Machine-learning driven strategies for adapting immunotherapy in metastatic NSCLC

Maliazurina B. Saad, Qasem Al-Tashi, Lingzhi Hong, Vivek Verma, Wentao Li, Daniel Boiarsky, Shenduo Li, Milena Petranovic, Carol C. Wu, Brett W. Carter, Girish S. Shroff, Tina Cascone, Xiuning Le, Yasir Y. Elamin, Mehmet Altan, Simon Heeke, Ajay Sheshadri, Joe Y. Chang, Percy P. Lee, Zhongxing Liao, Don L. Gibbons, Ara A. Vaporciyan, J. Jack Lee, Ignacio I. Wistuba, Cara Haymaker, Seyedali Mirjalili, David Jaffray, Justin F. Gainor, Yanyan Lou, Alessandro Federico, Federica Pecci, Mark Awad, Biagio Ricciuti, John V. Heymach, Natalie I. Vokes, Jianjun Zhang and Jia Wu ()
Additional contact information
Maliazurina B. Saad: The University of Texas MD Anderson Cancer Center
Qasem Al-Tashi: The University of Texas MD Anderson Cancer Center
Lingzhi Hong: The University of Texas MD Anderson Cancer Center
Vivek Verma: The University of Texas MD Anderson Cancer Center
Wentao Li: The University of Texas MD Anderson Cancer Center
Daniel Boiarsky: Yale University School of Medicine
Shenduo Li: Mayo Clinic
Milena Petranovic: Massachusetts General Hospital
Carol C. Wu: The University of Texas MD Anderson Cancer Center
Brett W. Carter: The University of Texas MD Anderson Cancer Center
Girish S. Shroff: The University of Texas MD Anderson Cancer Center
Tina Cascone: MD Anderson Cancer Center
Xiuning Le: MD Anderson Cancer Center
Yasir Y. Elamin: MD Anderson Cancer Center
Mehmet Altan: MD Anderson Cancer Center
Simon Heeke: MD Anderson Cancer Center
Ajay Sheshadri: The University of Texas MD Anderson Cancer Center
Joe Y. Chang: The University of Texas MD Anderson Cancer Center
Percy P. Lee: City of Hope Orange County
Zhongxing Liao: The University of Texas MD Anderson Cancer Center
Don L. Gibbons: MD Anderson Cancer Center
Ara A. Vaporciyan: The University of Texas MD Anderson Cancer Center
J. Jack Lee: The University of Texas MD Anderson Cancer Center
Ignacio I. Wistuba: The University of Texas MD Anderson Cancer Center
Cara Haymaker: The University of Texas MD Anderson Cancer Center
Seyedali Mirjalili: Fortitude Valley
David Jaffray: The University of Texas MD Anderson Cancer Center
Justin F. Gainor: Massachusetts General Hospital
Yanyan Lou: Mayo Clinic
Alessandro Federico: Harvard Medical School
Federica Pecci: Harvard Medical School
Mark Awad: Harvard Medical School
Biagio Ricciuti: Harvard Medical School
John V. Heymach: MD Anderson Cancer Center
Natalie I. Vokes: MD Anderson Cancer Center
Jianjun Zhang: MD Anderson Cancer Center
Jia Wu: The University of Texas MD Anderson Cancer Center

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Immune checkpoint inhibitors (ICIs), either as monotherapy (ICI-Mono) or combined with chemotherapy (ICI-Chemo), improves survival in advanced non-small cell lung cancer (NSCLC). However, prospective guidance for choosing between these options remains limited, and single-feature biomarkers like PD-L1 prove inadequate. We develop a machine learning model using clinicogenomic data from four cohorts (MD Anderson n = 750; Mayo Clinic n = 80; Dana-Farber n = 1077; Stand Up To Cancer n = 393) to predict individual benefit from adding chemotherapy. Benefit scores are calculated using five distinct functions derived from 28 genomic and 6 clinical features. Our integrated model, A-STEP (Attention-based Scoring for Treatment Effect Prediction), estimates heterogeneous treatment effects and achieves the largest reduction in 3-month progression risk, improving weighted risk reduction by 13–23% over stand-alone models. A-STEP recommends treatment changes for over 50% of patients, most often favoring ICI-Chemo. In simulation on external cohort, patients treated in accordance with A-STEP recommendations show improved 2-year progression-free survival (HR = 0.60 for ICI-Mono treatment arm; HR = 0.58 for ICI-Chemo treatment arm). Predictive features include FBXW7, APC, and PD-L1. In this study, we demonstrate how machine learning can fill critical gaps in immunotherapy selection for NSCLC, by modeling treatment heterogeneity with real-world clinicogenomic data, driving precision medicine beyond conventional biomarker boundaries.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-61823-w Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-61823-w

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-61823-w

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().