「優れたモデルの構築は仕事の 10% にすぎません。残りの 90% は規制、臨床検証、展開です。」 ――医療AI業界の現実。
1. SaMD — 医療機器としてのソフトウェア
FDA は SaMD を次のように定義しています。
1 つ以上の医療目的で使用することを目的としたソフトウェアで、ハードウェア医療機器の一部ではなくこれらの目的を実行します。
診断をサポートするために使用される AI/ML モデル = SaMD。
リスク分類マトリックス
| SaMDクラス | 患者のリスク | FDA パスウェイ | 例 |
|---|---|---|---|
| クラス I | 低い | 510(k) 免除または迅速化 | 基本的な心拍数モニタリング |
| クラス II | 平均 | 510(k) または De Novo | AI が糖尿病性網膜症を検出 |
| クラスⅢ | 曹操 | PMA (市販前承認) | AIがインスリンポンプを制御 |
クラスを決定するためのルール:
Healthcare situation severity × Significance of information
CRITICAL × CRITICAL = Class III (highest, PMA)
CRITICAL × SERIOUS = Class III
SERIOUS × CRITICAL = Class III
SERIOUS × SERIOUS = Class IIb (De Novo)
NON-SERIOUS × any = Class I/IIa (510k)
2. FDA 510(k) パスウェイ — 詳細
510(k) = 市場前通知。述語デバイスとの実質的同等性の証明が必要です。
# Tài liệu cần chuẩn bị cho 510(k) AI/ML:
SUBMISSION_CHECKLIST = {
"device_description": [
"Software architecture diagram",
"Training data description (source, size, demographics)",
"Algorithm description (model type, hyperparameters)",
"Intended use statement",
"Contraindications and limitations",
],
"performance_testing": [
"Standalone performance: sensitivity, specificity, AUC",
"Sub-group analysis: age, sex, race, disease severity",
"Comparison to predicate device",
"Clinical study: reader study with radiologists",
],
"cybersecurity": [
"SBOM (Software Bill of Materials)",
"Threat modeling",
"Security testing results",
"Patch management plan",
],
"ai_ml_specific": [
"Predetermined change control plan (PCCP)", # FDA 2023
"Algorithmic fairness analysis",
"Training/validation/test data split methodology",
"Distributional shift analysis",
]
}
＃＃＃２．１．読者調査のデザイン (510k にとって重要)
from scipy import stats
import numpy as np
def reader_study_analysis(
ai_sensitivities: list[float],
ai_specificities: list[float],
reader_sensitivities: list[float],
reader_specificities: list[float]
):
"""
FDA yêu cầu Non-Inferiority Study:
AI performance >= Radiologist performance - non-inferiority margin
Typical margin: 5% for sensitivity (không thể miss nhiều hơn 5% so với radiologist)
Thiết kế: Multi-reader Multi-case (MRMC)
- N cases (200-500+ cho rare disease)
- M readers (5-10 radiologists)
- AI vs readers (paired comparison)
"""
# Non-inferiority test cho sensitivity
ni_margin = 0.05 # 5% non-inferiority margin
mean_ai_sens = np.mean(ai_sensitivities)
mean_reader_sens = np.mean(reader_sensitivities)
# Compare distributions
t_stat, p_value = stats.ttest_ind(
ai_sensitivities, reader_sensitivities,
alternative='greater' # H1: AI >= Reader - margin
)
# 95% confidence interval
diff = mean_ai_sens - mean_reader_sens
se = np.std(np.array(ai_sensitivities) - np.array(reader_sensitivities)) / np.sqrt(len(ai_sensitivities))
ci_lower = diff - 1.96 * se
ci_upper = diff + 1.96 * se
non_inferior = ci_lower > -ni_margin
return {
"ai_mean_sensitivity": round(mean_ai_sens, 4),
"reader_mean_sensitivity": round(mean_reader_sens, 4),
"difference": round(diff, 4),
"ci_95_lower": round(ci_lower, 4),
"ci_95_upper": round(ci_upper, 4),
"non_inferior": non_inferior,
"p_value": round(p_value, 4),
"conclusion": (
"AI is non-inferior to radiologists" if non_inferior
else "AI did not demonstrate non-inferiority"
)
}
3. 事前に決定された変更管理計画 (PCCP)
AI/ML ベースの SaMD に関する FDA 2023 ガイダンス: 以下の場合、完全な再送信なしでモデルの更新が許可されます。
PCCP_REQUIREMENTS = {
"description_of_modifications": {
"algorithm_changes": "Retraining trên new data, same architecture",
"performance_goals": {
"sensitivity": ">= 85%",
"specificity": ">= 90%",
"auc": ">= 0.90",
},
"out_of_scope_changes": [
"New intended use (cần submission mới)",
"New patient population",
"Architecture changes (same model family OK)",
]
},
"monitoring_protocol": {
"real_world_performance_tracking": True,
"drift_detection_metrics": ["PSI", "KS test", "performance drift"],
"retrigger_training_conditions": [
"AUC drops below 0.85 for 30 consecutive days",
"Distribution shift PSI > 0.25",
],
"hold_out_reference_dataset": "Lock 500-sample reference set for comparison"
},
"verification_and_validation": {
"testing_on_new_data": True,
"comparison_to_locked_reference_performance": True,
"bias_analysis": ["sex", "age", "race", "disease_severity"],
}
}
4. EU AI法(2024年)とベトナム
EU AI 法 — 高リスク AI システム
Medical AI = HIGH RISK → nghĩa vụ nghiêm ngặt:
1. Risk Management System
2. Data Governance (quality, representativeness, documentation)
3. Technical Documentation
4. Transparency (người dùng biết đang dùng AI)
5. Human Oversight (bác sĩ vẫn có final decision)
6. Accuracy, Robustness, Cybersecurity
7. Conformity Assessment (CE marking)
ベトナム — 2024 年の法的枠組み
VN_REGULATORY_FRAMEWORK = {
"primary_laws": [
"Luật Khám chữa bệnh 2023 (Luật 15/2023/QH15)",
"Nghị định hướng dẫn thiết bị y tế (2022)",
"Thông tư về phần mềm y tế (Bộ Y tế)",
],
"key_requirements": {
"registration": "Đăng ký thiết bị y tế tại Cục Quản lý Dược",
"clinical_approval": "Thử nghiệm lâm sàng tại Bệnh viện hạng I hoặc Trung ương",
"data_protection": "Luật An ninh mạng 2018, Nghị định BVLCC",
"ai_specific": "Chưa có luật riêng — áp dụng khung thiết bị y tế chung",
},
"timeline_estimate": "12-24 tháng cho sản phẩm AI y tế lần đầu",
}
5. ドキュメントのフレームワーク
def generate_510k_summary_template(product_info: dict) -> str:
"""Generate FDA 510(k) Summary template."""
return f"""
FDA 510(k) SUMMARY
==================
Device Name: {product_info.get('device_name')}
Applicant: {product_info.get('company')}
Date of Summary: {product_info.get('date')}
INDICATIONS FOR USE:
{product_info.get('indications_for_use')}
DEVICE DESCRIPTION:
Type: AI/ML-based Software as a Medical Device (SaMD)
Input: {product_info.get('input_description')}
Output: {product_info.get('output_description')}
Intended User: {product_info.get('intended_user')}
PREDICATE DEVICE(S):
{product_info.get('predicate_devices')}
SUMMARY OF PERFORMANCE TESTING:
Primary Analysis Population: {product_info.get('test_population')}
Sensitivity: {product_info.get('sensitivity')} (95% CI: {product_info.get('sens_ci')})
Specificity: {product_info.get('specificity')} (95% CI: {product_info.get('spec_ci')})
AUC: {product_info.get('auc')} (95% CI: {product_info.get('auc_ci')})
CONCLUSION:
{product_info.get('device_name')} is substantially equivalent to predicate device(s)
and is safe and effective for its intended use.
"""
6. 演習
-
以下の 5 種類の医療 AI ソフトウェアを SaMD クラスに従って分類し、適切な FDA 経路を決定します: (a) AI による糖尿病性網膜症の検出、(b) AI トリアージ COVID-19 CT、(c) AI による化学療法の投与推奨、(d) AI ウェルネス アプリの歩数カウント、(e) AI による ICU での敗血症予測。
-
AI 胸部 X 線検査の読者研究の設計: 必要な症例数、非劣性基準、統計解析計画。
-
レッスン 4 で構築した AI モデルの PCCP アウトラインの草案を作成します。
レッスン 14: 医療 AI の導入 — HIPAA 準拠、実稼働対応。