19 June 2026 in Lung Cancer
Identifying the primary tumor in cancer of unknown primary (CUP) remains a major clinical challenge. While WGS-based tissue-of-origin (TOO) prediction has improved diagnostic precision, its use is constrained by cost and availability. We investigated whether a low-complexity surrogate, combining SMARCA4 mutations and smoking history, can identify a lung cancer origin in CUP (CUP-Lung). We retrospectively identified 305 provisional CUP cases from two Dutch CUP referral centers (2022-2025). Integration of whole-genome sequencing (WGS)-based TOO prediction with clinicopathological data identified 58 patients (18.9%) with CUP-Lung. Associations between SMARCA4 mutations, smoking history, and CUP-Lung were assessed using comparative and regression analyses. SMARCA4 mutations were present in 36.2% of CUP-Lung cases, significantly higher than in the overall CUP cohort (10.7%) and TCGA lung cancer datasets (6-8%). CUP-Lung cases had higher tumor mutational burden (median 21.5 vs. 12.6 mut/Mb, p < 0.001) and enriched smoking-related mutational signatures (p < 0.001). Smoking history was reported in 87.9% of cases. Smoking history (OR 4.9, 95% CI 2.2-10.9, p < 0.001) and SMARCA4 mutation (OR 10.3, 95% CI 4.5-23.8, p < 0.001) independently predicted CUP-Lung, together conferring a 76.0% probability of lung origin. No statistical differences were found between cases with and without detectable pulmonary involvement. Combined smoking history and SMARCA4 mutations support lung cancer classification even in the absence of detectable pulmonary involvement enabling organ-directed treatment when WGS is unavailable.
1 July 2026 in JCO Clinical Cancer Informatics
PURPOSE: Manual chart review (MR) of electronic health records (EHRs) is time-consuming, error-prone, and limits the reproducibility and scalability of real-world data (RWD) research. Automation and standardization using natural language processing (NLP) could improve efficiency and scalability. CTcue is an NLP-based software platform designed to extract structured and unstructured data from EHRs. This study evaluated the accuracy and efficiency of CTcue versus MR in patients with early-stage resectable non–small cell lung cancer (NSCLC). METHODS: Included were all patients with stage I to III NSCLC who underwent lung resections between January 2018 and December 2021 at the Leiden University Medical Center, the Netherlands. Demographics, tumor characteristics, treatment, and outcomes were collected. CTcue performance was compared with MR using weighted F1-scores, accuracy, precision, and recall for categorical variables and Bland-Altman analysis for continuous variables. RESULTS: Eighty-five patients (70.2% of patients from the manual cohort) were identified by both methods and included in the comparison. CTcue achieved weighted F1-scores >0.85 for seven of 15 categorical variables, including sex, tumor location, and deceased status, although some scores were based on low number of observations in both cohorts. Lower performance was observed for variables with varying terminology in documentation, such as Eastern Cooperative Oncology Group status and pathological N-stage. Continuous variables showed negligible mean differences, indicating good agreement. Survival outcomes were identical in both data sets. CONCLUSION: CTcue performance for patient selection was lower than anticipated. However, it enables accurate, efficient extraction of structured and unstructured EHR data in early-stage NSCLC. Manual validation remains necessary for variables with varying terminology. Further development of artificial intelligence-based tools—particularly for free-text data extraction—will be crucial to enhance the accuracy and scalability of future RWD research.