Skip to main content

Table 1 Six categories of gene mentions in clinical trial documents.

From: Identifying the status of genetic lesions in cancer clinical trial documents using machine learning

Category

Definition

Examples

ID

Stage I

Stage II

  

1

Gene-related

Genetic lesion detected

Genetic lesion status is detected.

• Positive EGFR mutation test...

• Patient with EGFR positive ...

2

 

Genetic lesion not detected

Genetic lesion status is Not Detected.

• ...negative staining for Kit.

• Patient must have wild type KRAS.

3

 

Genetic lesion mentioned

Analysis of genetic lesion is mentioned but not particular results

• BRAF - gene analysis of archival tissue

• mutational analysis of genes such as EGFR ...

4

 

Gene only

It refers to the gene entity only, no status is associated.

• KIT is a gene that codes for ...

• WT1 is a protein in cancer cells that regulates gene expression and ...

5

Drug

 

Gene related drugs, drug classes, or other therapy

• WT1 Peptide Vaccination in Carcinomas.

• Prior treatment with EGFR inhibitor chemotherapy...

6

Others

 

None of the above classes, e.g., English words,

• ...using the kit and testing procedures.

• Criteria are met.