# Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions

arXiv: https://arxiv.org/abs/2503.09226 · HTML: https://mlsanity.com/paper/2503.09226/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 108 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges](https://mlsanity.com/paper/1507.08025/) (2015)
- [Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination](https://mlsanity.com/paper/1906.00285/) (2019)
- [Pure Exploration with Multiple Correct Answers](https://mlsanity.com/paper/1902.03475/) (2019)
- [Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding](https://mlsanity.com/paper/1810.02894/) (2018)
- [Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data](https://mlsanity.com/paper/2111.02275/) (2021)
- [Fair Exploration via Axiomatic Bargaining](https://mlsanity.com/paper/2106.02553/) (2021)
- [A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trials](https://mlsanity.com/paper/1809.00258/) (2018)
- [Fair Off-Policy Learning from Observational Data](https://mlsanity.com/paper/2303.08516/) (2023)
- [Response-adaptive randomization in clinical trials: from myths to practical considerations](https://mlsanity.com/paper/2005.00564/) (2020)
- [Contextual Constrained Learning for Dose-Finding Clinical Trials](https://mlsanity.com/paper/2001.02463/) (2020)
- [SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups](https://mlsanity.com/paper/2101.10998/) (2021)
- [Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments](https://mlsanity.com/paper/2103.12198/) (2021)
- [Best Arm Identification with Contextual Information under a Small Gap](https://mlsanity.com/paper/2209.07330/) (2022)
- [Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions](https://mlsanity.com/paper/2208.05844/) (2022)

## Built on by (most cited first, 3 of 3)

- [Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation](https://mlsanity.com/paper/2509.21866/) (2025)
- [ActiveCQ: Active Estimation of Causal Quantities](https://mlsanity.com/paper/2509.24293/) (2025)
- [Observationally Informed Adaptive Causal Experimental Design](https://mlsanity.com/paper/2603.03785/) (2026)

## Abstract (arXiv)

Randomized Controlled Trials (RCTs) are the gold standard for evaluating the effect of new medical treatments. Treatments must pass stringent regulatory conditions in order to be approved for widespread use, yet even after the regulatory barriers are crossed, real-world challenges might arise: Who should get the treatment? What is its true clinical utility? Are there discrepancies in the treatment effectiveness across diverse and under-served populations? We introduce two new objectives for future clinical trials that integrate regulatory constraints and treatment policy value for both the entire population and under-served populations, thus answering some of the questions above in advance. Designed to meet these objectives, we formulate Randomize First Augment Next (RFAN), a new framework for designing Phase III clinical trials. Our framework consists of a standard randomized component followed by an adaptive one, jointly meant to efficiently and safely acquire and assign patients into treatment arms during the trial. Then, we propose strategies for implementing RFAN based on causal, deep Bayesian active learning. Finally, we empirically evaluate the performance of our framework using synthetic and real-world semi-synthetic datasets.