LAMPAD:An Integrated ctDNA-Based Model for Predicting Potential Cure in Resected NSCLC Patients.
2/5 보강
OpenAlex 토픽 ·
Lung Cancer Treatments and Mutations
Lung Cancer Research Studies
Cancer Genomics and Diagnostics
ℹ️ 이 논문은 무료 전문이 아직 없습니다. 코퍼스 전체의 43.6%는 무료 가능 (통계 →) · 🏥 기관 EZproxy로 시도
[INTRODUCTION] Evaluation of molecular residual disease (MRD) status in non-small cell lung cancer (NSCLC) patients after surgery primarily relies on circulating tumor DNA (ctDNA) analysis.
- p-value p<0.001
- 95% CI 0.06-0.21
- HR 0.11
APA
Jia-Tao Zhang, Ke‐Zhong Chen, et al. (2026). LAMPAD:An Integrated ctDNA-Based Model for Predicting Potential Cure in Resected NSCLC Patients.. Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer, 103729. https://doi.org/10.1016/j.jtho.2026.103729
MLA
Jia-Tao Zhang, et al.. "LAMPAD:An Integrated ctDNA-Based Model for Predicting Potential Cure in Resected NSCLC Patients.." Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer, 2026, pp. 103729.
PMID
42002075 ↗
Abstract 한글 요약
[INTRODUCTION] Evaluation of molecular residual disease (MRD) status in non-small cell lung cancer (NSCLC) patients after surgery primarily relies on circulating tumor DNA (ctDNA) analysis. However, given the narrow postoperative window (4-6 weeks) for adjuvant therapy, the approximately 70% false-negative rate of single-timepoint ctDNA landmark detection severely limits its utility.
[METHODS] Here, we introduce LAMPAD, an XGBoost-Cox model that incorporates an additional preoperative timepoint alongside the standard postoperative landmark. By leveraging ctDNA quantification from both timepoints, it refines prognostic stratification among patients with landmark undetectable MRD, specifically identifying those who are truly disease-free.
[RESULTS] The LAMPAD model, incorporating the top five features ranked by shapley additive explanations analysis-baseline ctDNA level, TNM stage, landmark cell-free DNA (cfDNA) concentration, baseline cfDNA concentration, and baseline ctDNA status-was trained on 163 stage I-III NSCLC patients with landmark undetectable MRD. The model effectively stratified patients into low-risk (2-year DFS: 97.8%) and high-risk (2-year DFS: 71.6%) groups (HR=0.11, 95% CI 0.06-0.21, p<0.001). LAMPAD demonstrated consistent performance across both fixed-panel and personalized ctDNA-MRD approaches in multiple validation NSCLC cohorts (pooled 2-year DFS: 94.3% vs 72.4% for low- vs high-risk groups; HR=0.18, 95% CI 0.13-0.25, p<0.001). Preoperative blood test significantly contributed to the LAMPAD model, with methylation analysis revealing elevated immune-derived and lung-derived cfDNA in high-risk patients, suggesting systemic immune involvement in risk stratification.
[CONCLUSIONS] Overall, the LAMPAD model outperforms single-timepoint postoperative ctDNA detection by effectively discriminating true negative patients, thereby offering a more reliable prognostic tool for identifying low-risk patients with potential for cure.
[METHODS] Here, we introduce LAMPAD, an XGBoost-Cox model that incorporates an additional preoperative timepoint alongside the standard postoperative landmark. By leveraging ctDNA quantification from both timepoints, it refines prognostic stratification among patients with landmark undetectable MRD, specifically identifying those who are truly disease-free.
[RESULTS] The LAMPAD model, incorporating the top five features ranked by shapley additive explanations analysis-baseline ctDNA level, TNM stage, landmark cell-free DNA (cfDNA) concentration, baseline cfDNA concentration, and baseline ctDNA status-was trained on 163 stage I-III NSCLC patients with landmark undetectable MRD. The model effectively stratified patients into low-risk (2-year DFS: 97.8%) and high-risk (2-year DFS: 71.6%) groups (HR=0.11, 95% CI 0.06-0.21, p<0.001). LAMPAD demonstrated consistent performance across both fixed-panel and personalized ctDNA-MRD approaches in multiple validation NSCLC cohorts (pooled 2-year DFS: 94.3% vs 72.4% for low- vs high-risk groups; HR=0.18, 95% CI 0.13-0.25, p<0.001). Preoperative blood test significantly contributed to the LAMPAD model, with methylation analysis revealing elevated immune-derived and lung-derived cfDNA in high-risk patients, suggesting systemic immune involvement in risk stratification.
[CONCLUSIONS] Overall, the LAMPAD model outperforms single-timepoint postoperative ctDNA detection by effectively discriminating true negative patients, thereby offering a more reliable prognostic tool for identifying low-risk patients with potential for cure.