Evaluation of AI-Generated Synthetic Data for Clinical Research in Secondary Cardiovascular Prevention among Dyslipidemia Patients
Abstract
Background: Access to high-quality clinical data is essential for advancing medical research and developing effective medical statistical and Artificial Intelligence models. However, privacy regulations and logistical barriers often hinder timely access to real-world data. Synthetic data offer a promising solution, preserving the statistical characteristics of original datasets while protecting patient privacy.
Objectives: This study investigates the use of synthetic data for secondary cardiovascular prevention in patients with dyslipidemia, using two real-world datasets from Centro Cardiologico Monzino.
Methods: Given the high dimensionality and limited sample size of the datasets, we employed a custom generative framework based on Large Language Models (LLMs). Pre-trained LLMs were fine-tuned on original clinical records to synthesize tabular data replicating source-data distributions. Fine-tuning was performed within the Centro Cardiologico Monzino’s secure infrastructure to ensure data sovereignty. We evaluate clinical utility and privacy using fidelity and privacy metrics, identifying the optimal generative model and benchmarking against traditional anonymization methods.
Results: Synthetic data achieved a superior trade-off than classically anonymized datasets. Real and synthetic datasets showed strong agreement, with significant distributional differences limited to few variables. Models trained on synthetic data replicated key associations from the original dataset,…
Read the paper
Related studies
- Biportal endoscopic versus microscopic lumbar decompressive laminectomy in patients with spinal stenosis: A randomized controlled trial
- A whey protein-based multi-ingredient nutritional supplement stimulates gains in lean body mass and strength in healthy older men: A randomized controlled trial
- Supplement-based nutritional strategies to tackle frailty: A multifactorial, double-blind, randomized placebo-controlled trial
- A randomized, double-blind, placebo-controlled, proof-of-concept trial of creatine monohydrate as adjunctive treatment for bipolar depression
- Creatine supplementation (3 g/day) and bone health in older women: a 2-year, randomized, placebo-controlled trial
- A Multi-Ingredient Nutritional Supplement in Combination With Resistance Exercise and High-Intensity Interval Training Improves Cognitive Function and Increases N-3 Index in Healthy Older Men: A Randomized Controlled Trial
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.