JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Association of artificial intelligence-based immunoscore with the efficacy of chemoimmunotherapy in patients with advanced non-squamous non-small cell lung cancer: a multicentre retrospective study

  • 0State Key Laboratory of Oncology in South China, Guangzhou, China.
Frontiers in Immunology +

|

November 21, 2024

|

November 21, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

An artificial intelligence-powered immunoscore accurately predicts survival outcomes for advanced non-squamous non-small cell lung cancer (NSCLC) patients receiving chemoimmunotherapy, identifying those who will benefit most.

Area Of Science

  • Oncology
  • Artificial Intelligence
  • Biomarker Development

Background

  • Chemoimmunotherapy efficacy varies in advanced non-squamous non-small cell lung cancer (NSCLC).
  • Predictive biomarkers are crucial for identifying patients likely to benefit from chemoimmunotherapy.

Purpose Of The Study

  • Develop an artificial intelligence (AI)-based immunoscore.
  • Evaluate the clinical utility of this patho-immunoscore in predicting outcomes for advanced non-squamous NSCLC.

Main Methods

  • An AI-powered immunoscore analyzer was developed using 1,333 whole-slide images from TCGA-LUAD.
  • Model validation was performed in the CPTAC-LUAD and ORIENT-11 study cohorts.
  • Clinical significance was assessed using the ORIENT-11 study cohort.

Main Results

  • The AI immunoscore analyzer demonstrated good accuracy across all cohorts (mean AUC: 0.741–0.783).
  • High patho-immunoscore significantly correlated with longer progression-free survival (13.8 vs 7.13 months) in patients receiving chemoimmunotherapy (p < 0.001).
  • No significant survival difference was observed in patients treated with chemotherapy alone.

Conclusions

  • AI-powered immunoscore on LUAD digital slides serves as a predictive biomarker for survival in advanced non-squamous NSCLC patients undergoing chemoimmunotherapy.
  • This AI methodology shows potential for application in other cancer types to advance cancer immunotherapy.

Keywords: