Louis Anthony Cox Jr. , R. Jeffrey Lewis , Saumitra V. Rege , Shubham Singh
{"title":"人工智能辅助暴露-反应数据分析:量化暴露对生存时间的异质性因果效应。","authors":"Louis Anthony Cox Jr. , R. Jeffrey Lewis , Saumitra V. Rege , Shubham Singh","doi":"10.1016/j.gloepi.2024.100179","DOIUrl":null,"url":null,"abstract":"<div><div>AI-assisted data analysis can help risk analysts better understand exposure-response relationships by making it relatively easy to apply advanced statistical and machine learning methods, check their assumptions, and interpret their results. This paper demonstrates the potential of large language models (LLMs), such as ChatGPT, to facilitate statistical analyses, including survival data analyses, for health risk assessments. Through AI-guided analyses using relatively recent and advanced methods such as Individual Conditional Expectation (ICE) plots using Random Survival Forests and Heterogeneous Treatment Effects (HTEs) estimated using Causal Survival Forests, population-level exposure-response functions can be disaggregated into individual-level exposure-response functions. These reveal the extent of heterogeneity in risks across individuals for different levels of exposure, holding other variables fixed. By applying these methods to an illustrative dataset on blood lead levels (BLL) and mortality risk among never-smoker men from the NHANES III survey, we show how AI can clarify inter-individual variations in exposure-associated risks. The results add insights not easily obtained from traditional parametric or semi-parametric models such as logistic regression and Cox proportional hazards models, illustrating the advantages of non-parametric approaches for quantifying heterogeneous causal effects on survival times. This paper also suggests some practical implications of using AI in regulatory health risk assessments and public policy decisions.</div></div>","PeriodicalId":36311,"journal":{"name":"Global Epidemiology","volume":"9 ","pages":"Article 100179"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11757793/pdf/","citationCount":"0","resultStr":"{\"title\":\"AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times\",\"authors\":\"Louis Anthony Cox Jr. , R. Jeffrey Lewis , Saumitra V. Rege , Shubham Singh\",\"doi\":\"10.1016/j.gloepi.2024.100179\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>AI-assisted data analysis can help risk analysts better understand exposure-response relationships by making it relatively easy to apply advanced statistical and machine learning methods, check their assumptions, and interpret their results. This paper demonstrates the potential of large language models (LLMs), such as ChatGPT, to facilitate statistical analyses, including survival data analyses, for health risk assessments. Through AI-guided analyses using relatively recent and advanced methods such as Individual Conditional Expectation (ICE) plots using Random Survival Forests and Heterogeneous Treatment Effects (HTEs) estimated using Causal Survival Forests, population-level exposure-response functions can be disaggregated into individual-level exposure-response functions. These reveal the extent of heterogeneity in risks across individuals for different levels of exposure, holding other variables fixed. By applying these methods to an illustrative dataset on blood lead levels (BLL) and mortality risk among never-smoker men from the NHANES III survey, we show how AI can clarify inter-individual variations in exposure-associated risks. The results add insights not easily obtained from traditional parametric or semi-parametric models such as logistic regression and Cox proportional hazards models, illustrating the advantages of non-parametric approaches for quantifying heterogeneous causal effects on survival times. This paper also suggests some practical implications of using AI in regulatory health risk assessments and public policy decisions.</div></div>\",\"PeriodicalId\":36311,\"journal\":{\"name\":\"Global Epidemiology\",\"volume\":\"9 \",\"pages\":\"Article 100179\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-12-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11757793/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Global Epidemiology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2590113324000452\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Epidemiology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590113324000452","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times
AI-assisted data analysis can help risk analysts better understand exposure-response relationships by making it relatively easy to apply advanced statistical and machine learning methods, check their assumptions, and interpret their results. This paper demonstrates the potential of large language models (LLMs), such as ChatGPT, to facilitate statistical analyses, including survival data analyses, for health risk assessments. Through AI-guided analyses using relatively recent and advanced methods such as Individual Conditional Expectation (ICE) plots using Random Survival Forests and Heterogeneous Treatment Effects (HTEs) estimated using Causal Survival Forests, population-level exposure-response functions can be disaggregated into individual-level exposure-response functions. These reveal the extent of heterogeneity in risks across individuals for different levels of exposure, holding other variables fixed. By applying these methods to an illustrative dataset on blood lead levels (BLL) and mortality risk among never-smoker men from the NHANES III survey, we show how AI can clarify inter-individual variations in exposure-associated risks. The results add insights not easily obtained from traditional parametric or semi-parametric models such as logistic regression and Cox proportional hazards models, illustrating the advantages of non-parametric approaches for quantifying heterogeneous causal effects on survival times. This paper also suggests some practical implications of using AI in regulatory health risk assessments and public policy decisions.