Artificial intelligence holds promise for detecting lung cancer if research presented last month at the International Association for the Study of Lung Cancer (IASLC) 2024 World Conference on Lung Cancer is any indicator.1
Wenhua Liang, MD, from the China State Key Laboratory of Respiratory Disease and National Clinical Research Center for Respiratory Disease, the First Affiliated Hospital of Guangzhou Medical University, China, and colleagues trained a tool called DeepGEM to scan routinely acquired histology slides and evaluate them for gene mutations. The initial cohort included an internal data set of 1717 patients. Then the program was subsequently tested on an external data set from 15 additional centers with 1719 patients and a public data set of 535 patients. To assess generalizability, the model was also tested on a lymph node metastases data set consisting of 331 biopsies.
Liang and colleagues noted that “DeepGEM demonstrated performance with a median area under the curve (AUC) of 0.938 for excisional biopsies and 0.891 for aspiration biopsies in the internal data set. On the multicenter external data set, the model achieved median AUCs of 0.859 for excisional biopsies and 0.826 for aspiration biopsies.” The researchers added that DeepGEM’s ability to predict mutations from primary biopsies extended to lymph node metastases, indicating a potential for prognostic prediction of targeted therapies.
“Compared to previous studies, DeepGEM achieved robust and superior predictive performance across various genes validating on the largest multicenter data sets to date. The rapid prediction capabilities of DeepGEM allow for quicker decision-making in treatment, enabling patients with severe symptoms to receive targeted therapies sooner. Furthermore, it presents opportunities for multigene mutation detection and precision treatment in economically underdeveloped areas where genomic testing is unaffordable. This innovative approach has the potential to transform the clinical management of lung cancer patients, making advanced genomic insights more accessible and actionable,” Liang said in a press release about the findings.2
Return to Top
Data presented at the International Association for the Study of Lung Cancer (IASLC) 2024 World Conference on Lung Cancer add another piece to the puzzle of people who have been diagnosed with lung cancer but have never smoked.
Researchers at British Columbia Cancer Research Institute, Vancouver, Canada, presented data from 255 newly diagnosed patients with lung cancer and known EGFR mutation status who never smoked. They included geocoded information on their residential history from birth to date of diagnosis that included data on high-resolution concentration estimates of PM2.5 exposure using ground measurements, satellite data, chemical transport models, corresponding to the time the individual lived at each address. The team obtained annual exposure data going back to 1996, when accurate air pollution information became available globally.
Significant associations were observed between EGFR mutation and cancer stage among women (P=.197 in men, P<.001 in women). Patients diagnosed with stage IV lung cancer displayed higher proportions of EGFR mutations compared to those without.
Also of note, the team identified differences in the cumulative 3-year PM2.5 exposure before diagnosis in women who never smoked with EGFR mutations compared to those without. This trend persisted when examining cumulative 5-year exposure (33.7 vs 29.5 μg/m3, P=.024) before diagnosis, with higher exposure observed in the EGFR mutation–positive group. These associations did not occur in the men who never smoked, the team noted. Moreover, long-term exposure, such as 10-, 15-, and 20-year cumulative exposure to PM2.5, was not associated with EGFR mutation status in either men or women.
The International Agency for Research on Cancer categorized outdoor air pollution and its key component, PM2.5, as group 1 carcinogens in 2013, indicating that they cause lung cancer.
“The timing and duration of PM2.5 exposure that are most relevant for the development of lung cancer and lung cancer risk have not been well characterized,” said Yixian Chen, PhD, a researcher at British Columbia Cancer Research Institute, Vancouver, Canada, in a press release about the findings.1 “These findings suggest a potential impact of recent exposure to PM2.5 on lung cancer in people who never smoked, particularly among women, with significant differences in stage IV diagnoses among EGFR-positive patients.
The research team noted that further studies are needed to confirm if PM2.5 measurement over 3 to 5 years is adequate for lung cancer risk assessment.
Ivonescimab has demonstrated a “statistically significant and clinically meaningful improvement” in progression-free survival over pembrolizumab (Keytruda) for patients with first-line non–small cell lung cancer (NSCLC), according to data presented at the IASLC World Conference on Lung Cancer in San Diego, held September 7-10, 2024.1
The data, from the HARMONi-2 (AK112-303) clinical trial, could mean a new first-line treatment option for these patients, the researchers, from Shanghai Pulmonary Hospital, Tongji University School of Medicine, in Shanghai, China, and others concluded in their study abstract.
Caicun Zhou, PhD, MD, of Shanghai Pulmonary, presented the data at the meeting, noting that 398 patients who had untreated locally advanced or metastatic NSCLC were randomly assigned in a 1:1 ratio, with 198 in the ivonescimab arm, to receive either 20 mg/kg of ivonescimab or 200 mg of pembrolizumab every 3 weeks.
The median progression-free survival was 11.14 months with ivonescimab and 5.85 months with pembrolizumab (HR, 0.51; 95% CI, 0.38-0.69; P<.0001) and was consistent across subgroups of patients, including those with higher PD-L1 tumor scores, with squamous and nonsquamous NSCLC, and with brain metastases.
“This is a historic moment for ivonescimab, Team Summit, our partners at Akeso, and most importantly, we believe this is the beginning of a paradigm change for treatment options for patients living with cancer,” Robert W. Duggan, chairman and chief executive officer of Summit, said in May.
The PD-L1 inhibitor durvalumab showed an overall survival benefit in patients with unresectable stage III non–small cell lung cancer (NSCLC) in the phase 3 PACIFIC trial.
Keep up to date with the latest news from us via social networks:
To sign up for our print publication or e-newsletter, please enter your contact information below.
