OncoSynth: Synthetic data generation for treatment effect estimation in oncology

Octavia-Andreea Ciora; Julian Welzel; Dennis Frauen; Maresa Schröder; Marie Brockschmidt; Harry Amad; Thomas Callender; Mihaela van der Schaar

cs.LGJun 24, 2026

OncoSynth: Synthetic data generation for treatment effect estimation in oncology

Authors: Octavia-Andreea Ciora, Julian Welzel, Dennis Frauen, Maresa Schröder, Marie Brockschmidt, Harry Amad, Thomas Callender, Mihaela van der Schaar, +1 more

Organizations: 1LMU Munich, Munich, Germany · 2Munich Center for Machine Learning (MCML), Munich, Germany · Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom · Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom · 5Cambridge Centre for AI in Medicine, University of Cambridge, Cambridge, United Kingdom · 6The Alan Turing Institute, London, United Kingdom

Abstract

In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existing methods for synthetic data generation fail to preserve the causal relationships between covariates, treatments, and outcomes, thereby leading to biased estimates of treatment effects. Here, we introduce OncoSynth, a generative, causally-aware machine learning framework designed to produce synthetic cohorts that enable accurate estimation of population- and patient-level treatment effects. OncoSynth uses a diffusion-based sequential approach to model how covariates influence treatment assignment and how treatment affects survival. We evaluate OncoSynth using large lung (N = 37,128) and breast cancer (N = 17,046) cohorts. Our results show that OncoSynth generates high-fidelity synthetic patient cohorts that preserve real-world patient, treatment, and outcome distributions. Notably, OncoSynth improves treatment effect estimation over existing approaches, by reducing population-level treatment effect error by up to 66%, and patient-level treatment effect error by up to 58%. Thereby, OncoSynth supports reliable evidence generation for precision oncology in settings where data sharing is restricted.

Explore similar work

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities
Apr 26, 2026Yichen XuCausal Inferences Synthetic Data
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
Jun 30, 2026Niccolò Maria Rizzi, Eugenio Lomurno, Alberto Archetti +1Survival Analysis Synthetic Tabular Data
Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets
May 18, 2026Nitish Nagesh, Pengbao Zhou, Atchuth Naveen Chilaparasetti +8Synthetic Data Benchmark Datasets

Apr 26, 2026 · stat.MEJ/K move · Enter open · S save

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities

Yichen Xu

University of California, Berkeley

Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference. We show that fully generative tabular synthesizers, including GAN- and LLM-based models, can preserve predictive utility while distorting average treatment effect (ATE) estimates. The failure is structural: ATE preservation requires both a realistic covariate law and an accurate treatment-effect contrast, whereas prediction loss penalizes treatment-effect error only through an overlap-weighted term. Thus, under imbalance or limited overlap, a generator may reproduce dominant observed outcomes while underlearning intervention-relevant contrasts. We formalize this mismatch through sensitivity and loss-decomposition results. Motivated by this causal analysis and intuition, we propose a hybrid synthetic-data framework for causal inference that generates covariates while modeling treatment and outcome mechanisms separately. We evaluate the framework in three settings: ATE preservation under fully generative versus hybrid synthesis, augmentation for practical positivity problems, and diagnostic simulation engines for comparing OR, IPW, AIPW, and TMLE before real-data analysis. We also stress-test the hybrid construction across settings that vary overlap, covariate dimension, seed sample size, and treatment-effect complexity, including a logistic outcome-model misspecification check. Across controlled simulation experiments, hybrid synthesis improves causal fidelity relative to fully generative baselines; the ACTG application shows improved predictive fidelity and potential for finite-sample estimator benchmarking. LLM-based hybrid synthesis is often more faithful than CTGAN in settings where causal fidelity can be assessed.

Causal Inferences Synthetic Data Heterogeneous Treatment Effects Synthetic Training Data Covariate Shift Tabular Prior-Data Fitted Network Hybrid

Open paper Ask about it PDF

Abstract

Explore similar work

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities

A Filtered Mixture-of-Generators for Fully Synthetic Survival Training

Memisis: Orchestrating and Evaluating Synthetic Data for Tabular Health Datasets