Abstract 95P
Background
Non-small cell lung cancer (NSCLC) is the most common subtype of lung cancer. Driver mutations in epidermal growth factor receptor (EGFR), which occur in ∼10-15% of NSCLC, can be targeted by specific therapies. Real-world data can provide valuable information regarding the prevalence of these mutations, including their subtypes. However, despite comprehensive data availability in the Dutch Pathology Registry (Palga), manual extraction of EGFR mutation status from narrative pathology reports is time-consuming. Therefore, we used machine learning and natural language processing (NLP) to identify pathology reports that state the presence of an EGFR mutation.
Methods
The NLP algorithm was trained and validated on manually curated datasets of semi-structured pathology reports from the Palga archive to generate a structured OMOP CDM database. Afterwards, pathology reports of patients with metastatic, non-squamous NSCLC in 2019-2020 were requested from the Palga registry. The output of the algorithm was compared to results of the manual extraction.
Results
The algorithm identified 839 (10.9%) reports that mention an EGFR alteration. Manual analysis indicated 875 reports, resulting in a data extraction accuracy of 95.9% (95% CI 92.7-99.2). The 36/875 (4.1%) reports that were not identified by the algorithm were all listed as variants of unknown significance (VUS) by the reader. In the EGFR-mutated patient groups, 73.0% (639/875) had a common EGFR mutation (i.e., exon 19 deletion (41.4%, 362/875) or p.(Leu858Arg) mutation (31.7%; 277/875)). Exon 20 insertions were detected in 8.1% (71/875) of patients. Automatic data processing was 48 times faster than complete manual extraction.
Conclusions
NLP algorithms allow rapid data extraction from pathology reports, thereby offering a time-efficient and cost-effective alternative to manual data processing. In turn, this approach enables rapid insight in current biomarker testing rates and prevalence of (actionable) mutations.
Editorial acknowledgement
Clinical trial identification
Legal entity responsible for the study
LynxCare Inc.
Funding
LynxCare Inc.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
169P - A real-world molecular pre-screening program in advanced breast cancer (ABC) at Institut Català d'Oncologia l'Hospitalet: Clinical practice study to assess treatment-decision choice based on molecular results
Presenter: David Lluís Garulo
Session: Cocktail & Poster Display session
Resources:
Abstract
170P - KRAS status in patients with pancreatic ductal adenocarcinoma: A single-center study from 2020 to 2023
Presenter: Manukyan Mariam
Session: Cocktail & Poster Display session
Resources:
Abstract
171P - Benefit of next-generation sequencing for lung cancer patients in a limited-resource area
Presenter: Kijjakom Thanasombunsukh
Session: Cocktail & Poster Display session
Resources:
Abstract
172P - Survival prediction using CT based radiomic features in patients of pancreatic cancer treated by chemotherapy followed by SBRT: A pilot study
Presenter: Divya Khosla
Session: Cocktail & Poster Display session
Resources:
Abstract
173P - Overcoming monocyte imbalance and T cell exhaustion in obesity-associated colorectal cancer liver metastasis
Presenter: Alyssa Cristea
Session: Cocktail & Poster Display session
Resources:
Abstract
174TiP - A pivotal clinical trial of a functional ex vivo organ culture assay for cancer precision medicine
Presenter: Sandra Hanks
Session: Cocktail & Poster Display session
Resources:
Abstract
177TiP - Myeloid-derived suppressor cells in the peripheral blood of patients with colorectal cancer: A trial in progress
Presenter: Hans Raskov
Session: Cocktail & Poster Display session
Resources:
Abstract