January, 2025
January 2025
M T W T F S S
 12345
6789101112
13141516171819
20212223242526
2728293031  
Aakash Desai: Can machine learning outperform PD-L1 as a predictive biomarker for ICI therapy in advanced NSCLC?
Jan 10, 2025, 15:30

Aakash Desai: Can machine learning outperform PD-L1 as a predictive biomarker for ICI therapy in advanced NSCLC?

Aakash Desai, Assistant Professor at UAB O’Neal Comprehensive Cancer Center, shared on LinkedIn:

“Can machine learning outperform PD-L1 as a predictive biomarker for immune checkpoint inhibitor (ICI) therapy in advanced NSCLC?

A new study by Ravi B. Parikh and colleagues in American Society of Clinical Oncology (ASCO) journal JCO CCI leveraged real-world data from 38,048 patients with advanced NSCLC to train machine learning (ML) algorithms to predict 12-month progression-free survival (PFS) and overall survival (OS) for patients receiving first-line therapy, including ICI monotherapy.

Key Findings:

• ML algorithms achieved an AUC of 0.701 for 12-month PFS and 0.718 for 12-month OS.
• Patients classified as low-risk (LR) by the ML model had significantly better outcomes:
Lower 12-month disease progression: HR 0.47 (P < .001).
Lower 12-month mortality: HR 0.31 (P < .0001).

Key Conclusion: The ML algorithm outperformed PD-L1 alone in predicting response to ICI therapies, demonstrating its potential to guide more precise clinical decision-making in oncology.

As we move toward more personalized cancer care, ML offers a robust complement to existing biomarkers.”