FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling

Jun Bai; Ruilin Wang; Yue Li

cs.LGAug 28, 2026

FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling

Authors: Jun Bai, Ruilin Wang, Yue Li

Organizations: School of Computer Science, McGill University, Montreal, Canada · Mila – Quebec AI Institute, Montreal, Canada

Abstract

Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling workflows. However, agents deployed at individual hospitals remain constrained by institution-specific data and modeling environments, while direct cross-hospital collaboration is restricted by the sensitivity of patient-level EHR data. Although federated learning (FL) provides a natural foundation for privacy-preserving collaboration, existing approaches remain predominantly model-centric, limiting federation to prediction models or their updates while overlooking the richer modeling experience accumulated by autonomous agents. To address this limitation, we propose FedEHR-Agents, an experience-centric federated agentic optimization framework for automated EHR modeling. Each hospital deploys an autonomous clinical EHR agent that performs data preprocessing and model development while refining local clinical modeling experience through historical memory, task-specific evaluation, and TextGrad-based prompt refinement. The federated server performs evidence-guided experience aggregation to integrate reliable and complementary modeling experience across heterogeneous hospitals and distills the aggregated experience into global meta-prompts for subsequent local refinement. Extensive experiments on real-world multi-hospital EHR benchmarks demonstrate that FedEHR-Agents consistently outperforms local and federated baselines across diverse clinical prediction tasks and remains robust across different federation scales and LLM backbones. These results establish clinical modeling experience as a promising collaborative object beyond conventional parameter-centric FL and point toward federated autonomous clinical intelligence.

Figures & tables

Figure 1. Motivation of FedEHR-Agents. Conventional FL performs collaboration through prediction model parameter aggregation, whereas FedEHR-Agents shifts the collaborative object toward clinical modeling experience. .

Figure 2. Overview of the proposed FedEHR-Agents framework. Each hospital deploys an autonomous clinical EHR agent to perform data preprocessing (DP) and model development (MD) while continuously refining local clinical modeling experience. The federated server aggregates module-specific experience representations through evidence-guided experience aggregation, synthesizes global DP and MD meta-prompts, and broadcasts them to guide subsequent local experience refinement. .

Centralized Methods (Upper Bound)
Method	Mortality-48h	ARF-4h	LOS $>$ 7d	Sepsis
Centralized AutoML	$0.232\pm 0.005$	$0.189\pm 0.006$	$0.543\pm 0.014$	$0.292\pm 0.007$
Centralized Agent	$0.242\pm 0.004$	$0.204\pm 0.005$	$0.578\pm 0.011$	$0.337\pm 0.008$
Independent Methods
Local AutoML	$0.205\pm 0.007$	$0.158\pm 0.007$	$0.465\pm 0.017$	$0.256\pm 0.005$
Local Agent	$0.218\pm 0.005$	$0.171\pm 0.005$	$0.483\pm 0.015$	$0.268\pm 0.007$

Table 1. Overall AUPRC comparison across four representative clinical prediction tasks. Higher values indicate better performance. The best results among the independent and federated methods are highlighted in bold. Centralized methods are reported only as upper-bound references.

Figure 3. Optimization trajectories of FedEHR-Agents on the Mortality-48h task across three hospitals. Solid lines denote performance measured by AUPRC, while dashed lines denote the number of selected features over communication rounds. .

Figure 4. Evolution of cross-hospital modeling consistency on the Mortality-48h task. (a) Pairwise feature selection consistency measured by Jaccard similarity. (b) Pairwise feature importance consistency measured by SHAP similarity. .

Figure 5. Hospital-level SHAP analysis of the shared clinically important features on the Mortality-48h task. The figure presents the SHAP distributions of the common top-ranked features identified across three hospitals after federated optimization. For readability, the feature names shown in Fig. 5 are normalized labels used after preprocessing rather than the original eICU variable names; detailed definitions are provided in Appendix Table C2 . .

Memory	Evaluator	DP Module	EGEA	AUPRC
$\times$	$\checkmark$	$\checkmark$	$\checkmark$	$0.223\pm 0.004$
$\checkmark$	$\times$	$\checkmark$	$\checkmark$	$0.226\pm 0.006$
$\checkmark$	$\checkmark$	$\times$	$\checkmark$	$0.219\pm 0.007$
$\checkmark$	$\checkmark$	$\checkmark$	$\times$	$0.221\pm 0.006$
$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$	$\mathbf{0.236\pm 0.005}$

Table 2. Ablation Study of FedEHR-Agents on the Mortality-48h prediction task.

Figure 6. Impact of the number of participating hospitals on Mortality-48h prediction. Average AUPRC is reported for federations with 3, 5, 10, 15, and 20 hospitals. .

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

\mathbf{Z}_{k}^{(r)}\leftarrow g_{\mathrm{DP}}\left(\mathcal{D}_{k},\mathcal{P}_{k,\mathrm{DP}}^{(r)}\right)

Appendix

Algorithm 1 FedEHR-Agents

# Hospitals	ARF-4h		LOS $>$ 7d		Sepsis
# Hospitals	PromptAvg	FedEHR-Agents	PromptAvg	FedEHR-Agents	PromptAvg	FedEHR-Agents
3	0.183 ± 0.006	0.194 ± 0.004	0.506 ± 0.012	0.532 ± 0.010	0.286 ± 0.011	0.316 ± 0.009
5	0.197 ± 0.004	0.225 ± 0.003	0.513 ± 0.011	0.538 ± 0.009	0.302 ± 0.011	0.322 ± 0.011
10	0.202 ± 0.006	0.229 ± 0.005	0.527 ± 0.010	0.544 ± 0.010	0.311 ± 0.010	0.328 ± 0.010
15	0.208 ± 0.005	0.231 ± 0.005	0.529 ± 0.013	0.546 ± 0.008	0.317 ± 0.007	0.335 ± 0.009
20	0.214 ± 0.006	0.236 ± 0.004	0.533 ± 0.011	0.553 ± 0.011	0.318 ± 0.009	0.341 ± 0.010

Appendix

Table B1. Scalability of FedEHR-Agents across additional clinical prediction tasks. Average AUPRC is reported under different numbers of participating hospitals. FedEHR-Agents (PromptAvg) is abbreviated as PromptAvg.

Memory	Evaluator	DP Module	EGEA	ARF-4h	LOS $>$ 7d	Sepsis
$\times$	✓	✓	✓	0.187 ± 0.004	0.521 ± 0.012	0.303 ± 0.010
✓	$\times$	✓	✓	0.185 ± 0.005	0.515 ± 0.010	0.298 ± 0.009
✓	✓	$\times$	✓	0.176 ± 0.005	0.510 ± 0.011	0.294 ± 0.008
✓	✓	✓	$\times$	0.183 ± 0.006	0.506 ± 0.010	0.286 ± 0.011
✓	✓	✓	✓	0.194 ± 0.004	0.532 ± 0.010	0.316 ± 0.009

Appendix

Table B2. Ablation results of FedEHR-Agents across additional clinical prediction tasks.

Figure B1. Comparison of different LLM backbones for federated clinical agent optimization. Results are averaged across the three participating hospitals. .

Hospital	$\mathbf{N_{k}}$	Demographic Features	Intake/Output Features	Laboratory Features	Medication Features	Respiratory Care Features	Periodic Vital Sign Features	Aperiodic Vital Sign Features	Total
Hospital 73	2,663	10	4	38	18	16	16	10	112
Hospital 264	3,006	9	4	33	15	14	14	9	98
Hospital 420	2,636	10	4	37	17	15	15	10	108

Appendix

Table C1. Initial feature composition of three representative hospitals on the Mortality-48h task.

N_{k}

denotes the number of patient samples, and the remaining columns report the numbers of features initially retained from different clinical sources at the first communication round.

Feature Name	eICU Mapping	Table Source	Description
creatinine	lab: creatinine	Laboratory	Serum creatinine reflecting renal function and potential kidney impairment.
bun	lab: BUN	Laboratory	Blood urea nitrogen reflecting renal function and accumulation of nitrogenous waste products.
lactate	lab: lactate	Laboratory	Blood lactate reflecting tissue hypoperfusion and metabolic stress.
glucose	lab: glucose / bedside glucose	Laboratory	Blood glucose concentration reflecting glycemic and metabolic status.
wbc	lab: WBC x 1000	Laboratory	White blood cell count reflecting inflammatory and infectious responses.
age	patient.age	Demographics	Patient age at ICU admission, representing baseline demographic risk.

Appendix

Table C2. Definitions and eICU mappings of the clinical features reported in the Mortality-48h SHAP analysis.

EHR Source	Data Characteristics	Primary Feature Strategy
Periodic Vital Signs	Dense and relatively high-frequency physiological measurements	Representative within-interval values together with compact temporal-change or variability features when sufficiently supported.
Laboratory	Sparse and irregular laboratory observations with high missingness	Representative measurements together with selected temporal-change or variability features while limiting redundant feature expansion.
Medication	Sparse event-based medication administration records	Binary indicators representing whether each medication category is administered within the corresponding temporal interval.
Intake/Output	Repeated fluid intake, output, and balance measurements	Temporal aggregation of intake, output, and net fluid-balance variables within each interval.
Respiratory Care	Sparse but clinically important respiratory-intervention events	Binary indicators representing the occurrence of respiratory-support events within each temporal interval.
Aperiodic Vital Signs	Sparse and intermittently measured physiological observations	Representative measurements, such as the most recent or average value, without unreliable higher-order temporal statistics.

Appendix

Table D1. Source-specific preprocessing strategies used by the DP Module.

Federated Learning

Federated learning trains shared models across data holders without requiring them to pool their raw data.

See all 939 papers

FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation
May 27, 2026Jun Bai, Ziyang Song, Yue LiSynthetic Data Generation Conditional Variational Autoencoder
McGill University Mila - Quebec AI Institute Montreal, Canada · Ohio University Athens, United States
Federated generative event models for tokenized electronic health records
Aug 3, 2026Michael C. Burkhart, Luke Solo, Inhyeok Lee +8Clinical Outcome Prediction Generative Modeling
Department of Medicine, University of Chicago, Chicago, Illinois, USA · Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework
Jul 21, 2026Akarsh K Nair, Muhammad Arifur Rahman, Nicholas Shopland +8Synthetic Data Pretraining Clinical Outcome Prediction
Department of Computer Science, Nottingham Trent University, Nottingham, United Kingdom · Division of Epidemiology and Public Health, University of Nottingham, Nottingham, United Kingdom · Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia +1

May 27, 2026J/K move · Enter open · S save

FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation

Jun Bai, Ziyang Song, Yue Li

McGill University Mila - Quebec AI Institute Montreal, Canada · Ohio University Athens, United States

Synthetic Data Generation Conditional Variational Autoencoder Longitudinal EHR Modeling Electronic Health Records Heterogeneous Federated Learning

Open paper AskPDF arXiv

Synthetic Electronic Health Record (EHR) generation provides a promising avenue for data augmentation and cross-hospital modeling in privacy-constrained healthcare settings. However, most existing EHR generative models are centralized and require pooling data across hospitals, which is often infeasible when real-world data sharing is restricted. While federated EHR generation offers a natural solution, direct federated modeling often collapses or diverges due to the high dimensionality, sparsity, and cross-hospital heterogeneity of EHR data. In this work, we propose FedEHR-Gen, the first federated framework for synthetic time-series EHR generation across distributed hospitals. FedEHR-Gen uses a two-stage learning paradigm. First, we introduce a federated autoencoder that projects high-dimensional and sparse EHR features onto a compact latent space. To ensure semantic consistency across hospitals, we develop a layer-wise matching aggregation mechanism that aligns local encoders into a unified global latent space. Second, operating on this aligned latent space, we train a federated temporal conditional variational autoencoder (TCVAE) with distribution-aware aggregation, enabling stable temporal generative modeling under severe cross-hospital heterogeneity. Extensive experiments on the eICU and MIMIC-III datasets demonstrate that FedEHR-Gen achieves generation fidelity, downstream utility, and privacy risk comparable to centralized training, while consistently outperforming the standard federated baseline.

Abstract

Federated Learning

Explore similar work

FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation

Federated generative event models for tokenized electronic health records

SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework