{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:12:03Z","timestamp":1753881123401,"version":"3.41.2"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"abstract":"<jats:p>Precise estimation of treatment effects is crucial for accurately evaluating the intervention. While deep learning models have exhibited promising performance in learning counterfactual representations for treatment effect estimation (TEE), a major limitation in most of these models is that they often overlook the diversity of treatment effects across potential subgroups that have varying treatment effects and characteristics, treating the entire population as a homogeneous group. This limitation restricts the ability to precisely estimate treatment effects and provide targeted treatment recommendations. In this paper, we propose a novel treatment effect estimation model, named SubgroupTE, which incorporates subgroup identification in TEE. SubgroupTE identifies heterogeneous subgroups with different responses and more precisely estimates treatment effects by considering subgroup-specific treatment effects in the estimation process. In addition, we introduce an expectation\u2013maximization (EM)-based training process that iteratively optimizes estimation and subgrouping networks to improve both estimation and subgroup identification. Comprehensive experiments on the synthetic and semi-synthetic datasets demonstrate the outstanding performance of SubgroupTE compared to the existing works for treatment effect estimation and subgrouping models. Additionally, a real-world study demonstrates the capabilities of SubgroupTE in enhancing targeted treatment recommendations for patients with opioid use disorder (OUD) by incorporating subgroup identification with treatment effect estimation.<\/jats:p>","DOI":"10.1145\/3718097","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T17:45:03Z","timestamp":1742406303000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SubgroupTE: Advancing Treatment Effect Estimation with Subgroup Identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7153-0680","authenticated-orcid":false,"given":"Seungyeon","family":"Lee","sequence":"first","affiliation":[{"name":"The Ohio State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-0651","authenticated-orcid":false,"given":"Ruoqi","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6146-4093","authenticated-orcid":false,"given":"Wenyu","family":"Song","sequence":"additional","affiliation":[{"name":"Harvard Medical School, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0746-1809","authenticated-orcid":false,"given":"Lang","family":"Li","sequence":"additional","affiliation":[{"name":"The Ohio State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4601-0779","authenticated-orcid":false,"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Ohio State University, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2020. MarketScan Research Databases. https:\/\/www.ibm.com\/products\/marketscan-research-databases"},{"key":"e_1_2_1_2_1","volume-title":"Bayesian inference of individualized treatment effects using multi-task gaussian processes. Advances in neural information processing systems 30","author":"Alaa M","year":"2017","unstructured":"Ahmed\u00a0M Alaa and Mihaela Van Der\u00a0Schaar. 2017. Bayesian inference of individualized treatment effects using multi-task gaussian processes. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_1_3_1","unstructured":"Peniel\u00a0N Argaw Elizabeth Healey and Isaac\u00a0S Kohane. 2022. Identifying Heterogeneous Treatment Effects in Multiple Outcomes using Joint Confidence Intervals. In Machine Learning for Health. PMLR 141\u2013170."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. 1027\u20131035","author":"Arthur David","year":"2007","unstructured":"David Arthur and Sergei Vassilvitskii. 2007. K-means++ the advantages of careful seeding. In Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. 1027\u20131035."},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","first-page":"e0205971","DOI":"10.1371\/journal.pone.0205971","article-title":"Subgroup identification in clinical trials via the predicted individual treatment effect","volume":"13","author":"Ballarini M","year":"2018","unstructured":"Nicol\u00e1s\u00a0M Ballarini, Gerd\u00a0K Rosenkranz, Thomas Jaki, Franz K\u00f6nig, and Martin Posch. 2018. Subgroup identification in clinical trials via the predicted individual treatment effect. PloS one 13, 10 (2018), e0205971.","journal-title":"PloS one"},{"key":"e_1_2_1_6_1","volume-title":"Random forests. Machine learning 45","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning 45 (2001), 5\u201332."},{"key":"e_1_2_1_7_1","doi-asserted-by":"crossref","first-page":"4227","DOI":"10.1002\/sim.9507","article-title":"CAPITAL: Optimal subgroup identification via constrained policy tree search","volume":"41","author":"Cai Hengrui","year":"2022","unstructured":"Hengrui Cai, Wenbin Lu, Rachel Marceau\u00a0West, Devan\u00a0V Mehrotra, and Lingkang Huang. 2022. CAPITAL: Optimal subgroup identification via constrained policy tree search. Statistics in Medicine 41, 21 (2022), 4227\u20134244.","journal-title":"Statistics in Medicine"},{"key":"e_1_2_1_8_1","volume-title":"Support-vector networks. Machine learning 20","author":"Cortes Corinna","year":"1995","unstructured":"Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine learning 20 (1995), 273\u2013297."},{"key":"e_1_2_1_9_1","first-page":"15883","article-title":"On inductive biases for heterogeneous treatment effect estimation","volume":"34","author":"Curth Alicia","year":"2021","unstructured":"Alicia Curth and Mihaela van\u00a0der Schaar. 2021. On inductive biases for heterogeneous treatment effect estimation. Advances in Neural Information Processing Systems 34 (2021), 15883\u201315894.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_10_1","volume-title":"Subgroup identification from randomized clinical trial data. Statistics in medicine 30, 24","author":"Foster C","year":"2011","unstructured":"Jared\u00a0C Foster, Jeremy\u00a0MG Taylor, and Stephen\u00a0J Ruberg. 2011. Subgroup identification from randomized clinical trial data. Statistics in medicine 30, 24 (2011), 2867\u20132880."},{"key":"e_1_2_1_11_1","volume-title":"Causal inference in public health. Annual review of public health 34","author":"Glass A","year":"2013","unstructured":"Thomas\u00a0A Glass, Steven\u00a0N Goodman, Miguel\u00a0A Hern\u00e1n, and Jonathan\u00a0M Samet. 2013. Causal inference in public health. Annual review of public health 34 (2013), 61\u201375."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3886\/ICPSR09795.v1"},{"key":"e_1_2_1_13_1","volume-title":"History of the discovery, development, and FDA-approval of buprenorphine medications for the treatment of opioid use disorder. Drug and Alcohol Dependence Reports","author":"Heidbreder Christian","year":"2023","unstructured":"Christian Heidbreder, Paul\u00a0J Fudala, and Mark\u00a0K Greenwald. 2023. History of the discovery, development, and FDA-approval of buprenorphine medications for the treatment of opioid use disorder. Drug and Alcohol Dependence Reports (2023), 100133."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1198\/jcgs.2010.08162"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1111\/add.13795","article-title":"Hospitalizations, costs and outcomes associated with heroin and prescription opioid overdoses in the United States 2001\u201312","volume":"112","author":"Hsu J","year":"2017","unstructured":"Douglas\u00a0J Hsu, Ellen\u00a0P McCarthy, Jennifer\u00a0P Stevens, and Kenneth\u00a0J Mukamal. 2017. Hospitalizations, costs and outcomes associated with heroin and prescription opioid overdoses in the United States 2001\u201312. Addiction 112, 9 (2017), 1558\u20131564.","journal-title":"Addiction"},{"volume-title":"Identification and estimation of causal effects of multiple treatments under the conditional independence assumption","author":"Lechner Michael","key":"e_1_2_1_16_1","unstructured":"Michael Lechner. 2001. Identification and estimation of causal effects of multiple treatments under the conditional independence assumption. Springer."},{"key":"e_1_2_1_17_1","first-page":"2282","article-title":"Robust recursive partitioning for heterogeneous treatment effects with uncertainty quantification","volume":"33","author":"Lee Hyun-Suk","year":"2020","unstructured":"Hyun-Suk Lee, Yao Zhang, William Zame, Cong Shen, Jang-Won Lee, and Mihaela van\u00a0der Schaar. 2020. Robust recursive partitioning for heterogeneous treatment effects with uncertainty quantification. Advances in Neural Information Processing Systems 33 (2020), 2282\u20132292.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_18_1","volume-title":"Causal rule ensemble: Interpretable inference of heterogeneous treatment effects. arXiv preprint arXiv:2009.09036","author":"Lee Kwonsang","year":"2020","unstructured":"Kwonsang Lee, Falco\u00a0J Bargagli-Stoffi, and Francesca Dominici. 2020. Causal rule ensemble: Interpretable inference of heterogeneous treatment effects. arXiv preprint arXiv:2009.09036 (2020)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00127"},{"key":"e_1_2_1_20_1","volume-title":"Identification of subgroups with differential treatment effects for longitudinal and multiresponse variables. Statistics in medicine 35, 26","author":"Loh Wei-Yin","year":"2016","unstructured":"Wei-Yin Loh, Haoda Fu, Michael Man, Victoria Champion, and Menggang Yu. 2016. Identification of subgroups with differential treatment effects for longitudinal and multiresponse variables. Statistics in medicine 35, 26 (2016), 4837\u20134855."},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1053\/j.ajkd.2018.07.015","article-title":"Effects of intensive blood pressure lowering on kidney tubule injury in CKD: a longitudinal subgroup analysis in SPRINT","volume":"73","author":"Malhotra Rakesh","year":"2019","unstructured":"Rakesh Malhotra, Timothy Craven, Walter\u00a0T Ambrosius, Anthony\u00a0A Killeen, William\u00a0E Haley, Alfred\u00a0K Cheung, Michel Chonchol, Mark Sarnak, Chirag\u00a0R Parikh, Michael\u00a0G Shlipak, et\u00a0al. 2019. Effects of intensive blood pressure lowering on kidney tubule injury in CKD: a longitudinal subgroup analysis in SPRINT. American Journal of Kidney Diseases 73, 1 (2019), 21\u201330.","journal-title":"American Journal of Kidney Diseases"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512034"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384456"},{"key":"e_1_2_1_24_1","volume-title":"VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RmB-88r9dL","author":"Nie Lizhen","year":"2021","unstructured":"Lizhen Nie, Mao Ye, qiang liu, and Dan Nicolae. 2021. VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RmB-88r9dL"},{"key":"e_1_2_1_25_1","volume-title":"Who are we missing? a principled approach to characterizing the underrepresented population. arXiv preprint arXiv:2401.14512","author":"Parikh Harsh","year":"2024","unstructured":"Harsh Parikh, Rachael Ross, Elizabeth Stuart, and Kara Rudolph. 2024. Who are we missing? a principled approach to characterizing the underrepresented population. arXiv preprint arXiv:2401.14512 (2024)."},{"key":"e_1_2_1_26_1","volume-title":"et\u00a0al","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1007\/s11606-022-07732-w","article-title":"Variation in Clinical Characteristics and Longitudinal Outcomes in Individuals with Opioid Use Disorder Diagnosis Codes","volume":"38","author":"Powell D","year":"2023","unstructured":"Victoria\u00a0D Powell, Colin Macleod, Jeremy Sussman, Lewei\u00a0A Lin, Amy\u00a0SB Bohnert, and Pooja Lagisetty. 2023. Variation in Clinical Characteristics and Longitudinal Outcomes in Individuals with Opioid Use Disorder Diagnosis Codes. Journal of General Internal Medicine 38, 3 (2023), 699\u2013706.","journal-title":"Journal of General Internal Medicine"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0037350"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a034","author":"Schwab Patrick","year":"2020","unstructured":"Patrick Schwab, Lorenz Linhardt, Stefan Bauer, Joachim\u00a0M Buhmann, and Walter Karlen. 2020. Learning counterfactual representations for estimating individual dose-response curves. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a034. 5612\u20135619."},{"key":"e_1_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 3076\u20133085","author":"Shalit Uri","year":"2017","unstructured":"Uri Shalit, Fredrik\u00a0D Johansson, and David Sontag. 2017. Estimating individual treatment effect: generalization bounds and algorithms. In International Conference on Machine Learning. PMLR, 3076\u20133085."},{"key":"e_1_2_1_31_1","volume-title":"Update on barriers to pharmacotherapy for opioid use disorders. Current psychiatry reports 19","author":"Sharma Anjalee","year":"2017","unstructured":"Anjalee Sharma, Sharon\u00a0M Kelly, Shannon\u00a0Gwin Mitchell, Jan Gryczynski, Kevin\u00a0E O\u2019Grady, and Robert\u00a0P Schwartz. 2017. Update on barriers to pharmacotherapy for opioid use disorders. Current psychiatry reports 19 (2017), 1\u20138."},{"key":"e_1_2_1_32_1","volume-title":"Adapting neural networks for the estimation of treatment effects. Advances in neural information processing systems 32","author":"Shi Claudia","year":"2019","unstructured":"Claudia Shi, David Blei, and Victor Veitch. 2019. Adapting neural networks for the estimation of treatment effects. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_33_1","volume-title":"et\u00a0al","author":"Solomon Alina","year":"2018","unstructured":"Alina Solomon, Heidi Turunen, Tiia Ngandu, Markku Peltonen, Esko Lev\u00e4lahti, Seppo Helisalmi, Riitta Antikainen, Lars B\u00e4ckman, Tuomo H\u00e4nninen, Antti Jula, et\u00a0al. 2018. Effect of the apolipoprotein E genotype on cognitive change during a multidomain lifestyle intervention: a subgroup analysis of a randomized clinical trial. JAMA neurology 75, 4 (2018), 462\u2013470."},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","first-page":"101","DOI":"10.3390\/pharma1030010","article-title":"Evaluation of the Effectiveness of Buprenorphine-Naloxone on Opioid Overdose and Death among Insured Patients with Opioid Use Disorder in the United States","volume":"1","author":"Sun Tianyu","year":"2022","unstructured":"Tianyu Sun, Natallia Katenka, Stephen Kogut, Jeffrey Bratberg, Josiah Rich, and Ashley Buchanan. 2022. Evaluation of the Effectiveness of Buprenorphine-Naloxone on Opioid Overdose and Death among Insured Patients with Opioid Use Disorder in the United States. Pharmacoepidemiology 1, 3 (2022), 101\u2013112.","journal-title":"Pharmacoepidemiology"},{"key":"e_1_2_1_35_1","doi-asserted-by":"crossref","first-page":"e76","DOI":"10.1097\/PTS.0000000000000566","article-title":"The burden of opioid-related adverse drug events on hospitalized previously opioid-free surgical patients","volume":"17","author":"Urman D","year":"2021","unstructured":"Richard\u00a0D Urman, Diane\u00a0L Seger, Julie\u00a0M Fiskio, Bridget\u00a0A Neville, Elizabeth\u00a0M Harry, Scott\u00a0G Weiner, Belinda Lovelace, Randi Fain, Jessica Cirillo, and Jeffrey\u00a0L Schnipper. 2021. The burden of opioid-related adverse drug events on hospitalized previously opioid-free surgical patients. Journal of Patient Safety 17, 2 (2021), e76\u2013e83.","journal-title":"Journal of Patient Safety"},{"key":"e_1_2_1_36_1","unstructured":"U.S. Food and Drug Administration. 2023. Information about Medication-Assisted Treatment (MAT). https:\/\/www.fda.gov. Accessed: 2023-02-05."},{"key":"e_1_2_1_37_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_1_38_1","volume-title":"Comparative effectiveness of different treatment pathways for opioid use disorder. JAMA network open 3, 2","author":"Wakeman E","year":"2020","unstructured":"Sarah\u00a0E Wakeman, Marc\u00a0R Larochelle, Omid Ameli, Christine\u00a0E Chaisson, Jeffrey\u00a0Thomas McPheeters, William\u00a0H Crown, Francisca Azocar, and Darshak\u00a0M Sanghavi. 2020. Comparative effectiveness of different treatment pathways for opioid use disorder. JAMA network open 3, 2 (2020), e1920622\u2013e1920622."},{"key":"e_1_2_1_39_1","volume-title":"Causal rule sets for identifying subgroups with enhanced treatment effects. INFORMS journal on computing 34, 3","author":"Wang Tong","year":"2022","unstructured":"Tong Wang and Cynthia Rudin. 2022. Causal rule sets for identifying subgroups with enhanced treatment effects. INFORMS journal on computing 34, 3 (2022), 1626\u20131643."},{"key":"e_1_2_1_40_1","volume-title":"et\u00a0al","author":"Wang Yeming","year":"2020","unstructured":"Yeming Wang, Dingyu Zhang, Guanhua Du, Ronghui Du, Jianping Zhao, Yang Jin, Shouzhi Fu, Ling Gao, Zhenshun Cheng, Qiaofa Lu, et\u00a0al. 2020. Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial. The lancet 395, 10236 (2020), 1569\u20131578."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103364"},{"key":"e_1_2_1_42_1","volume-title":"Tree-based Subgroup Discovery In Electronic Health Records: Heterogeneity of Treatment Effects for DTG-containing Therapies. arXiv preprint arXiv:2208.14329","author":"Yang Jiabei","year":"2022","unstructured":"Jiabei Yang, Ann\u00a0W Mwangi, Rami Kantor, Issa\u00a0J Dahabreh, Monicah Nyambura, Allison Delong, Joseph\u00a0W Hogan, and Jon\u00a0A Steingrimsson. 2022. Tree-based Subgroup Discovery In Electronic Health Records: Heterogeneity of Treatment Effects for DTG-containing Therapies. arXiv preprint arXiv:2208.14329 (2022)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","first-page":"108686","DOI":"10.1016\/j.jsat.2021.108686","article-title":"Examining differences in retention on medication for opioid use disorder: An analysis of Ohio Medicaid data","volume":"136","author":"Zhang Pengyue","year":"2022","unstructured":"Pengyue Zhang, Krystel Tossone, Robert Ashmead, Tina Bickert, Emelie Bailey, Nathan\u00a0J Doogan, Aimee Mack, Schuyler Schmidt, and Andrea\u00a0E Bonny. 2022. Examining differences in retention on medication for opioid use disorder: An analysis of Ohio Medicaid data. Journal of Substance Abuse Treatment 136 (2022), 108686.","journal-title":"Journal of Substance Abuse Treatment"},{"key":"e_1_2_1_44_1","volume-title":"NeurIPS ML Safety Workshop.","author":"Zhang YiFan","year":"2022","unstructured":"YiFan Zhang, Hanlin Zhang, Zachary\u00a0Chase Lipton, Li\u00a0Erran Li, and Eric Xing. 2022. Exploring transformer backbones for heterogeneous treatment effect estimation. In NeurIPS ML Safety Workshop."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T17:50:58Z","timestamp":1742406658000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,19]]},"references-count":44,"alternative-id":["10.1145\/3718097"],"URL":"https:\/\/doi.org\/10.1145\/3718097","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2025,3,19]]},"assertion":[{"value":"2024-06-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3718097"}}