Selection Instability and External Performance of Transcriptomic Models Beyond Age, Sex and Stage in Resected Lung Adenocarcinoma
- 1Department of Statistics and Data Science, Cornell University, Ithaca, NY 14853, USA
- 2Department of Pulmonary and Critical Care Medicine, The First Medical Center, Chinese PLA General Hospital, Beijing 100853, China
- 3Senior Department of Pulmonary and Critical Care Medicine, The Eighth Medical Center of Chinese PLA General Hospital, Beijing 100091, China
Abstract
Background/Objectives: We evaluated molecular selection stability and external prediction beyond age, sex and broad pathological stage in resected stage I–II lung adenocarcinoma. Methods: Models were developed in 228 patients from two sources and frozen before evaluation in four historical cohorts containing 778 patients. The primary comparison added pathway scores using elastic-net Cox regression. Secondary analyses examined a gene model, 200 development bootstrap resamples, alternative modeling specifications and locally updated baselines. Prediction error was measured by the integrated Brier score over 1–3 years (IBS); negative molecular-minus-clinical differences (ΔIBS) favored molecular models. Evaluation intervals used 2000 paired bootstrap resamples. Results: The pathway model retained no molecular terms. The final gene model retained 16 genes, whereas both source-held-out fits and 159/200 development resamples retained none. Penalties of 0.5, 0.15 and 0.05 were selected in 160, 38 and 2 resamples. Alternative specifications changed gene retention from 0 to 61 and pathway retention from 0 to 5. Frozen gene-model ΔIBS ranged from −0.0034 to 0.0055 across cohorts. Its equal cohort mean was 0.0016 (95% CI, −0.0012 to 0.0042), compared with −0.0008 (−0.0024 to 0.0007) after cross-fitted local baseline updating. The clinical model predicted a 3-year mortality of 19.6% in Japan and 22.6% in Moffitt, versus observed values of 9.1% and 28.6%. Conclusions: Molecular selection was unstable, and incremental performance depended on specification and population. The results characterize these learning procedures and their limited development sample; broader transcriptomic prognostic value and contemporary clinical utility remain unestablished.
Related
- An Oxidative Stress-Associated Seven-Gene Prognostic Signature in Lung Adenocarcinoma: Integrative Transcriptomic Analysis Across Public Cohorts
- Integrated Transcriptomic Analysis Reveals Distinct Molecular and Immune Microenvironment Features of Peutz–Jeghers Syndrome-Associated Lobular Endocervical Glandular Hyperplasia and Gastric-Type Endocervical Adenocarcinoma
- Cross-Platform External Validation of a Locked 12-Gene Prognostic Panel in Lung Adenocarcinoma Benchmarked Against Pathological Stage.
- Young Aggressive Prostate Tumors Exhibit Increased Genomic Instability and an Exploratory RNA–CNA-Concordant Transcriptomic Pattern
- Integrated transcriptomic and clinical prediction model for malignant pulmonary nodules : Model development, external dataset evaluation, and single-center expression validation
BibTeX
@article{lei2026selection,
title = {{Selection Instability and External Performance of Transcriptomic Models Beyond Age, Sex and Stage in Resected Lung Adenocarcinoma}},
author = {Zhihao Lei and Chenxi Zou and Wei Zhao},
journal = {Cancers},
year = {2026},
month = oct,
doi = {10.3390/cancers18203361},
url = {https://www.mdpi.com/2072-6694/18/20/3361},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Selection Instability and External Performance of Transcriptomic Models Beyond Age, Sex and Stage in Resected Lung Adenocarcinoma
AU - Zhihao Lei
AU - Chenxi Zou
AU - Wei Zhao
PY - 2026
DA - 2026/10/01
JO - Cancers
DO - 10.3390/cancers18203361
UR - https://www.mdpi.com/2072-6694/18/20/3361
AB - Background/Objectives: We evaluated molecular selection stability and external prediction beyond age, sex and broad pathological stage in resected stage I–II lung adenocarcinoma. Methods: Models were developed in 228 patients from two sources and frozen before evaluation in four historical cohorts containing 778 patients. The primary comparison added pathway scores using elastic-net Cox regression. Secondary analyses examined a gene model, 200 development bootstrap resamples, alternative modeling specifications and locally updated baselines. Prediction error was measured by the integrated Brier score over 1–3 years (IBS); negative molecular-minus-clinical differences (ΔIBS) favored molecular models. Evaluation intervals used 2000 paired bootstrap resamples. Results: The pathway model retained no molecular terms. The final gene model retained 16 genes, whereas both source-held-out fits and 159/200 development resamples retained none. Penalties of 0.5, 0.15 and 0.05 were selected in 160, 38 and 2 resamples. Alternative specifications changed gene retention from 0 to 61 and pathway retention from 0 to 5. Frozen gene-model ΔIBS ranged from −0.0034 to 0.0055 across cohorts. Its equal cohort mean was 0.0016 (95% CI, −0.0012 to 0.0042), compared with −0.0008 (−0.0024 to 0.0007) after cross-fitted local baseline updating. The clinical model predicted a 3-year mortality of 19.6% in Japan and 22.6% in Moffitt, versus observed values of 9.1% and 28.6%. Conclusions: Molecular selection was unstable, and incremental performance depended on specification and population. The results characterize these learning procedures and their limited development sample; broader transcriptomic prognostic value and contemporary clinical utility remain unestablished.
SN - 2072-6694
ER -