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 mo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Global Epidemiology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590113324000452 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558860199886848 |
|---|---|
| author | Louis Anthony Cox, Jr. R. Jeffrey Lewis Saumitra V. Rege Shubham Singh |
| author_facet | Louis Anthony Cox, Jr. R. Jeffrey Lewis Saumitra V. Rege Shubham Singh |
| author_sort | Louis Anthony Cox, Jr. |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-af2663a2d2084d92a0e4f317216373e0 |
| institution | Kabale University |
| issn | 2590-1133 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Global Epidemiology |
| spelling | doaj-art-af2663a2d2084d92a0e4f317216373e02025-01-06T04:08:54ZengElsevierGlobal Epidemiology2590-11332025-06-019100179AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival timesLouis Anthony Cox, Jr.0R. Jeffrey Lewis1Saumitra V. Rege2Shubham Singh3Cox Associates, Entanglement, and University of Colorado. 503 N. Franklin Street, Denver, Colorado, 80218, USA; Corresponding author.Kelly Services, Epidemiology Contractor (retired ExxonMobil Biomedical Sciences, Inc.), Lavallette, New Jersey, USAEpidemiology, ExxonMobil Biomedical Sciences, Inc.1545 U.S. Highway 22 East Annandale, NJ 08801-3059, USABusiness Analytics (BANA) Program, Business School, University of Colorado, 1475 Lawrence St. Denver, CO 80217-3364, USAAI-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.http://www.sciencedirect.com/science/article/pii/S2590113324000452AI-assisted data analysisICE plotsExposure-response modelingSurvival treesRandom survival ForestCausal Survival Forest |
| spellingShingle | Louis Anthony Cox, Jr. R. Jeffrey Lewis Saumitra V. Rege Shubham Singh AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times Global Epidemiology AI-assisted data analysis ICE plots Exposure-response modeling Survival trees Random survival Forest Causal Survival Forest |
| title | AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times |
| title_full | AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times |
| title_fullStr | AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times |
| title_full_unstemmed | AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times |
| title_short | AI-assisted exposure-response data analysis: Quantifying heterogeneous causal effects of exposures on survival times |
| title_sort | ai assisted exposure response data analysis quantifying heterogeneous causal effects of exposures on survival times |
| topic | AI-assisted data analysis ICE plots Exposure-response modeling Survival trees Random survival Forest Causal Survival Forest |
| url | http://www.sciencedirect.com/science/article/pii/S2590113324000452 |
| work_keys_str_mv | AT louisanthonycoxjr aiassistedexposureresponsedataanalysisquantifyingheterogeneouscausaleffectsofexposuresonsurvivaltimes AT rjeffreylewis aiassistedexposureresponsedataanalysisquantifyingheterogeneouscausaleffectsofexposuresonsurvivaltimes AT saumitravrege aiassistedexposureresponsedataanalysisquantifyingheterogeneouscausaleffectsofexposuresonsurvivaltimes AT shubhamsingh aiassistedexposureresponsedataanalysisquantifyingheterogeneouscausaleffectsofexposuresonsurvivaltimes |