{ "abstract": "Background: Slow gait, weak handgrip strength, and impaired balance are common functional deficits in aging populations that predict adverse health outcomes. Accurate, scalable prediction tools are needed for community-based screening in low-resource settings. Objectives: To benchmark nine machine learning (ML) classifiers for predicting the presence of ≥1 functional deficit using cardiometabolic and anthropometric predictors; to assess calibration, generalization, and clinical utility; to quantify the incremental value of these predictors over age and sex; and to characterize the stability of SHAP-based feature importance. Methods: We analyzed cross-sectional data from the Mexican Health and Aging Study 2012 (MHAS 2012) biomarker sub-study (N = 1961; mean age 61.9 ± 10.5 years; 59.8% women). The outcome was ≥1 of slow gait (<0.8 m/s), weak handgrip (EWGSOP2 sex-specific cut-points), or inability to sustain a 10-s one-leg stance (prevalence 78.7%). Twenty cardiometabolic and anthropometric predictors were used, excluding the functional measures used in outcome construction. Performance was estimated with nested, repeated stratified 10-fold cross-validation (5 × 10 outer folds; inner 5-fold hyperparameter tuning), with all preprocessing confined to training folds. Results: Logistic Regression (LR) achieved the highest discrimination (AUC-ROC 0.751, 95% CI 0.724–0.779), with good calibration (scaled Brier 0.125; calibration slope 0.96) and a small overfit gap (0.011); no classifier outperformed it (ET: AUC 0.745). An age–sex model alone reached AUC 0.734; all other predictors added ΔAUC = +0.018 (95% CI 0.004–0.031), almost entirely through anthropometry, whereas blood biomarkers and blood pressure added no measurable discrimination. SHAP identified age, sex, height, body weight, and BMI × Age as the most influential features; BMI ranked 12th of 20 (bootstrap 95% rank interval 8–20). Conclusions: Cardiometabolic and anthropometric predictors identify middle-aged and older Mexican people with ≥1 functional deficit with moderate accuracy (AUC ≈ 0.75), but most of the signal is carried by age, sex, and simple anthropometry. This reproducible, circularity- and leakage-free framework supports risk stratification rather than diagnosis, and requires external and temporal validation before clinical implementation.", "abstract_shown": true, "affiliations": [ "Department of Physical Activity Sciences, Faculty of Education Sciences, Universidad Católica del Maule, Talca 3480112, Chile", "Faculty of Education and Humanities, School of Sport Sciences, Universidad Andres Bello, Viña del Mar 2520000, Chile", "School of Medicine, Universidad Espíritu Santo, Samborondón 092301, Ecuador", "Escuela de Entrenador en Actividad Física y Deporte, Facultad de Ciencias Humanas, Universidad Bernardo O’Higgins, Santiago 8370993, Chile", "Escuela de Kinesiología, Facultad de Salud, Universidad Santo Tomás, Talca 3460000, Chile", "Vicerrectoría de Investigación e Innovación, Universidad Arturo Prat, Iquique 1100000, Chile", "Escuela de Fonoaudiología, Facultad de Ciencias de la Salud, Universidad Autónoma de Chile, Talca 3460000, Chile", "Laboratorio de Evaluación y Cuidado del Estado Nutricio, División de Ciencias de la Salud, Centro Universitario de Tonalá, Universidad de Guadalajara, Tonalá 45425, Jalisco, Mexico", "Red Iberoamericana de Investigadores en Antropometría Aplicada, 04120 Almería, Spain", "Marieb College of Health and Human Services, Florida Gulf Coast University, Fort Myers, FL 33965, USA", "Escuela de Ciencias de la Actividad Física, el Deporte y la Salud, Universidad de Santiago de Chile (USACH), Santiago 9170022, Chile", "Sports Coach Career, School of Education, Universidad Viña del Mar, Viña del Mar 2520000, Chile", "Escuela de Nutrición y Dietética, Facultad de Salud, Universidad Santo Tomás, Talca 3460000, Chile", "Department of Physical Activity Sciences, Universidad de Los Lagos, Osorno 5290000, Chile", "Department of Education, Faculty of Humanities, Universidad de La Serena, La Serena 1700000, Chile" ], "article_type": null, "arxiv": null, "author_total": 12, "authors": [ { "affs": [ 0 ], "name": "Jessica Mondaca Urrutia", "orcid": "0000-0002-4903-1882" }, { "affs": [ 1, 2 ], "name": "Rodrigo Yáñez-Sepúlveda", "orcid": "0000-0002-9311-6576" }, { "affs": [ 0, 3 ], "name": "Paz Pezoa-Fuentes", "orcid": "0000-0002-7063-5728" }, { "affs": [ 4, 5 ], "name": "Yeny Concha-Cisternas", "orcid": "0000-0001-7013-3894" }, { "affs": [ 4, 6 ], "name": "Eduardo Guzmán-Muñoz", "orcid": "0000-0001-7001-9004" }, { "affs": [ 7, 8 ], "name": "Carlos Abraham Herrera-Amante", "orcid": "0000-0002-3645-3621" }, { "affs": [ 9 ], "name": "Lawrence W. Judge", "orcid": "0000-0002-9941-5665" }, { "affs": [ 10 ], "name": "Claudio Farías-Valenzuela", "orcid": "0000-0002-4027-4415" }, { "affs": [ 0, 11 ], "name": "Pablo Valdés-Badilla", "orcid": "0000-0002-3948-8280" }, { "affs": [ 0, 12 ], "name": "Bastian Parada-Flores", "orcid": "0000-0002-0342-5237" }, { "affs": [ 13, 14 ], "name": "Jordan Hernandez-Martínez" }, { "affs": [ 0, 13 ], "name": "Exal Garcia-Carrillo", "orcid": "0000-0001-6190-938X" } ], "bibtex": "https://research.draconitic.com/paper/ctw94t3c3nezr.bib", "cited_by": 0, "doi": "10.3390/jcm15218618", "fulltext_url": null, "id": "ctw94t3c3nezr", "issns": [ "2077-0383" ], "landing_url": "https://www.mdpi.com/2077-0383/15/21/8618", "language": null, "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "article", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [], "openalex": null, "pdf_url": null, "pmcid": null, "pmid": null, "published": "2026-11-05", "publisher": "MDPI AG", "ris": "https://research.draconitic.com/paper/ctw94t3c3nezr.ris", "sources": [ { "first_seen": "2026-11-05T12:21:24Z", "native_id": "10.3390/jcm15218618", "source": "crossref", "url": "https://www.mdpi.com/2077-0383/15/21/8618" } ], "subjects": [ { "field": "medicine", "origin": "journal-openalex:F27", "subfield": "general" } ], "title": "Machine Learning-Based Prediction of Functional Deficit from Anthropometric and Cardiometabolic Biomarkers in Middle-Aged and Older People", "title_text": "Machine Learning-Based Prediction of Functional Deficit from Anthropometric and Cardiometabolic Biomarkers in Middle-Aged and Older People", "type": "peer-reviewed", "updated_at": "2026-11-07T00:21:23Z", "url": "https://research.draconitic.com/paper/ctw94t3c3nezr", "venue": "Journal of Clinical Medicine", "versions": [] }