Generating realistic tabular medical data usually comes with a frustrating trade-off: deep learning models (CTGAN, Diffusion) are slow, GPU-heavy, and prone to violating clinical rules.
To solve this, we built a transparent, ultra-fast Two-Stage Generative Engine combining Class-Conditional Gaussian Copulas and Decision Trees.
β‘ Key Benchmarks:
- Speed: 10,000 patients in 0.17s | 1,000,000 patients in ~6.9s (standard CPU)
- Privacy: 0 duplicate records against real datasets (Gower DCR: 0.0789)
- Clinical Logic: 100.0% rule compliance (0 boundary violations, non-asthmatics strictly 'N/A')
- ML Utility (TSTR): Classifiers trained on synthetic data achieve $\Delta \text{ROC-AUC} \le 0.0013$ on real test data
π οΈ How It Works:
- Prevalence (Stage 0): Bernoulli sampling matching ground-truth diagnosis prevalence (~24.3%).
- Class-Conditional Gaussian Copula (Stage 1): Captures non-linear dependencies across 14 features using empirical quantiles and Cholesky decomposition.
-
Decision Tree (Stage 2): Deterministically assigns
Asthma_Control_Level, perfectly decoupling non-asthmatics.
π Scientific Validation (4 Pillars):
| Pillar | Metric | Result | Status |
|---|---|---|---|
| Statistical Fidelity | Mean Diffs / Correlation Diff | < 0.6% / 0.0225 | PASS |
| Clinical Logic | Boundary Violations / Non-Asthmatic Rule | 0 Violations / 100% 'N/A' | PASS |
| Privacy Guarantee | Exact Clones vs Real Data | 0 Duplicates | PASS |
| ML Utility (TSTR) | Random Forest $\Delta \text{ROC-AUC}$ | 0.0013 | PASS |
Provenance note: Fitted on Arif Miah's (miadul) Apache 2.0 dataset on Kaggle. Replicates synthetic data distributions, not human biology.
π Live Interactive App & Resources:
Live Hugging Face Space (Try generating cohorts up to 1M):
https://huggingface.co/spaces/abdurrahman-hakan-acar/synthetic-asthma-generatorKaggle Benchmark Dataset (10k Patients - Usability 9.41):
https://www.kaggle.com/datasets/abdurrahmanhakanacar/synthetic-asthma-medical-dataset-10k-patientsKaggle EDA & Baseline ML Notebook:
https://www.kaggle.com/code/abdurrahmanhakanacar/synthetic-asthma-data-eda-risk-factor-modelingKaggle On-Demand Generator Notebook:
https://www.kaggle.com/code/abdurrahmanhakanacar/synthetic-asthma-data-generator-on-demand-custom
What is your preferred approach for tabular data synthesis: statistical copulas or deep neural nets? Let's discuss below!
Top comments (0)