Academic Journal
Προβολή σε EDS

Development and validation of a machine learning model for colorectal cancer status classification using NHANES data: A cross-sectional study.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Development and validation of a machine learning model for colorectal cancer status classification using NHANES data: A cross-sectional study.
Συγγραφείς: Chen J; Department of Medical Imaging, Lianjiang County General Hospital, Fuzhou, China.
Πηγή: Medicine [Medicine (Baltimore)] 2026 Jun 05; Vol. 105 (23), pp. e49114.
Τύπος έκδοσης: Journal Article; Validation Study
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Lippincott Williams & Wilkins Country of Publication: United States NLM ID: 2985248R Publication Model: Print Cited Medium: Internet ISSN: 1536-5964 (Electronic) Linking ISSN: 00257974 NLM ISO Abbreviation: Medicine (Baltimore) Subsets: MEDLINE
Imprint Name(s): Original Publication: Hagerstown, Md : Lippincott Williams & Wilkins
Ιατρικοί όροι (MeSH): Colorectal Neoplasms*/epidemiology , Colorectal Neoplasms*/classification , Colorectal Neoplasms*/diagnosis , Boosting Machine Learning Algorithms*, United States/epidemiology ; Aged ; Female ; Humans ; Male ; Middle Aged ; Case-Control Studies ; Classification Algorithms ; Cross-Sectional Studies ; Logistic Models ; Nutrition Surveys ; Predictive Learning Models ; Random Forest ; Support Vector Machine
Περίληψη: Colorectal cancer (CRC) is a leading cause of cancer-related morbidity and mortality worldwide. Tools based on routinely collected variables may help identify prevalent CRC status and support clinical evaluation. Traditional approaches often rely on limited predictors and may not capture the multidimensional nature of CRC. Data were obtained from the National Health and Nutrition Examination Survey 1999-2018. Among 53,881 participants, 420 reported physician-diagnosed CRC (MCQ220). A 1:10 stratified case-control sample was constructed (420 cases, 4200 controls) and randomly split into training (70%) and internal validation (30%) sets. Missing data were imputed separately in the training and validation sets using a random forest-based method. SMOTE was applied only to the training set. Logistic regression, random forest, support vector machine, k-nearest neighbors, and extreme gradient boosting (XGBoost) were compared. Performance was primarily assessed by discrimination in the held-out validation set. For the final XGBoost model, exploratory post hoc probability calibration analyses were performed on validation-set predictions using raw probabilities, prior prevalence correction, and Platt scaling. Model interpretability was examined using Shapley Additive Explanations (SHAP), and a web-based CRC status classifier was developed. XGBoost showed the best discrimination in the validation cohort, with an area under the receiver operating characteristic curve of 0.787 (95% confidence interval 0.749-0.825). At the Youden-index cutoff, sensitivity was 77.0%, specificity 67.6%, PPV 19.2%, and NPV 96.7%. In exploratory probability-based analyses, decision curve analysis using Platt-scaled probabilities showed greater net benefit than treat-all and treat-none strategies across low-to-moderate threshold probabilities. post hoc calibration analyses fitted and assessed on the validation-set predictions showed improved apparent agreement after Platt scaling, with a Brier score of 0.191 and a Hosmer-Lemeshow P value of 0.086. SHAP identified key predictors, including alcohol use, hypertension, age, triglycerides, absolute lymphocyte count, blood lead, serum cotinine, and neutrophil-to-lymphocyte ratio. An interpretable machine learning framework integrating multidomain predictors enabled effective CRC status classification in a large population-based cohort. Discrimination was strong, whereas probability-based outputs after post hoc calibration should be considered exploratory pending independent confirmation. The model may support clinical evaluation and triage for individuals requiring further assessment.
(Copyright © 2026 the Author(s). Published by Wolters Kluwer Health, Inc.)
Competing Interests: The author has no funding and conflicts of interest to disclose.
References: Zhou J, Yang Q, Zhao S, et al. Evolving landscape of colorectal cancer: Global and regional burden, risk factor dynamics, and future scenarios (the Global Burden of Disease 1990-2050). Ageing Res Rev. 2025;104:102666.
Junhai Z, Yang M, Zongbiao T, et al. Global, regional, and national burden of very early-onset colorectal cancer and its risk factors from 1990 to 2019: a systematic analysis for the global burden of disease study 2019. Neoplasia. 2025;60:101114.
Sun Q, Bi D, Pang Y, Xie J. China's colorectal cancer burden and dietary risk factors: a temporal analysis (1990-2021). Front Nutr. 2025;12:1590117.
Sung H, Siegel RL, Laversanne M, et al. Colorectal cancer incidence trends in younger versus older adults: an analysis of population-based cancer registry data. Lancet Oncol. 2025;26:51–63.
Papier K, Bradbury KE, Balkwill A, et al. Diet-wide analyses for risk of colorectal cancer: prospective study of 12,251 incident cases among 542,778 women in the UK. Nat Commun. 2025;16:375.
Simancas-Racines D, Reytor-Gonzalez C, Frias-Toral E, Katsanos CS, Hidalgo R. Weighty matters: unraveling the impact of obesity on colorectal cancer and nutritional interventions. Semin Cancer Biol. 2025;114:29–40.
Hu Y, Kharazmi E, Liang Q, et al. Risk of colorectal cancer by family history of both colorectal carcinomas and colorectal polyps: a nationwide cohort study. Cancer Commun (Lond). 2025;45:1407–16.
Zink A, Obermeyer Z, Pierson E. Race adjustments in clinical algorithms can help correct for racial disparities in data quality. Proc Natl Acad Sci U S A. 2024;121:e2402267121.
Zhang M, Zhang Y, Zhao L, et al. Development and Multi-center validation of a machine learning model for advanced colorectal neoplasms screening. Comput Biol Med. 2025;190:110066.
Domagalski M, Olszanska J, Pietraszek-Gremplewicz K, Nowak D. The role of adipogenic niche resident cells in colorectal cancer progression in relation to obesity. Obes Rev. 2025;26:e13873.
Tian J, Zhang M, Zhang F, et al. Developing an optimal stratification model for colorectal cancer screening and reducing racial disparities in multi-center population-based studies. Genome Med. 2024;16:81.
Kamrani A, Nasiri H, Hassanzadeh A, et al. New immunotherapy approaches for colorectal cancer: focusing on CAR-T cell, BiTE, and oncolytic viruses. Cell Commun Signal. 2024;22:56.
Zhao D, Zhu M. Invisible foes: how air pollution and lifestyle conspire in the rise of colorectal cancer. QJM. 2025;118:501–13.
Huang YQ, Chen XB, Cui YF, et al. Enhanced risk stratification for stage II colorectal cancer using deep learning-based CT classifier and pathological markers to optimize adjuvant therapy decision. Ann Oncol. 2025;36:1178–89.
Tattan-Birch H, Brown J, Jackson SE, Jarvis MJ, Shahab L. Secondhand nicotine absorption from E-cigarette vapor vs tobacco smoke in children. JAMA Netw Open. 2024;7:e2421246.
Bhargava V, Lee JS, Smith TA, Chakrovorty S. A measure of nutrition security using the National Health and Nutrition Examination Survey Dataset. JAMA Netw Open. 2025;8:e2462130.
Tozduman B, Ergor G. The fraction of cancer attributable to modifiable risk factors in Turkey in 2018. Int J Cancer. 2025;156:2140–7.
Bian Z, Zhang R, Yuan S, et al. Healthy lifestyle and cancer survival: a multinational cohort study. Int J Cancer. 2024;154:1709–18.
Raychaudhuri S, McLaughlin E, Pennell ML, et al. The relationship between cardiometabolic abnormalities and mortality in the Women's Health Initiative: a comparison of associations among women with cancer to women without cancer. Cancer. 2025;131:e35804.
Yang Y, Liang Y, Sadeghi F, et al. Risk of head and neck cancer in relation to blood inflammatory biomarkers in the Swedish AMORIS cohort. Front Immunol. 2023;14:1265406.
Zhou M, Gu Q, Zhou M, et al. Extensive study on the associations of 12 composite inflammatory indices with colorectal cancer risk and mortality: a cross-sectional analysis of NHANES 2001-2020. Int J Surg. 2025;111:7559–75.
Li N, Luo C, Chen Y, et al. Identification and validation of blood leukocyte DNA methylation biomarkers for early detection of colorectal neoplasm [published online ahead of print June 6, 2025]. Chin Med J (Engl). doi:10.1097/CM9.0000000000003681. (PMID: 10.1097/CM9.0000000000003681)
Chen H, Wang Z, Sun C, et al. MALMPS: a machine learning-based metabolic gene prognostic signature for stratifying clinical outcomes and molecular heterogeneity in stage II/III colorectal cancer. Adv Sci (Weinh). 2025;12:e01333.
Mohamedahmed AY, Zaman S, Agrof M, Adam MA, Husain N, Yassin NA. Systematic review and meta-analysis of the role of machine learning in predicting postoperative complications following colorectal surgery: how far has machine learning come? Int J Surg. 2025;111:8550–62.
Xie H, Ruan G, Wei L, et al. Comprehensive comparative analysis of prognostic value of serum systemic inflammation biomarkers for colorectal cancer: results from a large multicenter collaboration. Front Immunol. 2022;13:1092498.
Deng Y, Yang M, Peng P, et al. Plasma metabolites, metabolic risk score and colorectal cancer risk: a prospective cohort study. Eur J Epidemiol. 2025;40:1455–68.
Farhoudian A, Heidari A, Shahhosseini R. A new era in colorectal cancer: artificial intelligence at the forefront. Comput Biol Med. 2025;196(Pt C):110926.
Yuan F, Jia G, Wen W, et al. Blood metabolic biomarkers and colorectal cancer risk: results from large prospective cohort and Mendelian randomisation analyses. Br J Cancer. 2025;133:94–103.
Ali NF, Elfadel IM, Atef M. Multi-datasets transfer multitask learning for simultaneous blood glucose and blood pressure monitoring using common PPG features. Comput Biol Med. 2025;195:110434.
Xiao T, Zhao W, Sun Z, et al. Interpretable machine learning models for predicting lateral pelvic lymph node metastasis in rectal cancer: a chinese multicenter retrospective study. JCO Precis Oncol. 2025;9:e2500192.
Tempel F, Ihlen EAF, Adde L, Strümke I. Explaining human activity recognition with SHAP: validating insights with perturbation and quantitative measures. Comput Biol Med. 2025;188:109838.
Lyu H, Wang S, Guo G, et al. A machine learning-derived immune-related prognostic model identifies PLXNA3 as a functional risk gene in colorectal cancer. Front Immunol. 2025;16:1653794.
Oncu E, Ciftci F. Multimodal AI framework for lung cancer diagnosis: integrating CNN and ANN models for imaging and clinical data analysis. Comput Biol Med. 2025;193:110488.
Jin S, Lu Y, Zuo Y, et al. Akkermansia muciniphila ameliorates chronic stress-induced colorectal tumor growth by releasing outer membrane vesicles. Gut Microbes. 2025;17:2555618.
Eckardt JN, Hahn W, Ries RE, et al. Age-stratified machine learning identifies divergent prognostic significance of molecular alterations in AML. Hemasphere. 2025;9:e70132.
Zhang Y, Zhang X, Zhong X, et al. Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III-IV d-MMR/MSI-H colorectal cancer. J ImmunoTher Cancer. 2025;13:e011569.
Zhou J, Foroughi Pour A, Deirawan H, et al. Integrative deep learning analysis improves colon adenocarcinoma patient stratification at risk for mortality. EBioMedicine. 2023;94:104726.
Pan Y, Yuan Y, Yang J, et al. U-shaped relationship between frailty and non-HDL-cholesterol in the elderly: a cross-sectional study. Front Nutr. 2025;12:1596432.
Xie X, Li X, Li H, Gao Y, Zhao F, Jia C. Diagnostic efficacy of remnant cholesterol inflammatory index in diabetic kidney disease: machine learning approaches. Front Nutr. 2025;12:1642358.
Zou J, Hua Y, Cheng Y, Zhang L, Zhang H, Shen F. Comprehensive evaluation framework for compost maturity with biochar amendment. Bioresour Technol. 2025;436:132970.
Deshmukh H, Wilmot EG, Ssemmondo E, et al. Exploring the interaction between ethnicity, deprivation and the use of CGM on diabetes outcomes-a study from the Association of British Clinical Diabetologists. Diabetes Obes Metab. 2026;28:391–400.
Jeffrey AW, Majumdar A, Jeffrey G, et al. The portal hypertension decompensation score: a validated predictive model of liver decompensation related to portal hypertension [published online ahead of print August 22, 2025]. Am J Gastroenterol. doi: 10.14309/ajg.0000000000003744. (PMID: 10.14309/ajg.0000000000003744)
Stromdahl M, Hagman K, Hedman K, Westman A, Hedenstierna M, Ursing J. Time to staphylococcus aureus blood culture positivity as a risk marker of infective endocarditis: a retrospective cohort study. Clin Infect Dis. 2025;80:727–34.
Burstein B, Waterfield T, Umana E, Xie J, Kuppermann N. Prediction of bacteremia and bacterial meningitis among febrile infants aged 28 days or younger. JAMA. 2026;335:425–33.
Chen WK, Liu ZB, Lin TT, et al. Optimizing Y-chromosome microdeletion screening in Chinese male infertility patients: a large-scale multi-centre study on incidence. Hum Reprod. 2025;40:1036–44.
Welsh P, Kimenai DM, Woodward M. Updating the Scottish national cardiovascular risk score: ASSIGN version 2.0. Heart. 2025;111:557–64.
Caussy C, Verges B, Leleu D, et al. Screening for metabolic dysfunction-associated steatotic liver disease-related advanced fibrosis in diabetology: a prospective multicenter study. Diabetes Care. 2025;48:877–86.
Ye Z, Lin Z, Xie E, et al. Prediction of percutaneous coronary intervention success in patients with moderate to severe coronary artery calcification using machine learning based on coronary angiography: prospective cohort study. J Med Internet Res. 2025;27:e70943.
Cui Y, Dong W, Li Y, Janitz AE, Pokala HR, Zhu R. Explainable transformer-based deep survival analysis in childhood acute lymphoblastic leukemia. Comput Biol Med. 2025;191:110118.
Cao Y, Chen T, Han K, Chung H, Huang Z, Ding H. SET-DGCN: An end-to-end electroencephalography-based fatigue detection method for young drivers. Accid Anal Prev. 2026;225:108311.
Mridha K, Kuri AC, Saha T, Shukla M. SmartHeart: a conceptual framework for explainable machine learning in cardiovascular risk prediction. Comput Biol Med. 2025;198(Pt B):111221.
Bin Wan Mohd Nor WMFS, Kwong SC, Fuzi AAM, et al. Linking microRNA to metabolic reprogramming and gut microbiota in the pathogenesis of colorectal cancer (Review). Int J Mol Med. 2025;55:46.
Krupka S, Aldehoff AS, Goerdeler C, et al. Metabolic and molecular characterization, following dietary exposure to DINCH, reveals new implications for its role as a metabolism-disrupting chemical. Environ Int. 2025;196:109306.
Shih PC, Chen HP, Hsu CC, et al. Long-term DEHP/MEHP exposure promotes colorectal cancer stemness associated with glycosylation alterations. Environ Pollut. 2023;327:121476.
Tian RF, Feng LL, Liang X, et al. Carnitine palmitoyltransferase 2 as a novel prognostic biomarker and immunoregulator in colorectal cancer. Int J Biol Macromol. 2025;309(Pt 3):142945.
India Aldana S, Demateis D, Valvi D, et al. Windows of susceptibility to air pollution during and surrounding pregnancy in relation to longitudinal maternal measures of adiposity and lipid profiles. Environ Res. 2025;274:121198.
Tong M, Liu H, Xu H, et al. Clinical significance of peripheral blood-derived inflammation markers combined with serum eotaxin-2 in human colorectal cancer. Biotechnol Genet Eng Rev. 2024;40:1774–90.
Petracci E, Passardi A, Biggeri A, et al. Baseline and longitudinal neutrophil-to-lymphocyte ratio as prognostic factor for metastatic colorectal cancer: a secondary analysis of the ITACa randomized trial. JCO Precis Oncol. 2024;8:e2300256.
Yang Y, Jiang Q, Zhu Z, et al. Targeting the CCL28-STAT3-PLAC8 axis to suppress metastasis and remodel tumor microenvironment in colorectal cancer. Front Immunol. 2025;16:1610540.
Tian Q, Yan Z, Cheng J, et al. The role of neutrophil-related indicators in aneurysmal subarachnoid hemorrhage. Neurobiol Dis. 2025;215:107062.
Cheung JCT, Ng LW, Zhu Z, et al. A citrate synthase splice variant rewires the TCA cycle to promote colorectal cancer progression. Cancer Res. 2025;85:4450–68.
Palermo BJ, Wilkinson KS, Plante TB, et al. Interleukin-6, diabetes, and metabolic syndrome in a biracial cohort: the reasons for geographic and racial differences in stroke cohort. Diabetes Care. 2024;47:491–500.
Huang M, Zhang Y, Ni M, et al. Shen-Bai-Jie-Du decoction suppresses the progression of colorectal adenoma to carcinoma through regulating gut microbiota and short-chain fatty acids. Chin Med. 2024;19:149.
Chen Z, Zhou X, Zhou X, et al. Phosphomevalonate kinase controls β-catenin signaling via the metabolite 5-diphosphomevalonate. Adv Sci (Weinh). 2023;10:e2204909.
Wang W, Li H, Gao L, et al. Cross-ancestry meta-analysis identifies a GSTP1 variant in the polycyclic aromatic hydrocarbons metabolism-related pathway contributing to colorectal cancer susceptibility. Arch Toxicol. 2026;100:725–35.
Lehtovirta M, Pahkala K, Rovio SP, et al. Association of tobacco smoke exposure with metabolic profile from childhood to early adulthood: the Special Turku Coronary Risk Factor Intervention Project. Eur J Prev Cardiol. 2024;31:103–15.
Li N, Wen L, Wang F, et al. Mechanism of mitigating effect of wheat germ peptides on lead-induced oxidative damage in PC12 cells. Ecotoxicol Environ Saf. 2022;246:114190.
Pizent A, Andelkovic M, Tariba Lovakovic B, et al. Environmental exposure to metals, parameters of oxidative stress in blood and prostate cancer: results from two cohorts. Antioxidants (Basel). 2022;11:2044.
Wang T, Meng Y, Tu Y, et al. Associations between DNA methylation and genotoxicity among lead-exposed workers in China. Environ Pollut. 2023;316(Pt 1):120528.
Escobar Moreno JD, Fajardo Castiblanco JL, Riano Rodriguez LC, et al. miRNAs involvement in modulating signalling pathways involved in Ros-mediated oxidative stress in melanoma. Antioxidants (Basel). 2024;13:1326.
Li P, Zhu J, Wang S, et al. Decoding disease-specific ageing mechanisms through pathway-level epigenetic clock: insights from multi-cohort validation. EBioMedicine. 2025;118:105829.
Fei X, Du X, Wang J, et al. Precise diagnosis and risk stratification of prostate cancer by comprehensive serum metabolic fingerprints: a prediction model study. Int J Surg. 2024;110:1450–62.
Viceconti M, Lanubile F, Carbonaro A, et al. Position paper: extending credibility assessment of in silico medicine predictors to machine learning predictors. IEEE J Biomed Health Inform. 2025;29:5284–90.
Sun G, Fuller H, Fenton H, et al. The effect of aspirin and eicosapentaenoic acid on urinary biomarkers of prostaglandin E2 synthesis and platelet activation in participants of the seAFOod polyp prevention trial. Int J Cancer. 2024;154:873–85.
Chen C, Cai Y, Hu W, et al. Single-cell eQTL mapping reveals cell subtype-specific genetic control and mechanism in malignant transformation of colorectal cancer. Cancer Discov. 2025;15:1649–75.
Zhang Y, Karahalios A, Win AK, et al. A prediction model for metachronous colorectal cancer: development and validation. J Natl Cancer Inst. 2025;117:2082–8.
Cui Y, Shi X, Wang Q, et al. Artificial intelligence-based prediction model for surgical site infection in metastatic spinal disease: a multicenter development and validation study. Int J Surg. 2025;111:6867–84.
Lundstrom S, Agger E, Lydrup ML, Jörgren F, Buchwald P. Tumour deposit count is an independent prognostic factor in colorectal cancer-a population-based cohort study. Br J Surg. 2024;112:znae309.
van Amsterdam WAC, van Geloven N, Krijthe JH, Ranganath R, Cinà G. When accurate prediction models yield harmful self-fulfilling prophecies. Patterns (N Y). 2025;6:101229.
Mosquera Orgueira A, Gonzalez Perez MS, D’Agostino M, et al. Machine learning risk stratification strategy for multiple myeloma: insights from the EMN-HARMONY alliance platform. Hemasphere. 2025;9:e70228.
Hong Y, Chen X, Wang L, Zhang F, Zeng ZY, Xie W. Machine learning prediction of metabolic dysfunction-associated fatty liver disease risk in American adults using body composition: explainable analysis based on SHapley Additive exPlanations. Front Nutr. 2025;12:1616229.
Wang AX, Le VT, Trung HN, Nguyen BP. Addressing imbalance in health data: synthetic minority oversampling using deep learning. Comput Biol Med. 2025;188:109830.
Zheng Z, Xu Y, Kang N, et al. Assessing the effect of perfluoroalkyl and polyfluoroalkyl substances on cardiovascular-kidney-metabolic syndrome: insights from an interpretable machine learning model. Sci Total Environ. 2025;993:180003.
Oka S, Takefuji Y. Letter to the Editor regarding "Prediction of PFAS bioaccumulation in different plant tissues with machine learning models based on molecular fingerprints" by Song et al . (2024), Sci. Total Environ. 950 175091. Sci Total Environ. 2025;984:179714.
Wolff RF, Moons KGM, Riley RD, et al.. PROBAST: a tool to assess the risk of bias and applicability of prediction model studies. Ann Intern Med. 2019;170:51–8.
Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378.
Contributed Indexing: Keywords: NHANES; SHAP; colorectal cancer; explainable artificial intelligence; machine learning; status classification
Entry Date(s): Date Created: 20260609 Date Completed: 20260613 Latest Revision: 20260726
Update Code: 20260726
PubMed Central ID: PMC13246055
DOI: 10.1097/MD.0000000000049114
PMID: 42260815
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1536-5964
DOI:10.1097/MD.0000000000049114