GENETEX

GENETEX extracts and structures clinico-genomic data from electronic health records to enable genomic analyses and integration with clinical research datasets in oncology.

Key Features:

• Text mining / NLP: Employs natural language processing techniques to identify and extract genomic information from unstructured clinical narratives and genomic reports in EHRs.
• Data transformation: Converts semistructured clinico-genomic data into structured datasets suitable for analysis and integration.
• REDCap integration: Facilitates direct importation of processed data into Research Electronic Data Capture (REDCap) for clinical research data management.
• Accuracy and efficiency: Demonstrated over 99% agreement with manual abstraction and reduced extraction time to approximately one-fifth of manual processes.
• Implementation: Provided as an R package for programmatic use.

Scientific Applications:

• Precision medicine: Enables incorporation of detailed genomic profiles from routine clinical practice into individualized oncology treatment decisions.
• Clinical research: Supports retrospective and prospective studies that require curated clinico-genomic datasets derived from EHRs.
• Data standardization: Assists in harmonizing genomic data across healthcare systems by producing structured, consistent datasets.

Methodology:

Performs text mining using natural language processing to parse unstructured clinical and genomic reports, converts extracted information into structured formats compatible with REDCap, and supports automated importation into REDCap.