{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T00:08:51Z","timestamp":1792282131600,"version":"4.4.0"},"posted":{"date-parts":[[2026,6,29]]},"group-title":"Oncology","reference-count":29,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"name":"National Cancer Institute (NCI), National Institutes of Health (NIH) \u2013 Intramural Research Program, Center for Cancer Research","award":["grant ZIA BC 011492"],"award-info":[{"award-number":["grant ZIA BC 011492"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,18]]},"abstract":"<jats:title>Summary<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Five-year survival from lung cancer exceeds 60% at stage I\u2013II 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.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>\n                    Four urinary metabolites\u2014creatine riboside (CR), N-acetylneuraminic acid (NANA), 27-nor-5\u03b2-cholestane-3\u03b1,7\u03b1,12\u03b1,24\n                    <jats:italic>R<\/jats:italic>\n                    ,25\n                    <jats:italic>S<\/jats:italic>\n                    -pentol (CP), and cortisol sulfate (CS)\u2014and 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\u2013IV) and applied without refitting to the independent Colorado Lung Cancer Cohort (n=488; 211 controls, 277 cases). Analyses were prespecified; reporting followed TRIPOD+AI.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>uLCI achieved an area under the curve (AUC) of 0\u00b7906 (95% CI 0\u00b7887\u20130\u00b7926) in NCI-MD and 0\u00b7748 (0\u00b7701\u20130\u00b7793) in the independent Colorado cohort. Scores rose monotonically across stages in both cohorts (Spearman \u03c1=0\u00b769 and 0\u00b745; both p&lt;0\u00b70001). Stage-specific discrimination was preserved from stage I to IV (NCI-MD 0\u00b7900\u20130\u00b7927; Colorado 0\u00b7722\u20130\u00b7843). Net reclassification improvement over clinical variables was 1\u00b724 (1\u00b714\u20131\u00b736) and 0\u00b774 (0\u00b756\u20130\u00b790). uLCI tertiles stratified post-resection survival in stage I\u2013II disease (adjusted hazard ratio 2\u00b703, 1\u00b726\u20133\u00b727).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Interpretation<\/jats:title>\n                  <jats:p>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.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Research in context<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Evidence before this study<\/jats:title>\n                    <jats:p>We searched PubMed, Embase, and Web of Science from Jan 1, 2000, to Jan 31, 2026, without language restriction, for biomarker-based diagnostic or risk models for lung cancer, using \u201clung cancer\u201d, \u201cearly detection\u201d, \u201cbiomarker\u201d, \u201curine\u201d, \u201cmetabolite\u201d, \u201cmachine learning\u201d, \u201cTRIPOD\u201d, and \u201cvalidation in an independent cohort\u201d. Five-year survival exceeds 60% at stage I\u2013II but falls below 10% after metastasis. Low-dose CT reduces mortality in heavy smokers but carries an approximately 29% false-positive rate and excludes never-smokers, who account for 10\u201325% of US lung cancers and up to 40% globally; blood-based cell-free DNA and methylation assays report rates near 27%. Most prior urinary-metabolite work, including our 2024 creatine-riboside and N-acetylneuraminic-acid report, used case\u2013control designs without a locked, integrated model, and\u2014even where two cohorts were analyzed\u2014lacked prespecified independent validation or TRIPOD+AI-compliant reporting; an interpretable urinary index integrating an expanded metabolite panel with clinical variables under these standards had not been described.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Added value of this study<\/jats:title>\n                    <jats:p>Across two cohorts (1333 individuals), we developed and independently validated uLCI, an interpretable Lasso-regularised logistic index combining four urinary metabolites (CR, NANA, CP, CS) with age, race, and smoking, reported to TRIPOD+AI standards. The prespecified locked model achieved an AUC of 0\u00b7906 (95% CI 0\u00b7887\u20130\u00b7926) in NCI-MD development and 0\u00b7748 (0\u00b7701\u20130\u00b7793) in the independent Colorado cohort without refitting, with discrimination preserved from stage I to IV (0\u00b7900\u20130\u00b7927; 0\u00b7722\u20130\u00b7843). uLCI rose monotonically with stage in both cohorts (Spearman \u03c1=0\u00b7693 and 0\u00b7449; both p&lt;0\u00b70001), improved reclassification over clinical variables (net reclassification improvement 1\u00b724 and 0\u00b774), and independently stratified post-resection survival in stage I\u2013II disease (adjusted hazard ratio 2\u00b703 in NCI-MD; 3\u00b781 in Colorado). On indirect benchmarking, the 17\u201319% false-positive rate was below published estimates for low-dose CT (\u223c29%) and DELFI (\u223c27%), and discrimination was preserved in never-smokers \u2014 whom low-dose CT excludes \u2014 and across racial subgroups in the diverse development cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implications of all the available evidence<\/jats:title>\n                    <jats:p>A locked, independently validated, non-invasive urinary index that is interpretable, accurate from stage I, stage-responsive, and prognostic after resection addresses a defined detection gap, with a plausible role as a low-cost triage test that raises pre-test probability before imaging and extends risk assessment to screening-ineligible never-smokers, complementary to low-dose CT. Prospective screening-cohort evaluation (planned in the NCI PLCO and Southern Community Cohort biobanks), head-to-head comparison with blood-based assays, recalibration to screening prevalence, and replication in diverse cohorts are the warranted next steps.<\/jats:p>\n                  <\/jats:sec>\n                <\/jats:sec>","DOI":"10.64898\/2026.06.26.26356700","type":"posted-content","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T01:45:19Z","timestamp":1782783919000},"source":"Crossref","is-referenced-by-count":1,"title":["The urinary-metabolite-based lung cancer index (uLCI): an interpretable machine-learning risk model for early-stage disease"],"prefix":"10.64898","author":[{"given":"Mohammed A","family":"Khan","sequence":"first","affiliation":[{"name":"Laboratory of Human Carcinogenesis, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharon R","family":"Pine","sequence":"additional","affiliation":[{"name":"Division of Medical Oncology, Department of Medicine, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank J","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"Cancer Innovation Laboratory, Center for Cancer Research, National Cancer Institute, Bethesda, Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin W","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory of Human Carcinogenesis, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Curtis C","family":"Harris","sequence":"additional","affiliation":[{"name":"Laboratory of Human Carcinogenesis, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daxesh P","family":"Patel","sequence":"additional","affiliation":[{"name":"Laboratory of Human Carcinogenesis, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026082108500673000_2026.06.26.26356700v2.1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"2026082108500673000_2026.06.26.26356700v2.2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1102873"},{"key":"2026082108500673000_2026.06.26.26356700v2.3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1911793"},{"key":"2026082108500673000_2026.06.26.26356700v2.4","doi-asserted-by":"crossref","first-page":"100179","DOI":"10.1016\/j.lanepe.2021.100179","article-title":"Lung cancer mortality reduction by LDCT screening: UKLS randomised trial results and international meta-analysis","volume":"10","year":"2021","journal-title":"Lancet Reg Health Eur"},{"issue":"3","key":"2026082108500673000_2026.06.26.26356700v2.5","doi-asserted-by":"crossref","first-page":"234","DOI":"10.21037\/tlcr.2018.05.12","article-title":"Lung cancer screening with low-dose CT: a world-wide view","volume":"7","year":"2018","journal-title":"Transl Lung Cancer Res"},{"key":"2026082108500673000_2026.06.26.26356700v2.6","doi-asserted-by":"publisher","DOI":"10.1258\/jms.2012.012010"},{"issue":"1","key":"2026082108500673000_2026.06.26.26356700v2.7","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.jtho.2021.07.031","article-title":"Screening for Lung Cancer in Individuals Who Never Smoked: An International Association for the Study of Lung Cancer Early Detection and Screening Committee Report","volume":"17","year":"2022","journal-title":"J Thorac Oncol"},{"issue":"25","key":"2026082108500673000_2026.06.26.26356700v2.8","doi-asserted-by":"crossref","first-page":"2893","DOI":"10.1200\/JCO.2017.72.4203","article-title":"Risk Stratification for Second Primary Lung Cancer","volume":"35","year":"2017","journal-title":"J Clin Oncol"},{"issue":"2","key":"2026082108500673000_2026.06.26.26356700v2.9","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/S2213-2600(23)00338-7","article-title":"Low-dose CT screening among never-smokers with or without a family history of lung cancer in Taiwan: a prospective cohort study","volume":"12","year":"2024","journal-title":"Lancet Resp Med"},{"key":"2026082108500673000_2026.06.26.26356700v2.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05874-3"},{"key":"2026082108500673000_2026.06.26.26356700v2.11","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1211776"},{"key":"2026082108500673000_2026.06.26.26356700v2.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24994-w"},{"key":"2026082108500673000_2026.06.26.26356700v2.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2021.05.806"},{"issue":"16","key":"2026082108500673000_2026.06.26.26356700v2.14","doi-asserted-by":"crossref","first-page":"3592","DOI":"10.1158\/1078-0432.CCR-24-0637","article-title":"Urinary Metabolite Diagnostic and Prognostic Liquid Biopsy Biomarkers of Lung Cancer in Nonsmokers and Tobacco Smokers","volume":"30","year":"2024","journal-title":"Clin Cancer Res"},{"key":"2026082108500673000_2026.06.26.26356700v2.15","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-14-0109"},{"key":"2026082108500673000_2026.06.26.26356700v2.16","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-15-1191"},{"key":"2026082108500673000_2026.06.26.26356700v2.17","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2026082108500673000_2026.06.26.26356700v2.18","doi-asserted-by":"crossref","first-page":"113596","DOI":"10.1016\/j.jpba.2020.113596","article-title":"Improved detection and precise relative quantification of the urinary cancer metabolite biomarkers - Creatine riboside, creatinine riboside, creatine and creatinine by UPLC-ESI-MS\/MS: Application to the NCI-Maryland cohort population controls and lung cancer cases","volume":"191","year":"2020","journal-title":"J Pharm Biomed Anal"},{"key":"2026082108500673000_2026.06.26.26356700v2.19","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2929"},{"key":"2026082108500673000_2026.06.26.26356700v2.20","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehu207"},{"key":"2026082108500673000_2026.06.26.26356700v2.21","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361"},{"key":"2026082108500673000_2026.06.26.26356700v2.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2021.06.063"},{"key":"2026082108500673000_2026.06.26.26356700v2.23","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.lungcan.2016.06.003","article-title":"Integration of multiple \u201cOMIC\u201d biomarkers: A precision medicine strategy for lung cancer","volume":"107","year":"2017","journal-title":"Lung Cancer"},{"key":"2026082108500673000_2026.06.26.26356700v2.24","doi-asserted-by":"crossref","unstructured":"Zhang L , Zheng J , Bux RA , et al. Clinical Validation of Plasma Metabolite Markers for Early Lung Cancer Detection. Int J Mol Sci 2025; 26(10).","DOI":"10.3390\/ijms26104519"},{"issue":"1","key":"2026082108500673000_2026.06.26.26356700v2.25","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso","volume":"58","year":"1996","journal-title":"J Roy Stat Soc B"},{"key":"2026082108500673000_2026.06.26.26356700v2.26","doi-asserted-by":"crossref","unstructured":"Grinsztajn L , Oyallon E , Varoquaux G . Why do tree-based models still outperform deep learning on tabular data? arXiv 2022; arXiv:2207.08815.","DOI":"10.52202\/068431-0037"},{"issue":"7","key":"2026082108500673000_2026.06.26.26356700v2.27","doi-asserted-by":"crossref","first-page":"e470","DOI":"10.1016\/S2589-7500(24)00087-6","article-title":"Proteomic prediction of diverse incident diseases: a machine learning-guided biomarker discovery study using data from a prospective cohort study","volume":"6","year":"2024","journal-title":"Lancet Digit Health"},{"key":"2026082108500673000_2026.06.26.26356700v2.28","doi-asserted-by":"publisher","DOI":"10.1056\/nejmms2004740"},{"key":"2026082108500673000_2026.06.26.26356700v2.29","doi-asserted-by":"publisher","DOI":"10.1038\/nrc2190"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.26.26356700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:50:19Z","timestamp":1787327419000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.06.26.26356700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":29,"URL":"https:\/\/doi.org\/10.64898\/2026.06.26.26356700","relation":{},"subject":[],"published":{"date-parts":[[2026,6,29]]},"subtype":"preprint"}}