{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:51:03Z","timestamp":1767984663481,"version":"3.49.0"},"reference-count":44,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,3,19]],"date-time":"2023-03-19T00:00:00Z","timestamp":1679184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Canadian Institutes of Health Research","award":["202110LT5"],"award-info":[{"award-number":["202110LT5"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Acute myeloid leukemia (AML) is a type of blood cancer that affects both adults and children. Benzene exposure has been reported to increase the risk of developing AML in children. The assessment of the potential relationship between environmental benzene exposure and childhood has been documented in the literature using odds ratios and\/or risk ratios, with data fitted to unconditional logistic regression. A common feature of the studies involving relationships between environmental risk factors and health outcomes is the lack of proper analysis to evidence causation. Although statistical causal analysis is commonly used to determine causation by evaluating a distribution\u2019s parameters, it is challenging to infer causation in complex systems from single correlation coefficients. Machine learning (ML) approaches, based on causal pattern recognition, can provide an accurate alternative to model counterfactual scenarios. In this work, we propose a framework using average treatment effect (ATE) and Uplift modeling to evidence causation when relating exposure to benzene indoors and outdoors to childhood AML, effectively predicting causation when exposed indoors to this contaminant. An analysis of the assumptions, cross-validation, sample size, and interaction between predictors are also provided, guiding future works looking at the universalization of this approach in predicting health outcomes.<\/jats:p>","DOI":"10.3390\/a16030166","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T03:09:37Z","timestamp":1679281777000},"page":"166","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Framework for Evaluating Potential Causes of Health Risk Factors Using Average Treatment Effect and Uplift Modelling"],"prefix":"10.3390","volume":"16","author":[{"given":"Daniela","family":"Galatro","sequence":"first","affiliation":[{"name":"Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, Canada"}]},{"given":"Rosario","family":"Trigo-Ferre","sequence":"additional","affiliation":[{"name":"Faculty of Applied Science and Engineering, University of Toronto, Toronto, ON M5S 3E5, Canada"}]},{"given":"Allana","family":"Nakashook-Zettler","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, Canada"}]},{"given":"Vincenzo","family":"Costanzo-Alvarez","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada"}]},{"given":"Melanie","family":"Jeffrey","sequence":"additional","affiliation":[{"name":"Centre for Indigenous Studies, University of Toronto, Toronto, ON M5S 2J7, Canada"}]},{"given":"Maria","family":"Jacome","sequence":"additional","affiliation":[{"name":"Faculty of Applied Sciences and Technology, Humber Institute of Technology and Advanced Learning, Toronto, ON M9W 5L7, Canada"}]},{"given":"Jason","family":"Bazylak","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4314-8120","authenticated-orcid":false,"given":"Cristina H.","family":"Amon","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, Canada"},{"name":"Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,19]]},"reference":[{"key":"ref_1","unstructured":"(2023, February 08). What Is Acute Myeloid Leukemia (AML)? What Is AML?. Available online: https:\/\/www.cancer.org\/cancer\/acute-myeloid-leukemia\/about\/what-is-aml.html."},{"key":"ref_2","unstructured":"(2023, February 08). Administrator Just Diagnosed, Just Diagnosed with Acute Myeloid Leukemia (AML). Available online: https:\/\/childrensoncologygroup.org\/just-diagnosed-with-acute-myeloid-leukemia-aml-."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1093\/jnci\/86.22.1678","article-title":"Infant leukemia, topoisomerase II inhibitors, and the MLL gene","volume":"86","author":"Ross","year":"1994","journal-title":"JNCI J. Natl. Cancer Inst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/oxfordjournals.epirev.a036153","article-title":"Epidemiology of childhood leukemia, with a focus on infants","volume":"16","author":"Ross","year":"1994","journal-title":"Epidemiol. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.cbi.2010.01.002","article-title":"A review of the potential association between childhood leukemia and benzene","volume":"184","author":"Pyatt","year":"2010","journal-title":"Chem.-Biol. Interact."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1289\/ehp.9023","article-title":"Risk factors for acute leukemia in children: A review","volume":"115","author":"Belson","year":"2007","journal-title":"Environ. Health Perspect."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1289\/ehp.8982189","article-title":"Benzene and leukemia: An epidemiologic risk assessment","volume":"82","author":"Rinsky","year":"1989","journal-title":"Environ. Health Perspect."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1002\/ajim.20592","article-title":"Risk of leukemia and multiple myeloma associated with exposure to benzene and other organic solvents: Evidence from the Italian Multicenter Case-control study","volume":"51","author":"Costantini","year":"2008","journal-title":"Am. J. Ind. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1177\/0141076814562718","article-title":"The environment and disease: Association or causation?","volume":"108","author":"Hill","year":"2015","journal-title":"J. R. Soc. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1080\/10408444.2018.1518404","article-title":"Modernizing the Bradford Hill criteria for assessing causal relationships in observational data","volume":"48","author":"Cox","year":"2018","journal-title":"Crit. Rev. Toxicol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1055\/s-2008-1043877","article-title":"Erman case control study on childhood leukaemia\u2014Basic considerations, methodology and summary of the results","volume":"210","author":"Kaatsch","year":"1998","journal-title":"Klin. P\u00e4diatrie"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1002\/1097-0142(19880801)62:3<635::AID-CNCR2820620332>3.0.CO;2-3","article-title":"A population-based case-control study of childhood leukemia in Shanghai","volume":"62","author":"Shu","year":"1988","journal-title":"Cancer"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1002\/1097-0142(19890415)63:8<1457::AID-CNCR2820630802>3.0.CO;2-J","article-title":"Improvement in outcome for children with acute nonlymphocytic leukemia. A report from the Childrens Cancer Study Group","volume":"63","author":"Buckley","year":"1989","journal-title":"Cancer"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1177\/030089169007600501","article-title":"Parental occupation and other environmental factors in the etiology of leukemias and Non-Hodgkin\u2019S lymphomas in childhood: A case-control study","volume":"76","author":"Magnani","year":"1990","journal-title":"Tumori J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"564","DOI":"10.2105\/AJPH.91.4.564","article-title":"Household solvent exposures and childhood acute lymphoblastic leukemia","volume":"91","author":"Freedman","year":"2001","journal-title":"Am. J. Public Health"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1093\/aje\/kwj203","article-title":"Child and maternal household chemical exposure and the risk of acute leukemia in children with Down\u2019s syndrome: A Report from the Children\u2019s Oncology Group","volume":"164","author":"Alderton","year":"2006","journal-title":"Am. J. Epidemiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/978-1-60327-492-0_5","article-title":"Parental smoking and childhood leukemia","volume":"472","author":"Chang","year":"2009","journal-title":"Methods Mol. Biol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1038\/sj.leu.2404698","article-title":"Cigarette smoking, cytogenetic abnormalities, and acute myelogenous leukemia","volume":"21","author":"Lichtman","year":"2007","journal-title":"Leukemia"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s004200050186","article-title":"Environmental exposure to gasoline and leukemia in children and young adults-an ecology study","volume":"70","author":"Nordlinder","year":"1997","journal-title":"Int. Arch. Occup. Environ. Health"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1097\/01.ede.0000101749.28283.de","article-title":"Residential exposure to traffic in California and childhood cancer","volume":"15","author":"Reynolds","year":"2004","journal-title":"Epidemiology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1002\/ijc.11597","article-title":"Childhood leukemia and road traffic: A population-based case-control study","volume":"108","author":"Crosignani","year":"2003","journal-title":"Int. J. Cancer"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1136\/oem.2003.010868","article-title":"Acute childhood leukaemia and environmental exposure to potential sources of benzene and other hydrocarbons; a case-control study","volume":"61","author":"Steffen","year":"2004","journal-title":"Occup. Environ. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1136\/oem.56.11.774","article-title":"Analysis of incidence of childhood cancer in the West Midlands of the United Kingdom in relation to proximity to main roads and petrol stations","volume":"56","author":"Harrison","year":"1999","journal-title":"Occup. Environ. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1002\/ijc.31421","article-title":"Ambient benzene at the residence and risk for subtypes of childhood leukemia, lymphoma and CNS tumor","volume":"143","author":"Hvidtfeldt","year":"2018","journal-title":"Int. J. Cancer"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1016\/j.ijheh.2013.12.003","article-title":"Risk of leukemia in relation to exposure to Ambient Air Toxics in pregnancy and early childhood","volume":"217","author":"Heck","year":"2013","journal-title":"Int. J. Hyg. Environ. Health"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1002\/sim.9313","article-title":"Conditional or unconditional logistic regression for frequency matched case-control design?","volume":"41","author":"Wan","year":"2022","journal-title":"Stat. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3389\/fpubh.2018.00057","article-title":"Unconditional or conditional logistic regression model for age-matched case\u2013control data?","volume":"6","author":"Kuo","year":"2018","journal-title":"Front. Public Health"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"c315","DOI":"10.1159\/000323136","article-title":"Matching, an appealing method to avoid confounding?","volume":"118","author":"Jager","year":"2011","journal-title":"Nephron Clin. Pract."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"i969","DOI":"10.1136\/bmj.i969","article-title":"Analysis of matched case-control studies","volume":"352","author":"Pearce","year":"2016","journal-title":"BMJ"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1111\/j.1553-2712.2011.01185.x","article-title":"Logistic Regression: A brief primer","volume":"18","author":"Stoltzfus","year":"2011","journal-title":"Acad. Emerg. Med."},{"key":"ref_31","unstructured":"Gonfalonieri, A. (2023, February 08). Introduction to Causality in Machine Learning. Medium. Available online: https:\/\/towardsdatascience.com\/introduction-to-causality-in-machine-learning-4cee9467f06f."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"220638","DOI":"10.1098\/rsos.220638","article-title":"Causal machine learning for healthcare and Precision Medicine","volume":"9","author":"Sanchez","year":"2022","journal-title":"R. Soc. Open Sci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Venkatasubramaniam, A., Mateen, B.A., Shields, B.M., Hattersley, A.T., Jones, A.G., Vollmer, S.J., and Dennis, J.M. (2022). Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: An application for type 2 diabetes precision medicine. medRxiv.","DOI":"10.1101\/2022.11.07.22282023"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1214\/09-AOAS285","article-title":"Bart: Bayesian additive regression trees","volume":"4","author":"Chipman","year":"2010","journal-title":"Ann. Appl. Stat."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1139\/apnm-2021-0448","article-title":"Artificial intelligence in nutrition research: Perspectives on current and future applications","volume":"47","author":"Lamarche","year":"2022","journal-title":"Appl. Physiol. Nutr. Metab."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s12982-015-0037-4","article-title":"Applying the Bradford Hill criteria in the 21st Century: How data integration has changed causal inference in molecular epidemiology","volume":"12","author":"Fedak","year":"2015","journal-title":"Emerg. Themes Epidemiol."},{"key":"ref_37","unstructured":"Gailmard, S. (2018). Statistical Modeling and Inference for Social Science, Cambridge University Press."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v043.i11","article-title":"osDesign: An r package for the analysis, evaluation, and design of two-phase and case-control studies","volume":"43","author":"Haneuse","year":"2011","journal-title":"J. Stat. Softw."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"15828","DOI":"10.1021\/acs.est.2c02581","article-title":"Composition, emissions, and air quality impacts of hazardous air pollutants in unburned natural gas from residential stoves in California","volume":"56","author":"Lebel","year":"2022","journal-title":"Environ. Sci. Technol."},{"key":"ref_40","unstructured":"Centers for Disease Control and Prevention (2023, February 08). United States and Puerto Rico Cancer Statistics, 1999\u20132019 Incidence Request, Available online: https:\/\/wonder.cdc.gov\/cancer-v2019.HTML."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1177\/146642400112100109","article-title":"Personal exposure to benzene and the influence of attached and integral garages","volume":"121","author":"Mann","year":"2001","journal-title":"J. R. Soc. Promot. Health"},{"key":"ref_42","unstructured":"(2023, February 09). Uplift Modelling\u2014Github Pages. Available online: https:\/\/humboldt-wi.github.io\/blog\/research\/theses\/uplift_modeling_blogpost\/."},{"key":"ref_43","unstructured":"(2023, February 09). Quality Measures for Uplift Models\u2014Stochastic Solutions. Available online: https:\/\/www.stochasticsolutions.com\/pdf\/kdd2011late.pdf."},{"key":"ref_44","unstructured":"(2023, March 14). CHE408UofT\u2014Overview. Available online: https:\/\/github.com\/CHE408UofT."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/3\/166\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:58:36Z","timestamp":1760122716000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/3\/166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,19]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["a16030166"],"URL":"https:\/\/doi.org\/10.3390\/a16030166","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,19]]}}}