Efficient and robust approaches for analysis of sequential multiple assignment randomized trials: Illustration using the ADAPT-R trial.

Personalized intervention strategies, in particular those that modify treatment based on a participant's own response, are a core component of precision medicine approaches. Sequential multiple assignment randomized trials (SMARTs) are growing in popularity and are specifically designed to facilitate the evaluation of sequential adaptive strategies, in particular those embedded within the SMART. Advances in efficient estimation approaches that are able to incorporate machine learning while retaining valid inference can allow for more precise estimates of the effectiveness of these embedded regimes. However, to the best of our knowledge, such approaches have not yet been applied as the primary analysis in SMART trials. In this paper, we present a robust and efficient approach using targeted maximum likelihood estimation (TMLE) for estimating and contrasting expected outcomes under the dynamic regimes embedded in a SMART, together with generating simultaneous confidence intervals for the resulting estimates. We contrast this method with two alternatives (G-computation and inverse probability weighting estimators). The precision gains and robust inference achievable through the use of TMLE to evaluate the effects of embedded regimes are illustrated using both outcome-blind simulations and a real-data analysis from the Adaptive Strategies for Preventing and Treating Lapses of Retention in Human Immunodeficiency Virus (HIV) Care (ADAPT-R) trial (NCT02338739), a SMART with a primary aim of identifying strategies to improve retention in HIV care among people living with HIV in sub-Saharan Africa.

Estimators for the value of the optimal dynamic treatment rule with application to criminal justice interventions.

Given an (optimal) dynamic treatment rule, it may be of interest to evaluate that rule - that is, to ask the causal question: what is the expected outcome had every subject received treatment according to that rule? In this paper, we study the performance of estimators that approximate the true value of: (1) an a priori known dynamic treatment rule (2) the true, unknown optimal dynamic treatment rule (ODTR); (3) an estimated ODTR, a so-called "data-adaptive parameter," whose true value depends on the sample. Using simulations of point-treatment data, we specifically investigate: (1) the impact of increasingly data-adaptive estimation of nuisance parameters and/or of the ODTR on performance; (2) the potential for improved efficiency and bias reduction through the use of semiparametric efficient estimators; and, (3) the importance of sample splitting based on the cross-validated targeted maximum likelihood estimator (CV-TMLE) for accurate inference. In the simulations considered, there was very little cost and many benefits to using CV-TMLE to estimate the value of the true and estimated ODTR; importantly, and in contrast to non cross-validated estimators, the performance of CV-TMLE was maintained even when highly data-adaptive algorithms were used to estimate both nuisance parameters and the ODTR. In addition, we apply these estimators for the value of the rule to the "Interventions" study, an ongoing randomized controlled trial, to identify whether assigning cognitive behavioral therapy (CBT) to criminal justice-involved adults with mental illness using an ODTR significantly reduces the probability of recidivism, compared to assigning CBT in a non-individualized way.

The optimal dynamic treatment rule superlearner: considerations, performance, and application to criminal justice interventions.

The optimal dynamic treatment rule (ODTR) framework offers an approach for understanding which kinds of patients respond best to specific treatments - in other words, treatment effect heterogeneity. Recently, there has been a proliferation of methods for estimating the ODTR. One such method is an extension of the SuperLearner algorithm - an ensemble method to optimally combine candidate algorithms extensively used in prediction problems - to ODTRs. Following the ``causal roadmap," we causally and statistically define the ODTR and provide an introduction to estimating it using the ODTR SuperLearner. Additionally, we highlight practical choices when implementing the algorithm, including choice of candidate algorithms, metalearners to combine the candidates, and risk functions to select the best combination of algorithms. Using simulations, we illustrate how estimating the ODTR using this SuperLearner approach can uncover treatment effect heterogeneity more effectively than traditional approaches based on fitting a parametric regression of the outcome on the treatment, covariates and treatment-covariate interactions. We investigate the implications of choices in implementing an ODTR SuperLearner at various sample sizes. Our results show the advantages of: (1) including a combination of both flexible machine learning algorithms and simple parametric estimators in the library of candidate algorithms; (2) using an ensemble metalearner to combine candidates rather than selecting only the best-performing candidate; (3) using the mean outcome under the rule as a risk function. Finally, we apply the ODTR SuperLearner to the ``Interventions" study, an ongoing randomized controlled trial, to identify which justice-involved adults with mental illness benefit most from cognitive behavioral therapy to reduce criminal re-offending.

Adapt for Adolescents: Protocol for a sequential multiple assignment randomized trial to improve retention and viral suppression among adolescents and young adults living with HIV in Kenya.

BACKGROUND: Adolescents and young adults living with HIV (AYAH) aged 14-24 years in Africa experience substantially higher rates of virological failure and HIV-related mortality than adults. We propose to utilize developmentally appropriate interventions with high potential for effectiveness, tailored by AYAH pre-implementation, in a sequential multiple assignment randomized trial (SMART) aimed at improving viral suppression for AYAH in Kenya. METHODS: Using a SMART design, we will randomize 880 AYAH in Kisumu, Kenya to either youth-centered education and counseling (standard of care) or electronic peer navigation in which a peer provides support, information, and counseling via phone and automated monthly text messages. Those with a lapse in engagement (defined as either a missed clinic visit by ≥14 days or HIV viral load ≥1000 copies/ml) will be randomized a second time to one of three higher-intensity re-engagement interventions: This study will evaluate which interventions and which dynamic sequence of interventions improve sustained viral suppression and HIV care engagement in AYAH at 24 months post-enrollment and assess the cost-effectiveness of successful strategies. DISCUSSION: The study utilizes promising interventions tailored to AYAH while optimizing resources by intensifying services only for those AYAH who need more support. Findings from this innovative study will offer evidence for public health programming to end the HIV epidemic as a public health threat for AYAH in Africa. TRIAL REGISTRATION: Clinicaltrials.govNCT04432571, registered June 16, 2020.

Adaptive Strategies for Retention in Care among Persons Living with HIV.

BACKGROUND: Optimizing retention in human immunodeficiency virus (HIV) treatment may require sequential behavioral interventions based on patients' response. METHODS: In a sequential multiple assignment randomized trial in Kenya, we randomly assigned adults initiating HIV treatment to standard of care (SOC), Short Message Service (SMS) messages, or conditional cash transfers (CCT). Those with retention lapse (missed a clinic visit by ≥14 days) were randomly assigned again to standard-of-care outreach (SOC-Outreach), SMS+CCT, or peer navigation. Those randomly assigned to SMS or CCT who did not lapse after 1 year were randomly assigned again to either stop or continue the initial intervention. Primary outcomes were retention in care without an initial lapse, return to the clinic among those who lapsed, and time in care; secondary outcomes included adjudicated viral suppression. Average treatment effect (ATE) was calculated using targeted maximum likelihood estimation with adjustment for baseline characteristics at randomization and certain time-varying characteristics at rerandomization. RESULTS: Among 1809 participants, 79.7% of those randomly assigned to CCT (n=523/656), 71.7% to SMS (n=393/548), and 70.7% to SOC (n=428/605) were retained in care in the first year (ATE: 9.9%; 95% confidence interval [CI]: 5.4%, 14.4% and ATE: 4.2%; 95% CI: -0.7%, 9.2% for CCT and SMS compared with SOC, respectively). Among 312 participants with an initial lapse who were randomly assigned again, 69.1% who were randomly assigned to a navigator (n=76/110) returned, 69.5% randomly assigned to CCT+SMS (n=73/105) returned, and 55.7% randomly assigned to SOC-Outreach (n=54/97) returned (ATE: 14.1%; 95% CI: 0.6%, 27.6% and ATE: 11.4%; 95% CI: -2.2%, 24.9% for navigator and CCT+SMS compared with SOC-Outreach, respectively). Among participants without lapse on SMS, continuing SMS did not affect retention (n=122/180; 67.8% retained) versus stopping (n=151/209; 72.2% retained; ATE: -4.4%; 95% CI: -16.6%, 7.9%). Among participants without lapse on CCT, those continuing CCT had higher retention (n=192/230; 83.5% retained) than those stopping (n=173/287; 60.3% retained; ATE: 28.6%; 95% CI: 19.9%, 37.3%). Among 15 sequenced strategies, initial CCT, escalated to navigator if lapse occurred and continued if no lapse occurred, increased time in care (ATE: 7.2%, 95% CI: 3.7%, 10.7%) and viral suppression (ATE: 8.2%, 95% CI: 2.2%, 14.2%), the most compared with SOC throughout. Initial SMS escalated to navigator if lapse occurred, and otherwise continued, showed similar effect sizes compared with SOC throughout. CONCLUSIONS: Active interventions to prevent retention lapses followed by navigation for those who lapse and maintenance of initial intervention for those without lapse resulted in best overall retention and viral suppression among the strategies studied. Among those who remained in care, discontinuation of CCT, but not SMS, compromised retention and suppression. (Funded by National Institutes of Health grants R01 MH104123, K24 AI134413, and R01 AI074345; ClinicalTrials.gov number, NCT02338739.).

AI Estimation of Gestational Age from Blind Ultrasound Sweeps in Low-Resource Settings.

BACKGROUND: Ultrasound is indispensable to gestational age estimation and thus to quality obstetrical care, yet high equipment cost and the need for trained sonographers limit its use in low-resource settings. METHODS: From September 2018 through June 2021, we recruited 4695 pregnant volunteers in North Carolina and Zambia and obtained blind ultrasound sweeps (cineloop videos) of the gravid abdomen alongside standard fetal biometry. We trained a neural network to estimate gestational age from the sweeps and, in three test data sets, assessed the performance of the artificial intelligence (AI) model and biometry against previously established gestational age. RESULTS: In our main test set, the mean absolute error (MAE) (±SE) was 3.9±0.12 days for the model versus 4.7±0.15 days for biometry (difference, -0.8 days; 95% confidence interval [CI], -1.1 to -0.5; P<0.001). The results were similar in North Carolina (difference, -0.6 days; 95% CI, -0.9 to -0.2) and Zambia (-1.0 days; 95% CI, -1.5 to -0.5). Findings were supported in the test set of women who conceived by in vitro fertilization (MAE of 2.8±0.28 vs. 3.6±0.53 days for the model vs. biometry; difference, -0.8 days; 95% CI, -1.7 to 0.2) and in the set of women from whom sweeps were collected by untrained users with low-cost, battery-powered devices (MAE of 4.9±0.29 vs. 5.4±0.28 days for the model vs. biometry; difference, -0.6; 95% CI, -1.3 to 0.1). CONCLUSIONS: When provided blindly obtained ultrasound sweeps of the gravid abdomen, our AI model estimated gestational age with accuracy similar to that of trained sonographers conducting standard fetal biometry. Model performance appears to extend to blind sweeps collected by untrained providers in Zambia using low-cost devices. (Funded by the Bill and Melinda Gates Foundation.).