Statistical simulation platform for designing and validating adaptive clinical trial designs in silico. Enables optimization of interim analysis strategies, sample size adaptation, and early stopping rules while maintaining Type I error control.
# Run standard group sequential design
python scripts/main.py
# Adaptive design with sample size re-estimation
python scripts/main.py --design adaptive_reestimate
# Optimize design parameters
python scripts/main.py --optimize
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
| ----------- | ------ | --------- | ---------- | ------------- |
--design | str | group_sequential | No | Trial design type |
--n-simulations | int | 10000 | No | Number of Monte Carlo simulations |
--sample-size | int | 200 | No | Initial sample size per arm |
--effect-size | float | 0.3 | No | Effect size (Cohen's d) |
--alpha | float | 0.05 | No | Type I error rate |
--power | float | 0.80 | No | Target statistical power |
--interim-looks | int | 1 | No | Number of interim analyses |
--spending-function | str | obrien_fleming | No | Alpha spending function |
--reestimate-method | str | promising_zone | No | Sample size re-estimation method |
--output | str | results.json | No | Output file path |
--visualize | flag | False | No | Generate visualization charts |
--optimize | flag | False | No | Search for optimal design parameters |
# Full adaptive design with visualization
python scripts/main.py \
--design adaptive_reestimate \
--n-simulations 50000 \
--sample-size 250 \
--effect-size 0.35 \
--interim-looks 2 \
--spending-function obrien_fleming \
--visualize \
--output adaptive_results.json
| Design Type | Description | Use Case |
|---|---|---|
| ------------- | ------------- | ---------- |
| Group Sequential | Fixed interim looks with stopping boundaries | Standard adaptive trials |
| Adaptive Re-estimate | Sample size adjustment based on interim data | Uncertain effect size |
| Drop the Loser | Multi-arm trials dropping inferior arms | Phase II dose selection |
| Function | Characteristics | Early Boundary |
|---|---|---|
| ---------- | ---------------- | ---------------- |
| O'Brien-Fleming | Conservative early | High Z-scores early |
| Pocock | Aggressive early | Lower Z-scores throughout |
| Power Family | Moderate (ρ=3) | Balanced approach |
{
"design_config": {
"design_type": "adaptive_reestimate",
"sample_size_per_arm": 200,
"effect_size": 0.3,
"alpha": 0.05,
"target_power": 0.8
},
"simulation_results": {
"power": 0.8234,
"type_i_error": 0.0481,
"expected_sample_size": 385.2,
"early_stop_rate": {
"efficacy": 0.1523,
"futility": 0.0841
}
}
}
⚠️ AI自主验收状态: 需人工检查
This skill requires:
pip install -r requirements.txt
numpy>=1.20.0
scipy>=1.7.0
matplotlib>=3.4.0
| Risk Indicator | Assessment | Level |
|---|---|---|
| ---------------- | ------------ | ------- |
| Code Execution | Python scripts with mathematical calculations | Medium |
| Network Access | No network access | Low |
| File System Access | Writes simulation results | Low |
| Instruction Tampering | Statistical parameters could affect results | Medium |
| Data Exposure | No sensitive data exposure | Low |
pip install -r requirements.txt
python scripts/main.py --help
Available in references/:
⚠️ DISCLAIMER: This tool provides simulation results for research and planning purposes only. All clinical trial designs should be reviewed by qualified biostatisticians and regulatory experts before implementation.
共 1 个版本