The urinary-metabolite-based lung cancer index (uLCI): an interpretable machine-learning risk model for early-stage disease
Khan, M. A.; Mathe, E. A.; Pine, S. R.; Gonzalez, F. J.; Harris, C. C.; Wang, X. W.; Patel, D. P.
Show abstract
Background Five-year survival from lung cancer exceeds 60% at stage I-II but falls below 10% once metastasis occurs. Low-dose CT (LDCT) screening reduces mortality in heavy smokers but carries a false-positive rate of approximately 29% and is restricted to smoking-based eligibility, leaving most cases undetected. We aimed to develop and independently validate an interpretable machine-learning urinary metabolite risk index (uLCI) for non-invasive lung cancer detection. Methods Four urinary metabolites - creatine riboside (CR), N-acetylneuraminic acid (NANA), 27-nor-5-beta-cholestane-3-alpha,7-alpha,12-alpha,24,25-pentol (CP), and cortisol sulfate (CS) - and three clinical variables (age, race, smoking) were integrated by Lasso-regularised logistic regression into a uLCI score. The model was developed under 10-fold cross-validation in the NCI-Maryland (NCI-MD) cohort (n=845; 470 controls, 375 cases, stages I-IV) and applied without refitting to the independent Colorado Lung Cancer Cohort (n=488; 211 controls, 277 cases). Analyses were prespecified; reporting followed TRIPOD+AI. Findings uLCI achieved an area under the curve (AUC) of 0.906 (95% CI 0.887-0.926) in NCI-MD and 0.748 (0.701-0.793) in the independent Colorado cohort. Scores rose monotonically across stages in both cohorts (Spearman rho=0.69 and 0.45; both p<0.0001). Stage-specific discrimination was preserved from stage I to IV (NCI-MD 0.900-0.927; Colorado 0.722-0.843). Net reclassification improvement over clinical variables was 1.24 (1.14-1.36) and 0.74 (0.56-0.90). uLCI tertiles stratified post-resection survival in stage I-II disease (adjusted hazard ratio 2.03, 1.26-3.27). Interpretation uLCI is an independently validated, interpretable urinary risk index that detects lung cancer across all stages, with monotonic stage progression and post-resection prognostic value. Its false-positive rate compares favourably with published estimates for LDCT and cell-free-DNA assays, supporting prospective head-to-head evaluation as a non-invasive triage tool, including in screening-ineligible populations. Funding Intramural Research Program, Center for Cancer Research, National Cancer Institute, US National Institutes of Health.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Pan-cancer analysis demonstrates that integrating polygenic risk scores with modifiable risk factors improves risk prediction 93%
- Integration of clinical characteristics, lab tests and a deep learning CT scan analysis to predict severity of hospitalized COVID-19 patients 93%
- Integration of clinical, pathological, radiological, and transcriptomic data improves the prediction of first-line immunotherapy outcome in metastatic non-small cell lung cancer 92%
Similar papers in this journal
- The tumor burden of metastatic colorectal cancer patients at initial diagnosis, pre- versus post-Covid-19 lockdown 90%
- Missing data in the medical record for oncology patients: prevalence and association with outcomes 89%
- A comprehensive systematic review and meta-analysis of the global data involving 61,532 cancer patients with SARS-CoV-2 infection 89%
Similar papers in this journal
- Genomic Insights for Personalized Care: Motivating At-Risk Individuals Toward Evidence-Based Health Practices 93%
- Integrative deep learning analysis improves colon adenocarcinoma patient stratification at risk for mortality 92%
- Transformer-based deep learning model for the diagnosis of suspected lung cancer in primary care based on electronic health record data 92%
Similar papers in this journal
- Leveraging Longitudinal Patient-Reported Outcomes Trajectories to Predict Survival in Non-Small-Cell Lung Cancer 92%
- Cell-free urine- and plasma DNA mutational analysis predicts neoadjuvant chemotherapy response and outcome in patients with muscle invasive bladder cancer 92%
- RRAS and RRAS2 mutations are recurrent oncogenic drivers in lung cancer and are sensitive to the pan-RAS inhibitor RMC-6236 92%
Similar papers in this journal
- Asian Lung Cancer Absolute Risk Models for lung cancer mortality based on China Kadoorie Biobank 93%
- Stratifying Lung Adenocarcinoma Risk with Multi-ancestry Polygenic Risk Scores in East Asian Never-Smokers 92%
- Proteogenomic and observational evidence implicate ANGPTL4 as a potential therapeutic target for colorectal cancer prevention 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.