Clinical De-identification

**Clinical De-identification:**

The Clinical De-Identification Model is engineered to pinpoint and anonymize PHI in English-language clinical documentation. It skillfully identifies sensitive data, including patient identifiers, medical record numbers, and other confidential information. Upon detection, the PHI undergoes a sophisticated obfuscation process. This transformation alters the text to maintain its usability for research and analysis while effectively concealing patient-specific details.

**Key Features:**
- Expertly crafted to recognize and obfuscate a diverse array of PHI elements within medical texts, assuring thorough anonymization.
- The obfuscation process is meticulously designed to adhere to HIPAA and other healthcare-related privacy laws, contributing to regulatory compliance and safeguarding patient information.
- Ideally suited for use in healthcare research, data analytics, and educational settings, this model facilitates the secure exploitation of clinical data, negating risks to patient privacy.
This model stands as an invaluable tool in healthcare and research domains, prioritizing patient confidentiality. It enables the ethical and compliant use of critical medical data, fostering advanced research and knowledge dissemination while rigorously maintaining data privacy and security.

**Additional Model Information**
- [Industry Use-Case Demo](https://demo.johnsnowlabs.com/healthcare/DEID_PHI_TEXT_MULTI/)
- [Full model info on John Snow Labs Models Hub](https://nlp.johnsnowlabs.com/2023/07/11/clinical_deidentification_en.html)
- **Domain:** Clinical Data Privacy
- **Subdomain:** PHI Masking and De-identification
- **Predictable entities:** AGE, CONTACT, DATE, ID, LOCATION, NAME, PROFESSION, CITY, COUNTRY, DOCTOR, HOSPITAL, IDNUM, MEDICALRECORD, ORGANIZATION, PATIENT, PHONE, PROFESSION, STREET, USERNAME, ZIP, ACCOUNT, LICENSE, VIN, SSN, DLN, PLATE, IPADDR
- **Deployment Identifier:** 2. Clinical De-identification (Obfuscate)

**How to run this model:**
1. Acquire a John Snow Labs Pay As You Go (PAYG) license from [John Snow Labs](https://my.johnsnowlabs.com/).
2. Import this listing.
3. Use the attached notebook to deploy the model with **2. Clinical De-identification (Obfuscate)** as the model parameter. **Do not use the Open button on this page which appears after importing this listing. It will fail to deploy a model and does not work yet, you must use the attached notebook.**.

This model comes with optimized CPU and GPU builds. You can select which one to deploy via the notebook.

**How to obtain a PAYG license:**
1. Access [my.JohnSnowLabs.com](https://my.johnsnowlabs.com) and log in to your account. If you don't have an account, create one.
2. Go to the Get License page.
3. Switch to the PAYG Subscription tab and provide your credit card details.
4. Carefully review the End User License Agreement and the Terms and Conditions documents. If you agree, click on the Create Subscription button.
5. Once the process is complete, you will find your PAY-As-You-GO license listed on the My Subscriptions page.
6. Visit the My Subscriptions page and copy the PAYG license key by clicking on the copy icon in the License Key column.
7. Go to your Databricks notebook and paste your JSL-license into the JSL-License field in the top of the notebook. You are now ready to go!

**临床去标识化：**

临床去标识化模型（Clinical De-identification Model）专为识别并匿名化英文临床文档中的受保护健康信息（Protected Health Information, PHI）而研发。该模型可精准识别各类敏感数据，包括患者标识符、病历编号及其他机密信息。一旦检测到受保护健康信息，模型将通过复杂的混淆处理流程对其进行转换：在保留文本可用于研究与分析的可用性的同时，有效隐藏患者的个性化细节。

**关键特性：**
- 针对医疗文本中多样化的受保护健康信息元素，该模型可实现精准识别与混淆处理，确保全面的匿名化效果。
- 混淆处理流程严格遵循《健康保险流通与责任法案》（Health Insurance Portability and Accountability Act, HIPAA）及其他医疗相关隐私法规，助力合规性建设，切实保护患者信息安全。
- 该模型适配医疗研究、数据分析及教育场景，可安全地利用临床数据，同时规避患者隐私泄露风险。

本模型是医疗与研究领域的宝贵工具，始终将患者保密性置于首位。它可实现关键医疗数据的合规且伦理化使用，推动前沿研究与知识传播，同时严格保障数据隐私与安全。

**附加模型信息**
- [行业用例演示](https://demo.johnsnowlabs.com/healthcare/DEID_PHI_TEXT_MULTI/)
- [约翰·斯诺实验室（John Snow Labs）模型中心完整模型信息](https://nlp.johnsnowlabs.com/2023/07/11/clinical_deidentification_en.html)
- **领域：** 临床数据隐私
- **子领域：** 受保护健康信息遮蔽与去标识化
- **可识别实体：** 年龄（AGE）、联系方式（CONTACT）、日期（DATE）、标识符（ID）、地理位置（LOCATION）、姓名（NAME）、职业（PROFESSION）、城市（CITY）、国家（COUNTRY）、医生（DOCTOR）、医院（HOSPITAL）、编号（IDNUM）、病历号（MEDICALRECORD）、组织机构（ORGANIZATION）、患者（PATIENT）、电话（PHONE）、职业（PROFESSION）、街道（STREET）、用户名（USERNAME）、邮编（ZIP）、账户（ACCOUNT）、许可证号（LICENSE）、车辆识别码（VIN）、社会安全号码（SSN）、驾照号码（DLN）、车牌（PLATE）、IP地址（IPADDR）
- **部署标识符：** 2. 临床去标识化（混淆模式）

**如何运行此模型：**
1. 从[约翰·斯诺实验室（John Snow Labs）](https://my.johnsnowlabs.com/)获取按需付费（Pay As You Go, PAYG）许可证。
2. 导入此模型条目。
3. 使用附带的笔记本部署模型，需将**2. 临床去标识化（混淆模式）**作为模型参数。**请勿使用导入此条目后本页面出现的“打开”按钮，该按钮目前无法成功部署模型，请务必使用附带的笔记本。**

本模型提供优化后的CPU与GPU构建版本，您可通过笔记本选择所需的部署类型。

**如何获取按需付费许可证：**
1. 访问[my.JohnSnowLabs.com](https://my.johnsnowlabs.com)并登录账户，若无账户请先注册。
2. 进入“获取许可证”页面。
3. 切换至“按需付费订阅”标签页，提供您的信用卡信息。
4. 仔细阅读最终用户许可协议与条款文档，确认无误后点击“创建订阅”按钮。
5. 流程完成后，您可在“我的订阅”页面找到您的按需付费许可证。
6. 进入“我的订阅”页面，点击许可证密钥列的复制图标，复制您的按需付费许可证密钥。
7. 进入您的Databricks笔记本，将JSL许可证粘贴至笔记本顶部的JSL-许可证字段中，即可完成配置。