ICD-O Clinical Terminology Mapper

**ICD-O Clinical Terminology Mapper**

This model is tailored for oncology-specific clinical documentation. It helps identify oncological entities in medical texts and accurately maps them to the appropriate International Classification of Diseases for Oncology (ICD-O) codes. This model is crucial for detailed and precise cancer-related coding in medical records, research, and billing.

**Key Features:**
- The model identifies oncological entities and maps them to the most relevant ICD-O codes, offering a high level of detail, especially concerning body part references. The model also returns the original Topography (site of the tumor) and Histology (tumor characteristics) codes, along with their detailed descriptions. This feature ensures that the coding reflects the specific nature and location of the cancer.
- It provides the top terms and resolutions associated with each identified entity, allowing for a comprehensive understanding of the cancer's characteristics and its coding implications.
- By facilitating the accurate and granular ICD-O coding, the model significantly improves the precision and quality of oncological clinical documentation.

This model assists in medical billing and coding by providing a solution for accurate and comprehensive coding related to oncology, primarily for billing and insurance purposes. It aids in aggregating and analyzing oncological data for clinical research, leveraging precise and standardized coding. Additionally, it supports healthcare professionals in maintaining detailed and accurate medical records for cancer patients, contributing to improved healthcare documentation in oncology.

**Additional Model Information**
- [Full model info on John Snow Labs Models Hub](https://nlp.johnsnowlabs.com/2024/02/02/icdo_resolver_pipeline_en.htmll)
- **Domain:** Clinical Text Analysis
- **Subdomain:** Terminology Codes
- **Predictable entities:** ICD-O Codes

**How to run this model:**
1. Acquire a John Snow Labs license from [Sales](mailto:[e-mail])
2. Import this listing.
3. See the attached notebook to deploy and use the model.

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