{
  "abstract": "EEG-based machine-learning studies of attention-deficit/hyperactivity disorder (ADHD) are vulnerable to optimistic performance estimates when feature selection or model choice is informed by data outside the training fold. We compared expert-reconstructed, large language model (LLM)-guided and full-space feature strategies under leakage-controlled subject-level validation in a frozen cohort of 77 children (45 ADHD, 32 controls) represented by 1,185 gamma-free EEG features. Four classifiers (SVM, GMM, random forest [RF] and XGBoost) were evaluated with nested leave-one-subject-out cross-validation (LOOCV), with all data-dependent operations restricted to outer-training subjects. Across 100 repetitions of stratified 10-fold cross-validation, RF/expert achieved mean accuracy 62.8% (SD 3.5%; empirical 95% interval 55.8%-69.5%), mean balanced accuracy 62.3% and mean AUC-ROC 0.618. The corresponding LOOCV point estimate was 71.4% accuracy and 71.0% balanced accuracy (AUC-ROC 0.673). GMM/expert achieved the highest AUC-ROC (0.699), indicating metric-dependent model ranking. The expert-reconstructed strategy achieved the highest accuracy and balanced accuracy for every classifier, whereas the LLM-guided strategy showed no consistent advantage over the full feature space. Pairwise classifier differences were not significant after Holm correction. A pre-specified 200 {micro}V artifact gate reduced RF/expert accuracy to approximately 55.8%, below the 58.4% no-information rate; this drop may reflect removal of artifact-related signal and/or reduced epoch counts leading to noisier feature estimates. These findings support cautious benchmarking and external validation rather than claims of algorithmic or LLM superiority.",
  "abstract_shown": true,
  "affiliations": [
    "Uskudar University, Istanbul, Turkey; Brain and Trauma Foundation Grisons, Landquart, Switzerland"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "F. Rohani"
    },
    {
      "name": "H. Alhatab"
    },
    {
      "name": "M. Jarrud"
    },
    {
      "name": "N. Salous"
    },
    {
      "name": "S. Kasimoglu"
    },
    {
      "name": "A. Mueller"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3yarnr64xp31z.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.06.26364825",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.06.26364825v1.full",
  "id": "3yarnr64xp31z",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.06.26364825v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "psychiatry and clinical psychology"
    ],
    [
      "openalex",
      "2738|Attention Deficit Hyperactivity Disorder"
    ]
  ],
  "openalex": "W7220969764",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.06.26364825v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3yarnr64xp31z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:22Z",
      "native_id": "10.64898/2026.10.06.26364825",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.06.26364825v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:psychiatry and clinical psychology",
      "subfield": "psychiatry"
    }
  ],
  "title": "Feature-Engineering Strategies for EEG-Based ADHD Classification in Children: A Controlled Benchmark of Expert, LLM-Guided and Full-Space Comparators",
  "title_text": "Feature-Engineering Strategies for EEG-Based ADHD Classification in Children: A Controlled Benchmark of Expert, LLM-Guided and Full-Space Comparators",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:22Z",
  "url": "https://research.draconitic.com/paper/3yarnr64xp31z",
  "venue": "medRxiv",
  "versions": []
}