KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation

Jalen Jiang, Chufan Gao, Ethan Rasmussen, Stephen Z. Xie, Jimeng Sun
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:755-814, 2026.

Abstract

Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely released. Prior work has addressed only half of this gap: reconstructing Kaplan–Meier (KM) curves from published plots — typically requiring manual digitization or human-in-the-loop correction — while offering no mechanism for generating the adverse-event (AE) streams that constitute the other half of a patient record. We introduce KMGen, the first end-to-end framework that (i) fully automates KM curve extraction at accuracy competitive with human-guided tools, and (ii) generates synthetic per-patient AE trajectories from public trial registry records. The extraction stage is a fully automated agentic pipeline — an agent generates code to extract each step in the KM curve — achieving a mean Integrated Absolute Error (IAE) of 0.0151 on a 32-plot benchmark spanning clean, edge-case, and adversarial conditions. The IPD generation stage decouples patient archetype extraction from statistical sampling: an LLM distills the trial record into arm-specific statistics, adverse events, patient demographics, and risk multipliers. A mechanistic sampler generates patient events via clinical archetypes, bootstrap rank-correlation coupling to the empirical KM curve (preserving the marginal survival distribution exactly), and cycle-based AE scheduling with an induction/maintenance split. Across three held-out oncology trials spanning an order of magnitude in cohort size and 30 independent regenerations per trial, KMGen achieves mean integrated KM absolute difference $\Delta_{\mathrm{KM}} \leq 0.051$, sex/ECOG JSD $\leq 0.013$ on 5 of 6 demographic slots, and recovers $\geq 71%$ of the top-15 AEs by exact MedDRA term under a single fixed parameter set. The pipeline is interpretable end-to-end and released as open source at https://github.com/chufangao/kmgen.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-jiang26a, title = {KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation}, author = {Jiang, Jalen and Gao, Chufan and Rasmussen, Ethan and Xie, Stephen Z. and Sun, Jimeng}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {755--814}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/jiang26a/jiang26a.pdf}, url = {https://proceedings.mlr.press/v340/jiang26a.html}, abstract = {Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely released. Prior work has addressed only half of this gap: reconstructing Kaplan–Meier (KM) curves from published plots — typically requiring manual digitization or human-in-the-loop correction — while offering no mechanism for generating the adverse-event (AE) streams that constitute the other half of a patient record. We introduce KMGen, the first end-to-end framework that (i) fully automates KM curve extraction at accuracy competitive with human-guided tools, and (ii) generates synthetic per-patient AE trajectories from public trial registry records. The extraction stage is a fully automated agentic pipeline — an agent generates code to extract each step in the KM curve — achieving a mean Integrated Absolute Error (IAE) of 0.0151 on a 32-plot benchmark spanning clean, edge-case, and adversarial conditions. The IPD generation stage decouples patient archetype extraction from statistical sampling: an LLM distills the trial record into arm-specific statistics, adverse events, patient demographics, and risk multipliers. A mechanistic sampler generates patient events via clinical archetypes, bootstrap rank-correlation coupling to the empirical KM curve (preserving the marginal survival distribution exactly), and cycle-based AE scheduling with an induction/maintenance split. Across three held-out oncology trials spanning an order of magnitude in cohort size and 30 independent regenerations per trial, KMGen achieves mean integrated KM absolute difference $\Delta_{\mathrm{KM}} \leq 0.051$, sex/ECOG JSD $\leq 0.013$ on 5 of 6 demographic slots, and recovers $\geq 71%$ of the top-15 AEs by exact MedDRA term under a single fixed parameter set. The pipeline is interpretable end-to-end and released as open source at https://github.com/chufangao/kmgen.} }
Endnote
%0 Conference Paper %T KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation %A Jalen Jiang %A Chufan Gao %A Ethan Rasmussen %A Stephen Z. Xie %A Jimeng Sun %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-jiang26a %I PMLR %P 755--814 %U https://proceedings.mlr.press/v340/jiang26a.html %V 340 %X Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely released. Prior work has addressed only half of this gap: reconstructing Kaplan–Meier (KM) curves from published plots — typically requiring manual digitization or human-in-the-loop correction — while offering no mechanism for generating the adverse-event (AE) streams that constitute the other half of a patient record. We introduce KMGen, the first end-to-end framework that (i) fully automates KM curve extraction at accuracy competitive with human-guided tools, and (ii) generates synthetic per-patient AE trajectories from public trial registry records. The extraction stage is a fully automated agentic pipeline — an agent generates code to extract each step in the KM curve — achieving a mean Integrated Absolute Error (IAE) of 0.0151 on a 32-plot benchmark spanning clean, edge-case, and adversarial conditions. The IPD generation stage decouples patient archetype extraction from statistical sampling: an LLM distills the trial record into arm-specific statistics, adverse events, patient demographics, and risk multipliers. A mechanistic sampler generates patient events via clinical archetypes, bootstrap rank-correlation coupling to the empirical KM curve (preserving the marginal survival distribution exactly), and cycle-based AE scheduling with an induction/maintenance split. Across three held-out oncology trials spanning an order of magnitude in cohort size and 30 independent regenerations per trial, KMGen achieves mean integrated KM absolute difference $\Delta_{\mathrm{KM}} \leq 0.051$, sex/ECOG JSD $\leq 0.013$ on 5 of 6 demographic slots, and recovers $\geq 71%$ of the top-15 AEs by exact MedDRA term under a single fixed parameter set. The pipeline is interpretable end-to-end and released as open source at https://github.com/chufangao/kmgen.
APA
Jiang, J., Gao, C., Rasmussen, E., Xie, S.Z. & Sun, J.. (2026). KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:755-814 Available from https://proceedings.mlr.press/v340/jiang26a.html.

Related Material