiple regression is used in the analysis and its results are interpreted with SHAP values. The most significant factors associated with the number of causes of death, ranked in order of importance, are the place of death, the region, and the underlying cause of death. Age and autopsy also contribute, albeit to a lesser extent. Several important interactions were identified as well.\",\"PeriodicalId\":507690,\"journal\":{\"name\":\"Demografie\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Demografie\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.54694/dem.0331\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Demografie","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.54694/dem.0331","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Analýza faktorů asociovaných s vícečetnými příčinami smrti v Česku v roce 2018 pomocí XGBoost regrese a metody SHAP
This study focuses on the factors that are associated with recording multiple causes as the cause of death in Czechia. An XGBoost multiple regression is used in the analysis and its results are interpreted with SHAP values. The most significant factors associated with the number of causes of death, ranked in order of importance, are the place of death, the region, and the underlying cause of death. Age and autopsy also contribute, albeit to a lesser extent. Several important interactions were identified as well.