Guide on Methodological Standards in Pharmacoepidemiology (2nd edition) and their series interpretation (18): analysis strategies and clinical applications of heterogeneity of treatment effect

Published on Jun. 29, 2026Total Views: 46 times Total Downloads: 10 times Download Mobile

Author: HUANG Tao ¹ SHEN Zhuoheng ¹  XU Yang ^1, ²

Affiliation: 1.Department of Pharmacy Administration and Clinical Pharmacy, School of Pharmaceutical Sciences, Peking University, Beijing 100191, China 2.Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing 100191, China

Keywords: Heterogeneity of treatment effect Pharmacoepidemiology Real-world data Subgroup analysis Risk modelling Effect modelling Causal machine learning Precision medicine

DOI: 10.12173/j.issn.1005-0698.202606071

Reference: Huang T, Shen ZH, Xu Y. Guide on Methodological Standards in Pharmacoepidemiology (2nd edition) and their series interpretation (18): analysis strategies and clinical applications of heterogeneity of treatment effect[J]. Chinese Journal of Pharmacoepidemiology, 2026, 35(6): 601-612. DOI: 10.12173/j.issn.1005-0698.202606071.[Article in Chinese]  Copied

Abstract
Full-text
References

Abstract

Heterogeneity of treatment effect (HTE) refers to non-random variation in the magnitude or direction of treatment effects across patient characteristics, disease states, or clinical contexts. With the development of precision medicine, real-world evidence, and regulatory science, HTE analysis has become an important methodological tool for bridging population-average evidence and individualized clinical decision-making. Based on the framework of the Guide on Methodological Standards in Pharmacoepidemiology (2nd edition), this article interprets the core concepts, estimands, scale dependence, and causal identification assumptions of HTE. It introduces three approaches of subgroup analysis, risk modelling, and effect modelling, with emphasis on their principles, applicable scenarios, implementation steps, and representative case studies. Furthermore, this article discusses implementation workflows, credibility assessment, reporting, and clinical translation in real-world data studies.

Full-text

Please download the PDF version to read the full text: download

References

1. KentDM, HaywardRA. Limitations of applying summary results of clinical trials to individual patients: the need for risk stratification[J]. JAMA, 2007, 298(10): 1209-1212. DOI: 10.1001/jama.298.10.1209.

2. KentDM, RothwellPM, IoannidisJP, et al. Assessing and reporting heterogeneity in treatment effects in clinical trials: a proposal[J]. Trials, 2010, 11: 85. DOI: 10.1186/1745-6215-11-85.

3. VaradhanR, SegalJB, BoydCM, et al. A framework for the analysis of heterogeneity of treatment effect in patient-centered outcomes research[J]. J Clin Epidemiol, 2013, 66(8): 818-825. DOI: 10.1016/j.jclinepi.2013.02.009.

4. SegalJB, VaradhanR, GroenwoldRHH, et al. Assessing heterogeneity of treatment effect in real-world data[J]. Ann Intern Med, 2023, 176(4): 536-544. DOI: 10.7326/M22-1510.

5. ThelenH, HennessyS. Characterizing treatment effect heterogeneity using real-world data[J]. Clin Pharmacol Ther, 2025, 117(5): 1209-1216. DOI: 10.1002/cpt.3627.

6. RubinDB. Causal inference using potential outcomes: design, modeling, decisions[J]. J Am Stat Assoc, 2005, 100(469): 322-331. DOI: 10.1198/016214504000001880.

7. HernanMA, RobinsJM. Causal inference: What if (First edition)[B]. Taylor and Francis, 2024.

8. KentDM, PaulusJK, van KlaverenD, et al. The predictive approaches to treatment effect heterogeneity (PATH) statement[J]. Ann Intern Med, 2020, 172(1): 35-45. DOI: 10.7326/M18-3667.

9. VanderWeeleTJ, KnolMJ. A tutorial on interaction[J]. Epidemiol Methods, 2014, 3(1): 33-72. https://hsph.harvard.edu/wp-content/uploads/2024/10/InteractionTutorial_EM-1.pdf

10. RubinD. Estimating causal effects of treatments in experimental and observational studies[J]. ETS Res Bull Ser, 1972, 1972(2): 688-701. https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/j.2333-8504. 1972.tb00631.x

11. KnolMJ, VanderWeeleTJ. Recommendations for presenting analyses of effect modification and interaction[J]. Int J Epidemiol, 2012, 41(2): 514-520. DOI: 10.1093/ije/dyr218.

12. HernanMA, RobinsJM. Using big data to emulate a target trial when a randomized trial is not available[J]. Am J Epidemiol, 2016, 183(8): 758-764. DOI: 10.1093/aje/kwv254.

13. HernanMA, SauerBC, Hernandez-DiazS, et al. Specifying a target trial prevents immortal time bias and other self-inflicted injuries in observational analyses[J]. J Clin Epidemiol, 2016, 79: 70-75. DOI: 10.1016/j.jclinepi.2016.04.014.

14. HernanMA, DahabrehIJ, DickermanBA, et al. The target trial framework for causal inference from observational data: Why and when is it helpful?[J]. Ann Intern Med, 2025, 178(3): 402-407. DOI: 10.7326/ANNALS-24-01871.

15. RothwellPM. Treating individuals 2. Subgroup analysis in randomised controlled trials: Importance, indications, and interpretation[J]. Lancet, 2005, 365(9454): 176-186. DOI: 10.1016/S0140-6736(05)17709-5.

16. AssmannSF, PocockSJ, EnosLE, et al. Subgroup analysis and other (mis) uses of baseline data in clinical trials[J]. Lancet, 2000, 355(9209): 1064-1069. DOI: 10.1016/S0140-6736(00)02039-0.

17. WangR, LagakosSW, WareJH, et al. Statistics in medicine--reporting of subgroup analyses in clinical trials[J]. N Engl J Med, 2007, 357(21): 2189-2194. DOI: 10.1056/NEJMsr077003.

18. SchandelmaierS, BrielM, VaradhanR, et al. Development of the instrument to assess the credibility of effect modification analyses (iceman) in randomized controlled trials and meta-analyses[J]. CMAJ, 2020, 192(32): E901-E906. DOI: 10.1503/cmaj.200077.

19. MaemondoM, InoueA, KobayashiK, et al. Gefitinib or chemotherapy for non-small-cell lung cancer with mutated EGFR[J]. N Engl J Med, 2010, 362(25): 2380-2388. DOI: 10.1056/NEJMoa0909530.

20. KimES, HirshV, MokT, et al. Gefitinib versus docetaxel in previously treated non-small-cell lung cancer (interest): a randomised phase iii trial[J]. Lancet, 2008, 372(9652): 1809-1818. DOI: 10.1016/S0140-6736(08)61758-4.

21. ThatcherN, ChangA, ParikhP, et al. Gefitinib plus best supportive care in previously treated patients with refractory advanced non-small-cell lung cancer: Results from a randomised, placebo-controlled, multicentre study (Iressa Survival Evaluation In Lung Cancer)[J]. Lancet, 2005, 366(9496): 1527-1537. DOI: 10.1016/S0140-6736(05)67625-8.

22. FoxKA, Poole-WilsonP, ClaytonTC, et al. 5-year outcome of an interventional strategy in non-ST-elevation acute coronary syndrome: the british heart foundation rita 3 randomised trial[J]. Lancet, 2005, 366(9489): 914-920. DOI: 10.1016/S0140-6736(05)67222-4.

23. TangH, DonahooWT, SvenssonM, et al. Heterogeneous treatment effects of sodium-glucose cotransporter 2 inhibitors on risk of dementia in people with type 2 diabetes: a population-based cohort study[J]. Alzheimers Dement, 2024, 20(8): 5528-5539. DOI: 10.1002/alz.14048.

24. WangT, KeilAP, BuseJB, et al. Glucagon-like peptide 1 receptor agonists and asthma exacerbations: which patients benefit most?[J]. Ann Am Thorac Soc, 2024, 21(11): 1496-1506. DOI: 10.1513/AnnalsATS.202309-836OC.

25. RekkasA, RijnbeekPR, KentDM, et al. Estimating individualized treatment effects from randomized controlled trials: a simulation study to compare risk-based approaches[J]. BMC Med Res Methodol, 2023, 23(1): 74. DOI: 10.1186/s12874-023-01889-6.

26. van KlaverenD, BalanTA, SteyerbergEW, et al. Models with interactions overestimated heterogeneity of treatment effects and were prone to treatment mistargeting[J]. J Clin Epidemiol, 2019, 114: 72-83. DOI: 10.1016/j.jclinepi.2019.05.029.

27. SelbyJV, MaasC, FiremanBH, et al. Predictive modeling of heterogeneous treatment effects in rcts: a scoping review[J]. JAMA Netw Open, 2025, 8(7): e2522390. DOI: 10.1001/jamanetworkopen.2025.22390.

28. FeuerriegelS, FrauenD, MelnychukV, et al. Causal machine learning for predicting treatment outcomes[J]. Nat Med, 2024, 30(4): 958-968. DOI: 10.1038/s41591-024-02902-1.

29. AbecassisJ, DumasE, AlbergeJ, et al. From prediction to prescription: machine learning and causal inference for the heterogeneous treatment effect[J]. Annu Rev Biomed Data Sci, 2025, 8(1): 381-404. DOI: 10.1146/annurev-biodatasci-103123-095750.

30. InoueK, AdomiM, EfthimiouO, et al. Machine learning approaches to evaluate heterogeneous treatment effects in randomized controlled trials: a scoping review[J]. J Clin Epidemiol, 2024, 176: 111538. DOI: 10.1016/j.jclinepi.2024.111538.

31. LipkovichI, SvenssonD, RatitchB, et al. Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data[J]. Stat Med, 2024, 43(22): 4388-4436. DOI: 10.1002/sim.10167.

32. ImaiK, RatkovicM. Estimating treatment effect heterogeneity in randomized program evaluation[J]. Ann Appl Stat, 2013, 7(1): 443-470. DOI: 10.1214/12-Aoas593.

33. AtheyS, ImbensG. Recursive partitioning for heterogeneous causal effects[J]. Proc Natl Acad Sci U S A, 2016, 113(27): 7353-7360. DOI: 10.1073/pnas.1510489113.

34. WagerS, AtheyS. Estimation and inference of heterogeneous treatment effects using random forests[J]. J Am Stat Assoc, 2018, 113(523): 1228-1242. DOI: 10.1080/01621459.2017.1319839.

35. HillJL. Bayesian nonparametric modeling for causal inference[J]. J Comput Graph Stat, 2011, 20(1): 217-240. DOI: 10.1198/jcgs.2010.08162.

36. HahnPR, MurrayJS, CarvalhoCM. Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (with discussion)[J]. Bayesian Analysis, 2020, 15(3): 965-1056.

37. KunzelSR, SekhonJS, BickelPJ, et al. Metalearners for estimating heterogeneous treatment effects using machine learning[J]. Proc Natl Acad Sci U S A, 2019, 116(10): 4156-4165. DOI: 10.1073/pnas.1804597116.

38. HamayaR, HaraK, MansonJE, et al. Machine-learning approaches to predict individualized treatment effect using a randomized controlled trial[J]. Eur J Epidemiol, 2025, 40(2): 151-166. DOI: 10.1007/s10654-024-01185-7.

39. NieX, WagerS. Quasi-oracle estimation of heterogeneous treatment effects[J]. Biometrika, 2021, 108(2): 299-319. DOI: 10.1093/biomet/asaa076.

40. KennedyEH. Towards optimal doubly robust estimation of heterogeneous causal effects[J]. Electro J Stat, 2023, 17(2): 3008-3049. DOI: 10.1214/23-EJS2157.

41. BaumA, ScarpaJ, BruzeliusE, et al. Targeting weight loss interventions to reduce cardiovascular complications of type 2 diabetes: a machine learning-based post-hoc analysis of heterogeneous treatment effects in the look ahead trial[J]. Lancet Diabetes Endocrinol, 2017, 5(10): 808-815. DOI: 10.1016/S2213-8587(17)30176-6.

42. MunroeES, SpicerA, Castellvi-FontA, et al. Evidence-based personalised medicine in critical care: a framework for quantifying and applying individualised treatment effects in patients who are critically ill[J]. Lancet Respir Med, 2025, 13(6): 556-568. DOI: 10.1016/S2213-2600(25)00054-2.

43. BletteBS, GranholmA, LiF, et al. Causal bayesian machine learning to assess treatment effect heterogeneity by dexamethasone dose for patients with COVID-19 and severe hypoxemia[J]. Sci Rep, 2023, 13(1): 6570. DOI: 10.1038/s41598-023-33425-3.

44. GoligherEC, LawlerPR, JensenTP, et al. Heterogeneous treatment effects of therapeutic-dose heparin in patients hospitalized for COVID-19[J]. JAMA, 2023, 329(13): 1066-1077. DOI: 10.1001/jama.2023.3651.

45. HechtmanRK, KipnisP, CanoJ, et al. Heterogeneity of benefit from earlier time-to-antibiotics for sepsis[J]. Am J Respir Crit Care Med, 2024, 209(7): 852-860. DOI: 10.1164/rccm.202310-1800OC.

46. DesaiRJ, GlynnRJ, SolomonSD, et al. Individualized treatment effect prediction with machine learning-salient considerations[J]. NEJM Evid, 2024, 3(4): EVIDoa2300041. DOI: 10.1056/EVID oa2300041.

47. MollerM, WildEM, TanW, et al. Estimating heterogeneous treatment effects with real-world health data: a scoping review of machine learning methods[J]. Value Health, 2026, 29(5): 905-913. DOI: 10.1016/j.jval.2026.01.013.