Skip to main content

Table 5 Four example sentences for the four evidence types extracted by CIViCmine. The associated PubMed IDs are also shown for reference

From: Text-mining clinically relevant cancer biomarkers for curation into the CIViC database

Type

PMID

Sentence

Diagnostic

29214759

JAK2 V617F is the most common mutation in myeloproliferative neoplasms (MPNs) and is a major diagnostic criterion.

Predictive

28456787

In non-small cell lung cancer (NSCLC) driver mutations of EGFR are positive predictive biomarkers for efficacy of erlotinib and gefitinib.

Predisposing

28222693

Our study suggests that one BRCA1 variant may be associated with increased risk of breast cancer.

Prognostic

28469333

Overexpression of Her2 in breast cancer is a key feature of pathobiology of the disease and is associated with poor prognosis.