{
  "abstract": "Background: Pulmonary neuroendocrine carcinomas (pNECs) are a rare and heterogeneous group of malignancies, ranging from low-grade carcinoids to high-grade small-cell lung carcinoma (SCLC) and large-cell neuroendocrine carcinoma (LCNEC). Prognostic tools for these tumors are scarce and have rarely been validated in external cohorts.\n\nObjectives: This study aimed to develop a Transformer-based prognostic prediction model for pNEC and validate it in an independent external cohort, to improve survival estimation and support individualized treatment decisions.\n\nMethods: This retrospective two-center cohort study included 823 patients with surgically resected pNEC (2001-2023). Models were developed in Center 1 (n=374; randomly split 8:2 into training and internal test sets) and externally validated in an independent Center 2 cohort (n=449). Three algorithms—logistic regression (LR), decision tree (DT), and the Transformer-based tabular foundation model TabPFN—were compared for estimating overall survival (OS) and disease-free survival (DFS) at 1-, 3-, and 5-year landmarks, with evaluation by receiver operating characteristic, calibration, and decision curve analyses, and SHapley Additive exPlanations (SHAP) analysis for interpretability.\n\nResults: TabPFN achieved the highest area under the curve (AUC) in most tasks in both test sets, with task-dependent exceptions: in the internal test set, logistic regression performed best for 1-year OS (AUC 0.885), while TabPFN performed best for the remaining tasks, including 3-year OS (0.880), overall DFS (0.810), and 1-year DFS (0.892); in the external test set, TabPFN remained best for 1- and 3-year OS and for overall, 1-, and 3-year DFS (0.747-0.802), whereas logistic regression performed best for 5-year OS and DFS. External calibration was less satisfactory. Disease stage, pathological subtype, and age were the key prognostic predictors, and TabPFN was more accurate for low-grade subtypes. SHAP analysis quantified the contribution of each feature and made the model interpretable.\n\nConclusions: The Transformer-based model improves survival estimation in pNEC, with task-dependent advantages over conventional methods and confirmed transportability to an independent institutional cohort. Prospective multicenter validation and calibration refinement are needed before broader clinical use.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Science & Peking Union Medical College",
    "Department of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College",
    "Institute of Advanced Research, Infervision Medical Technology Co., Ltd"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Lei Liu"
    },
    {
      "affs": [
        1
      ],
      "name": "Linchuan Liang"
    },
    {
      "affs": [
        2
      ],
      "name": "Dawei Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Jiaqi Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Ke Zhao"
    },
    {
      "affs": [
        0
      ],
      "name": "Chao Guo"
    },
    {
      "affs": [
        0
      ],
      "name": "Cheng Huang"
    },
    {
      "affs": [
        0
      ],
      "name": "Shanqing Li"
    },
    {
      "affs": [
        1
      ],
      "name": "Yushun Gao"
    },
    {
      "affs": [
        0
      ],
      "name": "Yeye Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1qq1r9txpfya5.bib",
  "cited_by": 0,
  "doi": "10.3389/fonc.2026.1948262",
  "fulltext_url": "https://www.frontiersin.org/articles/10.3389/fonc.2026.1948262/full",
  "id": "1qq1r9txpfya5",
  "issns": [
    "2234-943X"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fonc.2026.1948262/full",
  "language": "en",
  "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": [
    [
      "lcc",
      "RC254-282"
    ],
    [
      "openalex",
      "2730|Lung Cancer Research Studies"
    ]
  ],
  "openalex": "W7223316944",
  "pdf_url": "https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2026.1948262/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-23",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/1qq1r9txpfya5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:13Z",
      "native_id": "10.3389/fonc.2026.1948262",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fonc.2026.1948262/full"
    },
    {
      "first_seen": "2026-10-30T13:43:12Z",
      "native_id": "bc2464a48d534a1c80dd7c7f8c877735",
      "source": "doaj",
      "url": "https://doi.org/10.3389/fonc.2026.1948262"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2730|Lung Cancer Research Studies",
      "subfield": "oncology"
    }
  ],
  "title": "Prognostic prediction of pulmonary neuroendocrine carcinoma using a transformer-based artificial intelligence model: a two-center retrospective cohort study",
  "title_text": "Prognostic prediction of pulmonary neuroendocrine carcinoma using a transformer-based artificial intelligence model: a two-center retrospective cohort study",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:43:12Z",
  "url": "https://research.draconitic.com/paper/1qq1r9txpfya5",
  "venue": "Frontiers in Oncology",
  "versions": []
}