MétaCan
Menu
Back to cohort
Record W4378801059 · doi:10.1016/s2589-7500(23)00082-1

Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study

2023· article· en· W4378801059 on OpenAlexfundno aff
Maliazurina B. Saad, Lingzhi Hong, Muhammad Aminu, Natalie I. Vokes, Pingjun Chen, Morteza Salehjahromi, Kang Qin, Sheeba J. Sujit, Xuetao Lu, Elliana Young, Qasem Al-Tashi, Rizwan Qureshi, Carol C. Wu, Brett W. Carter, Steven H. Lin, Percy P. Lee, Saumil Gandhi, Joe Y. Chang, Ruijiang Li, Michael F. Gensheimer, Heather A. Wakelee, Joel W. Neal, Hyun‐Sung Lee, Chao Cheng, Vamsidhar Velcheti, Yanyan Lou, Milena Petranović, Waree Rinsurongkawong, Xiuning Le, Vadeerat Rinsurongkawong, Amy Spelman, Yasir Y. Elamin, Marcelo V. Negrão, Ferdinandos Skoulidis, Carl M. Gay, Tina Cascone, Mara B. Antonoff, Boris Sepesi, Jeff Lewis, Ignacio I. Wistuba, John D. Hazle, Caroline Chung, David A. Jaffray, Don L. Gibbons, Ara A. Vaporciyan, John V. Heymach, Jianjun Zhang, Jia Wu

Bibliographic record

VenueThe Lancet Digital Health · 2023
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsnot available
FundersNational Institute of Biomedical Imaging and BioengineeringNational Cancer InstituteNGM BiopharmaceuticalsNovartis Institutes for BioMedical ResearchUniversity of Texas MD Anderson Cancer CenterEMD SeronoAstraZenecaGenentechNIH Clinical CenterSun PharmaAmgenSTCubeDaiichi Sankyo EuropeInnovent BiologicsEuropean Society for Medical OncologyUniversité de MontréalClovis OncologyBayer HealthCareAstellas PharmaRexanna's FoundationSeagenMacroGenicsJounce TherapeuticsViewRayRibon TherapeuticsBeiGeneHelsinnMirati TherapeuticsAmerican College of Radiology Imaging NetworkSociety for Immunotherapy of CancerJazz PharmaceuticalsConquer Cancer FoundationNational Institutes of HealthNateraRefleXion MedicalRegeneron PharmaceuticalsMcGill UniversityMerck KGaAVarian Medical SystemsDamon Runyon Cancer Research FoundationECOG-ACRIN Cancer Research GroupEli Lilly and CompanyCalithera BiosciencesGilead SciencesExelixisSanofiArrowhead PharmaceuticalsFoundation MedicineGlaxoSmithKlineBristol-Myers SquibbModernaPfizer
KeywordsMedicineContext (archaeology)Immune checkpointLung cancerOncologyInternal medicineUnivariate analysisCancerRetrospective cohort studyMultivariate analysisImmunotherapyBiology

Abstract

fetched live from OpenAlex

BACKGROUND: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. INTERPRETATION: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. FUNDING: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.005
Threshold uncertainty score0.010

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.275
Teacher spread0.266 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations109
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueThe Lancet Digital HealthSame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207