{
  "abstract": "AD is a progressive and irreversible neurodegenerative disorder. Because the structural changes that accompany the earliest stages of the disease are subtle and easily overlooked, manual interpretation of MRI is time-consuming and prone to inter-observer disagreement. This study presents an end-to-end deep learning framework that fuses spatial and sequential reasoning to classify brain MRI into four clinically meaningful stages: Person with no dementia, Person with very mild dementia, Person with mild dementia, and Person with moderate dementia. An additive attention mechanism subsequently weights the most informative positions before a compact dense head produces the final decision. Class imbalance is addressed by capped oversampling of real minority slices combined with residual cost-sensitive weighting, applied to the training fold only; pixel-space SMOTE is deliberately avoided because interpolating between two unregistered MRI slices produces images without an anatomical referent. Exact-duplicate screening is applied prior to partitioning, and a quantitative near-duplicate audit is reported for the fixed folds. Trained on 6,400 grayscale MRI slices under a stratified 70/15/15 protocol, the proposed CNN-BiLSTM-Attention model attains a test accuracy of 95.94%, a balanced accuracy of 96.08%, an MCC of 0.9334, a Cohen's kappa of 0.9325 and a macro-averaged one-vs.-rest AUC of 0.9954, on a slice-level held-out test fold. Per-class analysis shows strong sensitivity and specificity for the three better-represented stages; the extremely rare Person with moderate dementia class (nine test images) shows a favorable point estimate but is too small to support a claim of robust detection on its own. Attention maps and Grad-CAM overlays localize the evidence the network uses, and an error-structure analysis shows that no misclassification spans more than two stages. Because the corpus carries no subject identifiers, patient-grouped partitioning is not possible and the reported accuracies should be interpreted as an upper bound attainable under a slice-level split; this constraint is quantified explicitly and motivates the external-validation study outlined in the manuscript. Overall, the results highlight the methodological value of coupling convolutional feature extraction with bidirectional sequence modeling and additive attention under a leakage-aware, imbalance-aware evaluation protocol for multi-stage AD staging.",
  "abstract_shown": true,
  "affiliations": [
    "School of Computer Science Engineering and Information Systems, Vellore Institute of Technology (VIT) , ,"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "T. Deenadayalan"
    },
    {
      "affs": [
        0
      ],
      "name": "S. P. Shantharajah"
    },
    {
      "affs": [
        0
      ],
      "name": "Swarna Priya Ramu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7r6rdc9mjj3pw.bib",
  "cited_by": 0,
  "doi": "10.3389/frai.2026.1948601",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13725815/?tool=EBI",
  "id": "7r6rdc9mjj3pw",
  "issns": [
    "2624-8212"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13725815",
  "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",
      "2738|Dementia and Cognitive Impairment Research"
    ]
  ],
  "openalex": "W7222555854",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13725815/pdf/?tool=EBI",
  "pmcid": "PMC13725815",
  "pmid": "42974268",
  "published": "2026-10-16",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/7r6rdc9mjj3pw.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T15:20:51Z",
      "native_id": "PMC:PMC13725815",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13725815"
    },
    {
      "first_seen": "2026-11-04T15:20:48Z",
      "native_id": "MED:42974268",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42974268"
    },
    {
      "first_seen": "2026-11-05T12:22:16Z",
      "native_id": "PMC13725815",
      "source": "pmc",
      "url": "https://doi.org/10.3389/frai.2026.1948601"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2738|Dementia and Cognitive Impairment Research",
      "subfield": "psychiatry"
    }
  ],
  "title": "A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI",
  "title_text": "A hybrid CNN–BiLSTM network with additive attention for automated four-stage classification of Alzheimer's disease from brain MRI",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T12:21:55Z",
  "url": "https://research.draconitic.com/paper/7r6rdc9mjj3pw",
  "venue": "Frontiers in artificial intelligence",
  "versions": []
}