Digital Twin Patient Builder (ID: 208)

Function Overview

Build a "digital twin" model of a patient, integrating genotype, clinical history, and imaging data to test the efficacy and toxicity of different drug doses in a virtual environment.

Use Cases

- Personalized drug treatment plan design
Drug dose optimization
Adverse reaction risk assessment
Clinical trial virtual simulation

Input

Data Type	Description	Format
INLINECODE0	Patient genotype data (SNPs, CNVs)	JSON
INLINECODE1

Output

Output Type	Description
INLINECODE3	Efficacy prediction results
INLINECODE4

Toxicity reaction prediction | | optimal_dose | Optimal dose recommendation |

Usage

Command Line Usage

CODEBLOCK0

Parameters

Parameter	Type	Default	Required	Description
INLINECODE6	string	-	Yes	Path to patient data JSON file
INLINECODE7

string | - | Yes | Path to drug profile JSON file | | --doses | string | - | Yes | Dose range to test (JSON array format) | | --output, -o | string | - | No | Output file path for simulation results | | --simulation-days | int | 30 | No | Number of days to simulate | | --timestep | float | 0.5 | No | Simulation timestep in days |

Python API

CODEBLOCK1

Technical Architecture

CODEBLOCK2

Dependencies

- numpy >= 1.21.0
scipy >= 1.7.0
pandas >= 1.3.0

Example Data Format

Patient Data (patient_data.json)

CODEBLOCK3

Drug Profile (drug_profile.json)

CODEBLOCK4

Model Principles

1. Genotype Modeling: Parse drug metabolizing enzyme genotypes to predict metabolic phenotypes (ultrarapid/normal/poor metabolizer)
Physiological Modeling: Calculate personalized pharmacokinetic parameters based on age, weight, and organ function
Imaging Modeling: Extract tumor features to predict drug responsiveness
Integrated Model: Multi-modal data fusion to build a comprehensive digital twin
Drug Simulation: PBPK (physiologically-based pharmacokinetics) + PD (pharmacodynamics) model

References

- PBPK modeling guidelines (FDA, 2018)
Pharmacogenomics in precision medicine (Nature Reviews, 2020)

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python scripts with tools	High
Network Access

Security Checklist

- [ ] No hardcoded credentials or API keys
[ ] No unauthorized file system access (../)
[ ] Output does not expose sensitive information
[ ] Prompt injection protections in place
[ ] API requests use HTTPS only
[ ] Input validated against allowed patterns
[ ] API timeout and retry mechanisms implemented
[ ] Output directory restricted to workspace
[ ] Script execution in sandboxed environment
[ ] Error messages sanitized (no internal paths exposed)
[ ] Dependencies audited
[ ] No exposure of internal service architecture

Prerequisites

CODEBLOCK5

Evaluation Criteria

Success Metrics

- [ ] Successfully executes main functionality
[ ] Output meets quality standards
[ ] Handles edge cases gracefully
[ ] Performance is acceptable

Test Cases

1. Basic Functionality: Standard input → Expected output
Edge Case: Invalid input → Graceful error handling
Performance: Large dataset → Acceptable processing time

Lifecycle Status

- Current Stage: Draft
Next Review Date: 2026-03-06
Known Issues: None
Planned Improvements:

- Performance optimization - Additional feature support

数字孪生患者构建器 (ID: 208)

功能概述

构建患者的数字孪生模型，整合基因型、临床病史和影像数据，在虚拟环境中测试不同药物剂量的疗效和毒性。

应用场景

- 个性化药物治疗方案设计
药物剂量优化
不良反应风险评估
临床试验虚拟仿真

输入

数据类型	描述	格式
genotype	患者基因型数据（SNPs、CNVs）	JSON
clinical_history

输出

输出类型	描述
efficacyprediction	疗效预测结果
toxicityprediction

毒性反应预测 | | optimal_dose | 最佳剂量推荐 |

使用方法

命令行使用

bash
python scripts/main.py --patient patientdata.json --drug drugprofile.json --doses [50, 100, 150]

参数

参数	类型	默认值	必需	描述
--patient	字符串	-	是	患者数据JSON文件路径
--drug

字符串 | - | 是 | 药物配置文件JSON文件路径 | | --doses | 字符串 | - | 是 | 待测试剂量范围（JSON数组格式） | | --output, -o | 字符串 | - | 否 | 模拟结果输出文件路径 | | --simulation-days | 整数 | 30 | 否 | 模拟天数 | | --timestep | 浮点数 | 0.5 | 否 | 模拟时间步长（天） |

Python API

python
from scripts.main import DigitalTwinBuilder

builder = DigitalTwinBuilder()
twin = builder.buildtwin(patientdata)
results = twin.simulatedrugregimen(drugprofile, doserange)

技术架构

digital-twin-patient-builder/
├── SKILL.md # 本文件
├── scripts/
│ └── main.py # 核心实现
│
├── 核心组件:
│ ├── PatientProfile # 患者档案管理
│ ├── GenotypeModel # 基因型建模
│ ├── ClinicalModel # 临床数据建模
│ ├── ImagingModel # 影像特征建模
│ ├── DigitalTwin # 数字孪生主类
│ ├── PharmacokineticModel # 药代动力学模型
│ └── DrugSimulator # 药物模拟器

依赖项

- numpy >= 1.21.0
scipy >= 1.7.0
pandas >= 1.3.0

示例数据格式

患者数据 (patient_data.json)

json { patient_id: P001, genotype: { CYP2D6: 1/4, TPMT: 1/3C, SNPs: {rs12345: AG, rs67890: CC} }, clinical: { age: 58, weight: 70.5, height: 170, lab_values: {creatinine: 1.2, alt: 45, ast: 38}, comorbidities: [hypertension, diabetes] }, imaging: { tumor_volume: 45.2, perfusion_rate: 0.85, texture_features: {entropy: 5.2, uniformity: 0.45} } }

药物配置文件 (drug_profile.json)

json { drug_name: ExampleDrug, drug_class: chemotherapy, metabolizing_enzymes: [CYP2D6, CYP3A4], target_genes: [EGFR, KRAS], pk_params: { clearance: 15.5, volume_distribution: 45.0, half_life: 8.0 }, efficacybiomarkers: [tumorreduction, survival_rate], toxicity_markers: [neutropenia, hepatotoxicity] }

模型原理

1. 基因型建模：解析药物代谢酶基因型以预测代谢表型（超快代谢/正常代谢/慢代谢）
生理建模：基于年龄、体重和器官功能计算个性化药代动力学参数
影像建模：提取肿瘤特征以预测药物反应性
集成模型：多模态数据融合构建综合数字孪生
药物模拟：PBPK（基于生理的药代动力学）+ PD（药效学）模型

参考文献

- PBPK建模指南（FDA，2018）
精准医学中的药物基因组学（Nature Reviews，2020）

风险评估

风险指标	评估	等级
代码执行	带工具的Python脚本	高
网络访问

安全检查清单

- [ ] 无硬编码的凭据或API密钥
[ ] 无未经授权的文件系统访问（../）
[ ] 输出不暴露敏感信息
[ ] 已实施提示注入防护
[ ] API请求仅使用HTTPS
[ ] 输入已根据允许模式进行验证
[ ] 已实现API超时和重试机制
[ ] 输出目录限制在工作空间内
[ ] 在沙盒环境中执行脚本
[ ] 错误消息已清理（不暴露内部路径）
[ ] 已审计依赖项
[ ] 不暴露内部服务架构

前置条件

bash

Python依赖项

pip install -r requirements.txt

评估标准

成功指标

- [ ] 成功执行主要功能
[ ] 输出符合质量标准
[ ] 优雅处理边界情况
[ ] 性能可接受

测试用例

1. 基本功能：标准输入 → 预期输出
边界情况：无效输入 → 优雅的错误处理
性能：大数据集 → 可接受的处理时间

生命周期状态

- 当前阶段：草稿
下次审核日期：2026-03-06
已知问题：无
计划改进：

- 性能优化 - 额外功能支持

digital-twin-patient-builder数字孪生患者建模