{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:56:48Z","timestamp":1770818208376,"version":"3.50.1"},"reference-count":67,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:00:00Z","timestamp":1670371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Efficient allocation of limited resources relies on accurate estimates of potential incremental benefits for each candidate. These heterogeneous treatment effects (HTE) can be estimated with properly specified theory-driven models and observational data that contain all confounders. Using causal machine learning to estimate HTE from big data offers higher benefits with limited resources by identifying additional heterogeneity dimensions and fitting arbitrary functional forms and interactions, but decisions based on black-box models are not justifiable.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Our solution is designed to increase resource allocation efficiency, enhance the understanding of the treatment effects, and increase the acceptance of the resulting decisions with a rationale that is in line with existing theory. The case study identifies the right individuals to incentivize for increasing their physical activity to maximize the population's health benefits due to reduced diabetes and heart disease prevalence. We leverage large-scale data from multi-wave nationally representative health surveys and theory from the published global meta-analysis results. We train causal machine learning ensembles, extract the heterogeneity dimensions of the treatment effect, sign, and monotonicity of its moderators with explainable AI, and incorporate them into the theory-driven model with our generalized linear model with the qualitative constraint (GLM_QC) method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The results show that the proposed methodology improves the expected health benefits for diabetes by 11% and for heart disease by 9% compared to the traditional approach of using the model specification from the literature and estimating the model with large-scale data. Qualitative constraints not only prevent counter-intuitive effects but also improve achieved benefits by regularizing the model.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2022.1015604","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T05:22:26Z","timestamp":1670390546000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Targeting resources efficiently and justifiably by combining causal machine learning and theory"],"prefix":"10.3389","volume":"5","author":[{"given":"Ozden","family":"Gur Ali","sequence":"first","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2022,12,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2642","DOI":"10.1287\/mnsc.2021.4004","article-title":"Gain-loss incentives and physical activity: the role of choice and wearable health tools","volume":"68","author":"Adjerid","year":"2022","journal-title":"Manage. Sci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e0232951","DOI":"10.1371\/journal.pone.0232951","article-title":"Estimating the potential impact of behavioral public health interventions nationally while maintaining agreement with global patterns on relative risks","volume":"15","author":"Ali","year":"2020","journal-title":"PLoS ONE"},{"key":"B3","first-page":"18","article-title":"\u201cLearning from sparse data by exploiting monotonicity constraints,\u201d","volume-title":"Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence","author":"Altendorf","year":"2012"},{"key":"B4","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inform. Fus."},{"key":"B5","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1509\/jmr.16.0163","article-title":"Retention futility: targeting high-risk customers might be ineffective","volume":"55","author":"Ascarza","year":"2018","journal-title":"J. Market. Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s40547-017-0080-0","article-title":"In pursuit of enhanced customer retention management: review, key issues, and future directions","volume":"5","author":"Ascarza","year":"2018","journal-title":"Customer Needs Solutions"},{"key":"B7","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1126\/science.aal4321","article-title":"Beyond prediction: using big data for policy problems","volume":"355","author":"Athey","year":"2017","journal-title":"Science"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7353","DOI":"10.1073\/pnas.1510489113","article-title":"Recursive partitioning for heterogeneous causal effects","volume":"113","author":"Athey","year":"2016","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1214\/18-AOS1709","article-title":"Generalized random forests","volume":"47","author":"Athey","year":"2019","journal-title":"Ann. Stat."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2014.0129","article-title":"\u201cResearch in public health for efficient, effective, and equitable outcomes,\u201d","author":"Ayer","year":"2014","journal-title":"Bridging Data and Decisions. INFORMS"},{"key":"B11","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3389\/fpubh.2019.00042","article-title":"Optimizing precision medicine for public health","volume":"7","author":"Bilkey","year":"2019","journal-title":"Front. Public Health"},{"key":"B12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1287\/mnsc.2018.3271","article-title":"The structure of health incentives: evidence from a field experiment","volume":"66","author":"Carrera","year":"2020","journal-title":"Manage. Sci."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788613","article-title":"\u201cIntelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission,\u201d","author":"Caruana","year":"2015","journal-title":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"B15","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1177\/0898264316688791","article-title":"Outcomes of a digital health program with human coaching for diabetes risk reduction in a Medicare population","volume":"30","author":"Castro Sweet","year":"2018","journal-title":"J. Aging Health"},{"key":"B16","volume-title":"Double\/Debiased Machine Learning for Treatment and Structural Parameters.","author":"Chernozhukov","year":"2018"},{"key":"B17","unstructured":"ChipmanH.\n            GeorgeE.\n            McCullochR.\n          Bayesian ensemble learning. 2006"},{"key":"B18","doi-asserted-by":"publisher","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":"B19","doi-asserted-by":"publisher","first-page":"113664","DOI":"10.1016\/j.dss.2021.113664","article-title":"Interpretable data science for decision making","volume":"150","author":"Coussement","year":"2021","journal-title":"Decis. Support Syst."},{"key":"B20","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1002\/sim.5933","article-title":"Qualitative interaction trees: a tool to identify qualitative treatment-subgroup interactions","volume":"33","author":"Dusseldorp","year":"2014","journal-title":"Stat. Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"8472391","DOI":"10.1155\/2016\/8472391","article-title":"Adaptation and feasibility study of a digital health program to prevent diabetes among low-income patients: results from a partnership between a digital health company and an academic research team","volume":"2016","author":"Fontil","year":"2016","journal-title":"J. Diabetes Res."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","author":"Friedman","year":"2010","journal-title":"J. Stat. Softw"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1016\/S0140-6736(17)32336-X","article-title":"Global, regional, and national comparative risk assessment of 84 behavioural, environmental and occupational, and metabolic risks or clusters of risks, 1990\u20132016: a systematic analysis for the Global Burden of Disease Study 2016","volume":"390","author":"Gakidou","year":"2017","journal-title":"Lancet"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511790942","volume-title":"Data Analysis Using Regression and Multilevel\/Hierarchical Models","author":"Gelman","year":"2006"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99740-7_21","article-title":"\u201cExplainable AI: the new 42?,\u201d","author":"Goebel","year":"2018","journal-title":"International Cross-Domain Conference for Machine Learning and Knowledge Extraction"},{"key":"B26","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1016\/j.ejor.2019.11.030","article-title":"Response transformation and profit decomposition for revenue uplift modeling","volume":"283","author":"Gubela","year":"2020","journal-title":"Eur. J. Oper. Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1214\/18-STS665","article-title":"Nonparametric shape-restricted regression","volume":"33","author":"Guntuboyina","year":"2018","journal-title":"Stat. Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e3319","DOI":"10.1002\/dmrr.3319","article-title":"Diabetes is a risk factor for the progression and prognosis of COVID-19","volume":"36","author":"Guo","year":"2020","journal-title":"Diabetes Metab. Res. Rev."},{"key":"B29","volume-title":"An Introduction to Machine Learning Interpretability","author":"Hall","year":"2019"},{"key":"B30","unstructured":"HastieT.\n            QianJ.\n          2014"},{"key":"B31","volume-title":"Generalized Additive Models. Vol. 43","author":"Hastie","year":"1990"},{"key":"B32","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/j.ejor.2021.05.045","article-title":"Targeting customers under response-dependent costs","volume":"297","author":"Haupt","year":"2022","journal-title":"Eur. J. Oper. Res."},{"key":"B33","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1146\/annurev-statistics-031219-041110","article-title":"Bayesian additive regression trees: a review and look forward","volume":"7","author":"Hill","year":"2020","journal-title":"Annu. Rev. Stat. Appl"},{"key":"B34","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1198\/jcgs.2010.08162","article-title":"Bayesian nonparametric modeling for causal inference","volume":"20","author":"Hill","year":"2011","journal-title":"J. Comput. Graph. Stat."},{"key":"B35","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1287\/msom.2017.0659","article-title":"OM forum-Causal inference models in operations management","volume":"19","author":"Ho","year":"2017","journal-title":"Manuf. Serv. Oper. Manag."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1111\/jocs.14596","article-title":"At the heart of COVID-19","volume":"35","author":"Khan","year":"2020","journal-title":"J. Card. Surg."},{"key":"B37","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.ecosta.2019.02.001","article-title":"Oracle inequalities for sign constrained generalized linear models","volume":"11","author":"Koike","year":"2019","journal-title":"Econ. Stat."},{"key":"B38","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.1073\/pnas.1804597116","article-title":"Metalearners for estimating heterogeneous treatment effects using machine learning","volume":"116","author":"K\u00fcnzel","year":"2019","journal-title":"Proc. Nat. Acad. Sci. USA"},{"key":"B39","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1080\/01621459.2016.1264957","article-title":"Bayesian regression trees for high-dimensional prediction and variable selection","volume":"113","author":"Linero","year":"2018","journal-title":"J. Am. Stat. Assoc."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339556","article-title":"\u201cIntelligible models for classification and regression,\u201d","author":"Lou","year":"2012","journal-title":"Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487579","article-title":"\u201cAccurate intelligible models with pairwise interactions,\u201d","author":"Lou","year":"2013","journal-title":"Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1109\/EMBC48229.2022.9872018","article-title":"\u201cEstimating heterogeneous causal effect of polysubstance usage on drug overdose from large-scale electronic health record,\u201d","author":"Mahipal","year":"2022","journal-title":"2022 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1201\/9780203753736","volume-title":"Generalized Linear Models.","author":"McCullagh","year":"2019"},{"key":"B44","author":"McCulloch","year":"2019","journal-title":"BART: Bayesian Additive Regression Trees."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1214\/13-EJS818","article-title":"Sign-constrained least squares estimation for high-dimensional regression","volume":"7","author":"Meinshausen","year":"2013","journal-title":"Electron. J. Stat."},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1145\/3368555.3384456","article-title":"\u201cInterpretable subgroup discovery in treatment effect estimation with application to opioid prescribing guidelines,\u201d","author":"Nagpal","year":"2020","journal-title":"Proceedings of the ACM Conference on Health, Inference, and Learning"},{"key":"B47","article-title":"Interpretml: a unified framework for machine learning interpretability","author":"Nori","year":"2019","journal-title":"arXiv preprint arXiv:"},{"key":"B48","unstructured":"Deep structural causal models for tractable counterfactual inference857869\n            PawlowskiN.\n            Coelho de CastroD.\n            GlockerB.\n          Adv. Neural Inf. Process. Syst.332020"},{"key":"B49","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/s42256-020-0197-y","article-title":"Causal inference and counterfactual prediction in machine learning for actionable healthcare","volume":"2","author":"Prosperi","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"B50","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s11222-013-9448-7","article-title":"Shape constrained additive models","volume":"25","author":"Pya","year":"2015","journal-title":"Stat. Comput."},{"key":"B51","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies","volume":"66","author":"Rubin","year":"1974","journal-title":"J. Educ. Psychol."},{"key":"B52","article-title":"Distance between homes and exercise facilities related to frequency of exercise among San Diego residents","author":"Sallis","year":"1990","journal-title":"Public Health Rep."},{"key":"B53","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-28954-6","volume-title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (vol. 11700)","author":"Samek","year":"2019"},{"key":"B54","doi-asserted-by":"publisher","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":"B55","doi-asserted-by":"publisher","first-page":"3004","DOI":"10.1214\/13-EJS868","article-title":"Non-negative least squares for high-dimensional linear models: consistency and sparse recovery without regularization","volume":"7","author":"Slawski","year":"2013","journal-title":"Electron. J. Stat."},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/09-STS313","article-title":"Matching methods for causal inference: a review and a look forward","volume":"25","author":"Stuart","year":"2010","journal-title":"Stat. Sci."},{"key":"B57","unstructured":"Facilitating score and causal inference trees for large observational studies2955\n            SuX.\n            KangJ.\n            FanJ.\n            LevineR. A.\n            YanX.\n          J. Mach. Learn. Res.132012"},{"key":"B58","unstructured":"TibshiraniJ.\n            AtheyS.\n            WagerS.\n            FriedbergR.\n            MinerL.\n            WrightM.\n          grf: Generalized Random Forests (Beta). R Package Version 0.102018"},{"key":"B59","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1093\/biostatistics\/kxs019","article-title":"Efficient estimation of the attributable fraction when there are monotonicity constraints and interactions","volume":"14","author":"Traskin","year":"2013","journal-title":"Biostatistics"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1145\/3527154","article-title":"D'ya like DAGs? A survey on structure learning and causal discovery","author":"Vowels","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"B61","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"J. Am. Stat. Assoc."},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2021.1143","article-title":"Causal rule sets for identifying subgroups with enhanced treatment effects","author":"Wang","year":"2022","journal-title":"INFORMS J. Comput"},{"key":"B63","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1016\/j.jclinepi.2009.11.020","article-title":"Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression","volume":"63","author":"Westreich","year":"2010","journal-title":"J. Clin. Epidemiol."},{"key":"B64","unstructured":"Fact Sheets2019"},{"key":"B65","article-title":"Adversarial counterfactual augmentation: application in Alzheimer's disease classification","author":"Xia","year":"2022","journal-title":"arXiv preprint arXiv:"},{"key":"B66","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.1001\/jama.280.19.1690","article-title":"What's the relative risk? A method of correcting the odds ratio in cohort studies of common outcomes","volume":"280","author":"Zhang","year":"1998","journal-title":"JAMA"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26989-4_4","article-title":"\u201cAn overview of concept drift applications,\u201d","author":"\u017dliobaite","year":"2016","journal-title":"Big Data Analysis: New Algorithms for a New Society"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1015604\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T05:22:46Z","timestamp":1670390566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2022.1015604\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,7]]},"references-count":67,"alternative-id":["10.3389\/frai.2022.1015604"],"URL":"https:\/\/doi.org\/10.3389\/frai.2022.1015604","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,7]]},"article-number":"1015604"}}