{
  "abstract": "Introduction: Machine-learning (ML) studies increasingly compare feature-importance rankings between small, unevenly sized cohorts and interpret the differences as evidence of culturally specific “risk architectures.” We show that such comparisons can be highly misleading without leakage-free evaluation, using a worked example from our own cross-sectional lifestyle and health data collected during June-August 2024 from two universities in India and Japan. Three problems were identified in our preliminary analysis: (1) an outcome (obesity, defined as BMI ≥ 25) that was tautologically predicted by including BMI itself as a model input; (2) model evaluation without a held-out test set; and (3) feature-importance comparisons that ignored sampling variability from an eightfold difference in cohort size.\n\nMethods: We addressed each problem using penalized logistic regression, Random Forest, and gradient-boosted trees with proper train/test splitting, held-out permutation importance, and bootstrap confidence intervals. We also ran a sensitivity analysis that repeatedly subsampled the Indian cohort down to the size of the Japanese cohort.\n\nResults: Removing body mass index (BMI) as a predictor collapsed obesity-model discrimination from perfect (AUC = 1.00) to chance level (AUC = 0.50-0.57), confirming that the BMI-obesity association was definitional rather than empirical. Held-out predictive performance for the remaining viable outcome, elevated self-rated stress, was modest at best (AUC 0.49-0.71). Critically, in the subsampling analysis, every feature-importance value observed in the actual Japanese data fell within the range produced by sample-size noise alone.\n\nDiscussion: We present this analysis as a transparent, reproducible case study of specific, checkable pitfalls: label leakage, missing train/test evaluation, unadjusted small-sample comparison, and mislabeled psychometric instruments. These should be routinely screened for before ML feature importance is interpreted as evidence of population-level or cultural differences in digital health research.",
  "abstract_shown": true,
  "affiliations": [
    "Faculty of Science & Technology, Sophia University , ,",
    "School of Engineering, St Aloysius (Deemed to be University) , ,",
    "Father Muller Medical College , ,"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Eiko Takaoka"
    },
    {
      "affs": [
        1
      ],
      "name": "S. Ruban"
    },
    {
      "affs": [
        1
      ],
      "name": "B. Mohammed Siraj"
    },
    {
      "affs": [
        1
      ],
      "name": "Varenya Vinay"
    },
    {
      "affs": [
        2
      ],
      "name": "Hilda Shanthini"
    },
    {
      "affs": [
        2
      ],
      "name": "Akshay Dias"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2t28mhfxp8w25.bib",
  "cited_by": 0,
  "doi": "10.3389/fdgth.2026.1791066",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13719548/?tool=EBI",
  "id": "2t28mhfxp8w25",
  "issns": [
    "2673-253X"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13719548",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "3605|Artificial Intelligence in Healthcare"
    ]
  ],
  "openalex": "W7222538825",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13719548/pdf/?tool=EBI",
  "pmcid": "PMC13719548",
  "pmid": "42964282",
  "published": "2026-10-16",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/2t28mhfxp8w25.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:21:36Z",
      "native_id": "PMC:PMC13719548",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13719548"
    },
    {
      "first_seen": "2026-11-02T12:23:29Z",
      "native_id": "PMC13719548",
      "source": "pmc",
      "url": "https://doi.org/10.3389/fdgth.2026.1791066"
    }
  ],
  "subjects": [],
  "title": "Do machine learning models really encode cross-cultural lifestyle-health differences? A leakage-free reanalysis of two university cohorts in India and Japan",
  "title_text": "Do machine learning models really encode cross-cultural lifestyle-health differences? A leakage-free reanalysis of two university cohorts in India and Japan",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:20:37Z",
  "url": "https://research.draconitic.com/paper/2t28mhfxp8w25",
  "venue": "Frontiers in digital health",
  "versions": []
}