MétaCan
Menu
← Back to cohort
Record W4409632226 · doi:10.1158/1538-7445.am2025-5781

Abstract 5781: Comparing prognostic association of manual vs. artificial intelligence derived quantifications from baseline computed tomography scans in MYSTIC, a global phase 3 trial for treatment of metastatic non-small cell lung cancer

2025· article· en· W4409632226 on OpenAlexaff
Harish RaviPrakash, Qin Li, Kedar A. Patwardhan, J. Riskas, Shahid Haider, Oleksandra Samodorova, Vignesh Sivan, Felix Baldauf-Lenschen, Omar Khan

Bibliographic record

VenueCancer Research · 2025
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsMedicineComputed tomographyBaseline (sea)Internal medicineNuclear medicineOncologyRadiologyBiology

Abstract

fetched live from OpenAlex

Abstract Background: Sum of longest diameters (SLD) of target lesions per response evaluation criteria in solid tumors (RECIST) 1.1 is the standard measure of baseline (BL) disease burden, which plays an important prognostic role. Fully automated, artificial intelligence (AI) derived measures from BL computed tomography (CT) scans like imaging-based prognostication (IPRO) and lung volumetric tumor burden (VTB), generated by AI models trained on real-world imaging data, have shown promising association with overall survival (OS). Methods: BL CT scans acquired in MYSTIC (NCT02453282) were combined across trial arms and retrospectively analyzed. Patients with consent were included in this study. We compared the prognostic association of manually derived SLD with AI derived IPRO and lung VTB using concordance index (c-index), Kaplan-Meier methods, time-dependent area under the curve (TD-AUC), and standardized hazard ratios (HRs) from Cox proportional hazards models. Results: BL CT scans of 672 patients had available quantifications for comparative analysis. Median OS (mOS) was 12.2 months, 194 patients (29%) were female, 106 (16%) were non-smokers, 193 (29%) had squamous cell carcinoma and 201 (30%) had PD-L1 > 50%. SLD, IPRO, and lung VTB, yielded c-indexes of 0.56 (95% CI: 0.54-0.59), 0.61 (0.59-0.64), and 0.57 (0.54-0.60), respectively. Results are shown in Table 1. Conclusions: BL IPRO has greater association with OS than SLD, and VTB shows similar prognostic association as SLD. AI derived quantifications offer enhanced stratification and may provide an efficient way to analyze treatment effects.‬‬‬‬‬‬‬‬‬ Citation Format: Harish RaviPrakash, Qin Li, Kedar Patwardhan, John Riskas, Shahid Haider, Oleksandra Samodorova, Jay Hennessy, Vignesh Sivan, Felix Baldauf-Lenschen, Omar Khan Comparing prognostic association of manual vs. artificial intelligence derived quantifications from baseline computed tomography scans in MYSTIC, a global phase 3 trial for treatment of metastatic non-small cell lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 5781.

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)0.003
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.997
Threshold uncertainty score0.018

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

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 head0.094
GPT teacher head0.468
Teacher spread0.374 · 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.

Study designObservational
DomainMethods
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueCancer Research→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→