We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

LabMedica

Download Mobile App
Recent News Expo Clinical Chem. Molecular Diagnostics Hematology Immunology Microbiology Pathology Technology Industry Focus

AI Identifies Advanced Lung Cancer Patients Who Respond to Immunotherapy

By LabMedica International staff writers
Posted on 10 Oct 2023

Lung cancer treatment planning is often complex due to the variations in evaluating immune biomarkers. In a new study, researchers utilized artificial intelligence (AI) and digital pathology techniques to improve the accuracy of such evaluations.

The study by scientists at the Yale School of Medicine (New Haven, CT, USA) focused on how AI-based digital assessment could fare against traditional manual methods in scoring the PD-L1 immune biomarker. The goal was to see if a novel immunotherapy treatment called atezolizumab could be beneficial for patients suffering from advanced non-small cell lung cancer (NSCLC). To undertake this research, they drew upon data from the IMpower 110 phase III trial, which examined the effectiveness of atezolizumab against chemotherapy for treating advanced NSCLC. Through both manual and AI-guided evaluations of tumor cells, the team discovered that the AI system was more efficient at identifying patients as PD-L1 positive than manual methods.


Image: AI more accurately identifies patients with advanced lung cancer who respond to immunotherapy (Photo courtesy of 123RF)
Image: AI more accurately identifies patients with advanced lung cancer who respond to immunotherapy (Photo courtesy of 123RF)

Moreover, the study found that both AI-based and traditional manual scoring techniques were equally competent at predicting patient results, including how long patients lived and how long it took before the cancer progressed. Additionally, the AI system aided in confirming that for patients with a particular subtype of NSCLC known as squamous histology, the existence of PD-L1+ lymphocytes was linked to better outcomes in terms of slowing down disease progression when treated with atezolizumab.

“Our study suggests that artificial intelligence has the ability to improve the identification of PD-L1 positive patients by providing a predictive accuracy that was better than manual scoring,” said Roy S. Herbst, lead study author and deputy director of Yale Cancer Center. “The research underscores the potential of digital pathology and AI tools in enhancing PD-L1 scoring accuracy for both clinical practice and clinical trials.”

“The insights gained with AI and digital scoring could make diagnosing and choosing the right treatment easier,” added Herbst. “Our data shows that this AI technology can help refine strategies for treating advanced non-small cell lung cancer.”

Related Links:
Yale School of Medicine 


Gold Member
Fully Automated Cell Density/Viability Analyzer
BioProfile FAST CDV
Gold Member
Troponin T QC
Troponin T Quality Control
New
hCG Urine Test
QuickVue hCG Urine Test
New
Myocardial Infarction Test
Savvycheck SensA Heart

Latest Pathology News

AI Tool Analyzes 30K Data Points Per Medical Imaging Pixel in Cancer Search

New Technique Predicts Tumor’s Responsiveness to Breast Cancer Treatment

AI Tool Combines Data from Medical Images with Text to Predict Cancer Prognoses