From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories

• URL: http://arxiv.org/abs/2603.06720v1
• Date: Fri, 06 Mar 2026 00:17:59 GMT
• Title: From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories
• Abstract summary: We developed a pipeline to make synthetic patient trajectories clinically consistent.<n>We generated 18,071 synthetic patient records from a source of 180,712 real patients.<n>We found no evidence of privacy risks, with membership performance indistinguishable from random guessing.
• Score: 0.8261055975875736
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Access to electronic health records (EHRs) for digital health research is often limited by privacy regulations and institutional barriers. Synthetic EHRs have been proposed as a way to enable safe and sovereign data sharing; however, existing methods may produce records that capture overall statistical properties of real data but present inconsistencies across clinical processes and observations. We developed an integrated pipeline to make synthetic patient trajectories clinically consistent through two synergistic steps: high-fidelity generation and scalable auditing. Using the MIMIC-IV database, we trained a knowledge-grounded generative model that represents nearly 32,000 distinct clinical events, including demographics, laboratory measurements, medications, procedures, and diagnoses, while enforcing structural integrity. To support clinical consistency at scale, we incorporated an automated auditing module leveraging large language models to filter out clinical inconsistencies (e.g., contraindicated medications) that escape probabilistic generation. We generated 18,071 synthetic patient records derived from a source cohort of 180,712 real patients. While synthetic clinical event probabilities demonstrated robust agreement (mean bias effectively 0.00) and high correlation (R2=0.99) with the real counterparts, review of a random sample of synthetic records (N=20) by three clinicians identified inconsistencies in 45-60% of them. Automated auditing reduced the difference between real and synthetic data (Cohen's effect size d between 0.59 and 1.60 before auditing, and between 0.18 and 0.67 after auditing). Downstream models trained on audited data matched or even exceeded real-data performance. We found no evidence of privacy risks, with membership inference performance indistinguishable from random guessing (F1-score=0.51).

Related papers

• Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets [0.06372261626436676]
  The present work addresses the gap by validating the FedCVR framework on five publicly available real cardiovascular datasets.<n>Results demonstrate that FedCVR preserves its adaptive advantage on real data, achieving an F1-Score of 79.2% and AUC of 0.96.<n>The measured privacy cost on real data confirms the graceful degradation pattern observed in the synthetic experiments.
  arXiv  Detail & Related papers  (2026-07-07T18:51:13Z)
• PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization [1.9205944025326402]
  We present PSyGenTAB, a framework for balancing privacy protection and clinical utility in synthetic healthcare data.<n>PSyGenTAB enforces minimum privacy thresholds while maximizing clinical data utility.<n>Downstream evaluation shows that models trained on synthetic data achieve performance comparable to those trained on real patient records.
  arXiv  Detail & Related papers  (2026-06-16T22:14:40Z)
• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture [71.46525715889656]
  General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement.<n>We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record.<n>We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions.
  arXiv  Detail & Related papers  (2026-04-29T17:59:28Z)
• DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data [2.3915781021862332]
  DISCO-TAB is a novel framework that orchestrates a fine-tuned LLM with a multi-objective discriminator system optimized via Reinforcement Learning.<n>We rigorously validate our framework across diverse benchmarks, including high-dimensional, small-sample medical datasets.<n>Our results demonstrate that hierarchical feedback yields state-of-the-art performance, achieving up to 38.2% improvement in downstream clinical utility.
  arXiv  Detail & Related papers  (2026-04-01T23:37:58Z)
• Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model [95.41752463487008]
  Parkinson's disease affects over ten million people worldwide.<n>Inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost.<n>We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI.
  arXiv  Detail & Related papers  (2026-03-31T02:36:10Z)
• Image-based Quantification of Postural Deviations on Patients with Cervical Dystonia: A Machine Learning Approach Using Synthetic Training Data [42.305152571036786]
  Cervical dystonia (CD) is the most common form of dystonia.<n>Current assessment relies on subjective clinical rating scales, such as the Toronto Western Spasmodic Torticollis Rating Scale (TWSTRS)<n>We developed an assessment tool that combines a pretrained head-pose estimation algorithm for rotational symptoms with a deep learning model trained exclusively on 16,000 synthetic avatar images.
  arXiv  Detail & Related papers  (2026-03-27T14:12:41Z)
• LiveClin: A Live Clinical Benchmark without Leakage [50.45415584327275]
  LiveClin is a live benchmark designed for approximating real-world clinical practice.<n>We transform authentic patient cases into complex, multimodal evaluation scenarios that span the entire clinical pathway.<n>Our evaluation of 26 models on LiveClin reveals the profound difficulty of these real-world scenarios, with the top-performing model achieving a Case Accuracy of just 35.7%.
  arXiv  Detail & Related papers  (2026-02-18T03:59:46Z)
• Federated Proximal Optimization for Privacy-Preserving Heart Disease Prediction: A Controlled Simulation Study on Non-IID Clinical Data [1.620240963217448]
  This paper presents a comprehensive simulation research of Federated Proximal Optimization (FedProx) for Heart Disease prediction based on UCI Heart Disease dataset.<n>We generate realistic non-IID data partitions by simulating four heterogeneous hospital clients from the Cleveland Clinic.<n>Our results are directly transferable to hospital IT-administrators, implementing privacy-preserving collaborative learning.
  arXiv  Detail & Related papers  (2026-01-23T21:18:08Z)
• CoSMeTIC: Zero-Knowledge Computational Sparse Merkle Trees with Inclusion-Exclusion Proofs for Clinical Research [2.0497679299764355]
  CoSMeTIC is a zero-knowledge computational framework that generates verifiable inclusion and exclusion proofs for individual participants' data in clinical studies.<n>We demonstrate that CoSMeTIC achieves strong privacy guarantees while maintaining statistical fidelity.<n>Our results suggest that CoSMeTIC provides a scalable and practical alternative for achieving regulatory compliance with rigorous privacy protection in large-scale clinical research.
  arXiv  Detail & Related papers  (2026-01-17T18:47:17Z)
• One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training [45.49415063761575]
  EndoRare is a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image.<n>We validated the framework across four rare pathologies.<n>These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.
  arXiv  Detail & Related papers  (2025-12-30T15:07:09Z)
• A Hybrid Machine Learning Approach for Synthetic Data Generation with Post Hoc Calibration for Clinical Tabular Datasets [0.9940728137241215]
  Healthcare research and development face significant obstacles due to data scarcity and stringent privacy regulations.<n>We produce artificial datasets that emulate real data statistics while safeguarding patient privacy.<n>This scalable, privacy-preserving approach matches state-of-the-art methods, sets new benchmarks for joint-distribution fidelity in healthcare.
  arXiv  Detail & Related papers  (2025-10-12T09:23:43Z)
• DualAlign: Generating Clinically Grounded Synthetic Data [9.87164447021602]
  We introduce DualAlign, a framework that enhances statistical fidelity and clinical plausibility through dual alignment.<n>Using Alzheimer's disease (AD) as a case study, DualAlign produces context-grounded symptom-level sentences.<n>Fine-tuning an LLaMA 3.1-8B model with a combination of DualAlign-generated and human-annotated data yields substantial performance gains.
  arXiv  Detail & Related papers  (2025-09-05T18:04:38Z)
• Auditing and Generating Synthetic Data with Controllable Trust Trade-offs [54.262044436203965]
  We introduce a holistic auditing framework that comprehensively evaluates synthetic datasets and AI models. It focuses on preventing bias and discrimination, ensures fidelity to the source data, assesses utility, robustness, and privacy preservation. We demonstrate the framework's effectiveness by auditing various generative models across diverse use cases.
  arXiv  Detail & Related papers  (2023-04-21T09:03:18Z)
• Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model [40.473866438962034]
  Synthetic electronic health records can serve as an alternative to real EHRs for machine learning (ML) modeling and statistical analysis. We propose Hierarchical Autoregressive Language mOdel (HALO) for generating longitudinal high-dimensional EHR.
  arXiv  Detail & Related papers  (2023-04-04T23:53:34Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.