Research unlocks insights into lung cancer evolution from electronic medical records

 A recently completed study at the University Hospital of Toulouse, France emphasized the benefits of a "domain-specific natural language processing (NLP) pipeline...in extracting clinically meaningful information from diverse clinical documents of patients with non-small cell lung cancer."  Following an analysis of 1,028 discharge summaries and external consultation letters from 120 non-small cell lung cancer patients undergoing oral targeted therapy, "the domain-adapted NLP solution achieved an F1 score of 79.7% for tumor evolution concept extraction and 62.0% for temporality alignment." 

To read more about this study, click here. 

Source mentioned: 

Vinot, C., et al. "Automated extraction of temporalized tumor evolution from oncology EMRs using natural language processing." ESMO Real World Data and Digital Oncology 11 (2026): 100660.

Worse survival among patients diagnosed with cancer during first 2 years of the COVID-19 pandemic

A recently published U.S. population-based cohort study found "significant reductions in 1-year cause-specific survival rates among patients diagnosed with both early-stage and late-stage cancer in 2020 and 2021."   Compared to cancer patients diagnosed between 2015-2019, patients with a diagnosis of esophageal cancer (early-stage, 3.67%-3.89%), colorectal cancer (0.78%-1.08%) and prostate cancer (late-stage, 0.64%-0.77%)), were noted to have the largest site-specific survival reductions during the first 2 years of the COVID-19 pandemic.  The authors of this cohort study thus propose that "swift action should be taken to increase cancer screening, rebuild healthcare capacity, and improve patient communication." 

Source mentioned:

Burus T, Damgacioglu H, Huang B, et al. Survival of Patients Diagnosed With Cancer During the COVID-19 Pandemic . JAMA Oncology; Published online 5 February 2026. doi:10.1001/jamaoncol.2025.6332

Trustworthy and explainable AI – a key to equitable oncology

Trustworthiness of artificial intelligence (AI) applications and validating data analysis in cancer care was recently discussed at the ESMO Women for Oncology Forum.  

Click here to read about an interview with Alessandra Pedrocchi, founder of the laboratory for oncology at the National Cancer Institute in Milan.  

RAS inhibition in pancreatic cancer

 The Experimental Oncology Group at the National Research Centre (CNIO) in Madrid has recently unveiled findings from genetically engineered mice afflicted with pancreatic ductal adenocarcinoma.  The mice "underwent rapid apoptotic cell death that resulted in complete tumour regressions and remained tumour-free for over 200 days post-treatment."  While results of these animal studies are promising towards determining therapeutic vulnerabilities of pancreatic cancer, Dr. Ben Westphalen, chair of the European Society of Medical Oncology (ESMO) Precision Oncology Task Force cautions that these results cannot yet be applied to patient care. More work is needed to determine side effects of the triple combination therapy in humans. 

Click here to learn more about this news story.