Use of Machine Learning to Estimate the Per-Protocol Effect of Low-Dose Aspirin on Pregnancy Outcomes: A Secondary Analysis of a Randomized Clinical Trial

Yongqi Zhong, Maria M Brooks, Edward H Kennedy, Lisa M Bodnar, Ashley I Naimi, Yongqi Zhong, Maria M Brooks, Edward H Kennedy, Lisa M Bodnar, Ashley I Naimi

Abstract

Importance: In randomized clinical trials (RCTs), per-protocol effects may be of interest in the presence of nonadherence with the randomized treatment protocol. Using machine learning in per-protocol effect estimation can help avoid model misspecification owing to strong parametric assumptions, as is common with standard methods (eg, logistic regression).

Objectives: To demonstrate the use of ensemble machine learning with augmented inverse probability weighting (AIPW) for per-protocol effect estimation in RCTs and to evaluate the per-protocol effect size of aspirin on pregnancy.

Design, setting, and participants: This secondary analysis used data from 1227 women in the Effects of Aspirin in Gestation and Reproduction (EAGeR) trial, a multicenter, block-randomized, double-blind, placebo-controlled clinical trial of the effect of daily low-dose aspirin on pregnancy outcomes in women at high risk of pregnancy loss. Participants were recruited at 4 university medical centers in the US from June 15, 2007, to July 15, 2012. Women were followed up for 6 menstrual cycles for attempted pregnancy and 36 weeks of gestation if pregnancy occurred. Follow-up was completed on August 17, 2012. Data analyses were performed on July 9, 2021.

Exposures: Daily low-dose (81 mg) aspirin taken at least 5 of 7 days per week for at least 80% of follow-up time relative to placebo.

Main outcomes and measures: Pregnancy detected using human chorionic gonadotropin (hCG) levels.

Results: Among the 1227 women included in the analysis (mean SD age, 28.74 [4.80] years), 1161 (94.6%) were non-Hispanic White and 858 (69.9%) adhered to the protocol. Five machine learning models were combined into 1 meta-algorithm, which was used to construct an AIPW estimator for the per-protocol effect. Compared with adhering to placebo, adherence to the daily low-dose aspirin protocol for at least 5 of 7 days per week was associated with an increase in the probability of hCG-detected pregnancy of 8.0 (95% CI, 2.5-13.6) more hCG-detected pregnancies per 100 women in the sample, which is substantially larger than the estimated intention-to-treat estimate of 4.3 (95% CI, -1.1 to 9.6) more hCG-detected pregnancies per 100 women in the sample.

Conclusions and relevance: These findings suggest that a low-dose aspirin protocol is associated with increased hCG-detected pregnancy in women who adhere to treatment for at least 5 days per week. With the presence of nonadherence, per-protocol treatment effect estimates differ from intention-to-treat estimates in the EAGeR trial. The results of this secondary analysis of clinical trial data suggest that machine learning could be used to estimate per-protocol effects by adjusting for confounders related to nonadherence in a more flexible way than traditional regressions.

Trial registration: ClinicalTrials.gov Identifier: NCT00467363.

Conflict of interest statement

Conflict of Interest Disclosures: Drs Brooks, Kennedy, Bodnar, and Naimi reported receiving grants from the National Institutes of Health (NIH) during the conduct of the study. Dr Brooks reported serving on the data safety and monitoring board for Cerus Corporation. No other disclosures were reported.

Figures

Figure 1.. CONSORT Study Flow Diagram for…
Figure 1.. CONSORT Study Flow Diagram for the Effects of Aspirin in Gestation and Reproduction (EAGeR) Trial
Figure 2.. Number of Participants Who Adhered…
Figure 2.. Number of Participants Who Adhered to Assigned Treatment by Different Follow-up Thresholds

References

    1. Gupta SK. Intention-to-treat concept: a review. Perspect Clin Res. 2011;2(3):109-112. doi:10.4103/2229-3485.83221
    1. Hernán MA, Hernández-Díaz S, Robins JM. Randomized trials analyzed as observational studies. Ann Intern Med. 2013;159(8):560-562. doi:10.7326/0003-4819-159-8-201310150-00709
    1. Manson JE, Shufelt CL, Robins JM. The potential for postrandomization confounding in randomized clinical trials. JAMA. 2016;315(21):2273-2274. doi:10.1001/jama.2016.3676
    1. Naimi AI, Perkins NJ, Sjaarda LA, et al. . The effect of preconception-initiated low-dose aspirin on human chorionic gonadotropin-detected pregnancy, pregnancy loss, and live birth: per protocol analysis of a randomized trial. Ann Intern Med. 2021;174(5):595-601. doi:10.7326/M20-0469
    1. Hernán MA, Robins JM. Per-protocol analyses of pragmatic trials. N Engl J Med. 2017;377(14):1391-1398. doi:10.1056/NEJMsm1605385
    1. Cain LE, Cole SR. Inverse probability-of-censoring weights for the correction of time-varying noncompliance in the effect of randomized highly active antiretroviral therapy on incident AIDS or death. Stat Med. 2009;28(12):1725-1738. doi:10.1002/sim.3585
    1. Lodi S, Freiberg M, Gnatienko N, et al. . Per-protocol analysis of the ZINC trial for HIV disease among alcohol users. Trials. 2021;22(1):226. doi:10.1186/s13063-021-05178-9
    1. Lodi S, Sharma S, Lundgren JD, et al. ; INSIGHT Strategic Timing of AntiRetroviral Treatment (START) Study Group . The per-protocol effect of immediate versus deferred antiretroviral therapy initiation. AIDS. 2016;30(17):2659-2663. doi:10.1097/QAD.0000000000001243
    1. Murnane PM, Brown ER, Donnell D, et al. ; Partners PrEP Study Team . Estimating efficacy in a randomized trial with product nonadherence: application of multiple methods to a trial of preexposure prophylaxis for HIV prevention. Am J Epidemiol. 2015;182(10):848-856. doi:10.1093/aje/kwv202
    1. Murray EJ, Hernán MA. Improved adherence adjustment in the Coronary Drug Project. Trials. 2018;19(1):158. doi:10.1186/s13063-018-2519-5
    1. Neumann A, Maura G, Weill A, Ricordeau P, Alla F, Allemand H. Comparative effectiveness of rosuvastatin versus simvastatin in primary prevention among new users: a cohort study in the French national health insurance database. Pharmacoepidemiol Drug Saf. 2014;23(3):240-250. doi:10.1002/pds.3544
    1. Toh S, Hernández-Díaz S, Logan R, Robins JM, Hernán MA. Estimating absolute risks in the presence of nonadherence: an application to a follow-up study with baseline randomization. Epidemiology. 2010;21(4):528-539. doi:10.1097/EDE.0b013e3181df1b69
    1. Naimi AI, Mishler AE, Kennedy EH. Challenges in obtaining valid causal effect estimates with machine learning algorithms. Am J Epidemiol. Published online July 15, 2021. doi:10.1093/aje/kwab201
    1. Zivich PN, Breskin A. Machine learning for causal inference: on the use of cross-fit estimators. Epidemiology. 2021;32(3):393-401. doi:10.1097/EDE.0000000000001332
    1. Hastie T, Tibshirani R, Friedman JH. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer; 2009.
    1. Naimi AI, Balzer LB. Stacked generalization: an introduction to super learning. Eur J Epidemiol. 2018;33(5):459-464. doi:10.1007/s10654-018-0390-z
    1. Little MP, Brocard P, Elliott P, Steer PJ. Hemoglobin concentration in pregnancy and perinatal mortality: a London-based cohort study. Am J Obstet Gynecol. 2005;193(1):220-226. doi:10.1016/j.ajog.2004.11.053
    1. Schisterman EF, Silver RM, Perkins NJ, et al. . A randomized trial to evaluate the effects of low-dose aspirin in gestation and reproduction: design and baseline characteristics. Paediatr Perinat Epidemiol. 2013;27(6):598-609. doi:10.1111/ppe.12088
    1. Schisterman EF, Silver RM, Lesher LL, et al. . Preconception low-dose aspirin and pregnancy outcomes: results from the EAGeR randomized trial. Lancet. 2014;384(9937):29-36. doi:10.1016/S0140-6736(14)60157-4
    1. Schisterman EF, Mumford SL, Schliep KC, et al. . Preconception low dose aspirin and time to pregnancy: findings from the effects of aspirin in gestation and reproduction randomized trial. J Clin Endocrinol Metab. 2015;100(5):1785-1791. doi:10.1210/jc.2014-4179
    1. Rudolph JE, Naimi AI, Westreich DJ, Kennedy EH, Schisterman EF. Defining and identifying per-protocol effects in randomized trials. Epidemiology. 2020;31(5):692-694. doi:10.1097/EDE.0000000000001234
    1. Robins JM, Rotnitzky A. Semiparametric efficiency in multivariate regression models with missing data. J Am Stat Assoc. 1995;90(429):122-129. doi:10.1080/01621459.1995.10476494
    1. Van der Laan MJ, Polley EC, Hubbard AE. Super learner. Stat Appl Genet Mol Biol. 2007;6(1):e25. doi:10.2202/1544-6115.1309
    1. Zhong Y, Kennedy EH, Bodnar LM, Naimi AI. AIPW: an R package for augmented inverse probability weighted estimation of average causal effects. Am J Epidemiol. 2021;190(12):2690-2699. doi:10.1093/aje/kwab207
    1. Friedman JH. Multivariate adaptive regression splines. Ann Stat. 1991;19(1):1-67. doi:10.1214/aos/1176347963
    1. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32. doi:10.1023/A:1010933404324
    1. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery; 2016:785-794.
    1. Naimi AI, Cole SR, Kennedy EH. An introduction to g methods. Int J Epidemiol. 2017;46(2):756-762. doi:10.1093/ije/dyw323
    1. Hernán MA, Robins JM. Estimating causal effects from epidemiological data. J Epidemiol Community Health. 2006;60(7):578-586. doi:10.1136/jech.2004.029496
    1. Rose S, van der Laan MJ. Targeted Learning: Causal Inference for Observational and Experimental Data. Springer; 2011.
    1. Polley E, LeDell E, Kennedy C, Lendle S, van der Laan M. SuperLearner: Super Learner Prediction. 2019. Accessed August 27, 2020.
    1. Gruber S, van der Laan MJ. tmle: An R package for targeted maximum likelihood estimation. J Stat Softw. 2012;51(13):1-35. doi:10.18637/jss.v051.i13
    1. Carin L, Pencina MJ. On deep learning for medical image analysis. JAMA. 2018;320(11):1192-1193. doi:10.1001/jama.2018.13316
    1. Wang S, Pathak J, Zhang Y. Using electronic health records and machine learning to predict postpartum depression. Stud Health Technol Inform. 2019;264:888-892. doi:10.3233/SHTI190351
    1. Khera R, Haimovich J, Hurley NC, et al. . Use of machine learning models to predict death after acute myocardial infarction. JAMA Cardiol. 2021;6(6):633-641. doi:10.1001/jamacardio.2021.0122
    1. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. 2nd ed. Springer; 2009:587-604.
    1. Cutler D, Lleras-Muney A.. Education and health: evaluating theories and evidence. In: House J, Schoeni R, Kaplan G, Pollack H, eds. Making Americans Healthier: Social and Economic Policy as Health Policy. Russell Sage Foundation; 2008.
    1. Dunn G, Lovrić M. Complier-average causal effect (CACE) estimation. In: Lorvić M, ed. International Encyclopedia of Statistical Science. Springer Nature; 2011.
    1. Awtry EH, Loscalzo J. Aspirin. Circulation. 2000;101(10):1206-1218. doi:10.1161/01.CIR.101.10.1206
    1. Abraha I, Montedori A. Modified intention to treat reporting in randomized controlled trials: systematic review. BMJ. 2010;340:c2697. doi:10.1136/bmj.c2697
    1. Montedori A, Bonacini MI, Casazza G, et al. . Modified versus standard intention-to-treat reporting: are there differences in methodological quality, sponsorship, and findings in randomized trials? a cross-sectional study. Trials. 2011;12(1):58. doi:10.1186/1745-6215-12-58
    1. Benkeser D, Díaz I, Luedtke A, Segal J, Scharfstein D, Rosenblum M. Improving precision and power in randomized trials for COVID-19 treatments using covariate adjustment, for binary, ordinal, and time-to-event outcomes. Biometrics. 2021;77(4):1467-1481. doi:10.1111/biom.13377

Source: PubMed

Sponzoři a spolupracovníci

Zdravotní podmínky

Drogové intervence

3
Předplatit