{
  "abstract": "Neoadjuvant chemoimmunotherapy improves outcomes for resectable non-small cell lung cancer (NSCLC), but can cause severe treatment-related adverse events (TRAEs). Pretreatment models for predicting grade ≥3 TRAEs during neoadjuvant chemoimmunotherapy remain limited. This study aimed to develop and externally validate an explainable machine learning model for predicting grade ≥3 TRAEs in patients with resectable NSCLC receiving neoadjuvant chemoimmunotherapy. This multicenter retrospective study included a discovery cohort (n=953) and an independent external validation cohort (n=143). The discovery cohort was stratified into training (n=668) and internal test (n=285) sets. Pretreatment candidates included routine clinical and laboratory variables and first-cycle treatment characteristics. Stability-oriented Boruta selection was used for variable selection, followed by variance inflation factor (VIF) assessment. Eight machine learning (ML) algorithms were tuned using 10-fold cross-validation in the training set. Discrimination, calibration, decision curve analysis (DCA), and explanations based on SHapley Additive exPlanations (SHAP) were evaluated. Secondary analyses assessed hematologic, nonhematologic, and immune-related adverse event (irAE) endpoints. Grade ≥3 TRAEs occurred in 496 of 1,096 patients (45.3%); 464 patients (42.3%) experienced grade ≥3 hematologic toxicity, and 446 (89.9% of patients with grade ≥3 TRAEs) reached the composite endpoint exclusively because of hematologic events. The final random forest model incorporating 12 pretreatment predictors achieved areas under the receiver operating characteristic curve (AUCs) of 0.782 and 0.742 in the internal test and external validation cohorts, respectively. When the locked overall-TRAE model was applied to toxicity subtypes, discrimination was maintained for grade ≥3 hematologic toxicity (AUCs, 0.764 and 0.732) but was substantially weaker for grade ≥3 nonhematologic toxicity (0.638 and 0.631) and any-grade irAEs (0.435 and 0.535). The hematologic toxicity-specific model achieved AUCs of 0.777 and 0.711 in the internal test and external validation cohorts, respectively. The pretreatment random forest model showed moderate external discrimination for overall grade ≥3 TRAEs, primarily reflecting hematologic toxicity.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China.",
    "Department of Thoracic Surgery, Shandong Public Health Clinical Center Affiliated to Shandong University, Jinan, China.",
    "First Clinical Medical College, Shandong University of Traditional Chinese Medicine, Jinan, China.",
    "Department of Thoracic Surgery, Anhui Chest Hospital, Hefei, China.",
    "Department of Thoracic Surgery, Ningbo No. 2 Hospital, Chinese Academy of Sciences, Ningbo, China.",
    "Department of Pathology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 17,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Fei-Hang Zhi"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Yunzeng Zhang"
    },
    {
      "affs": [
        3
      ],
      "name": "Tengfei Ge"
    },
    {
      "affs": [
        0
      ],
      "name": "Lei Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "Yichen Dong"
    },
    {
      "affs": [
        0
      ],
      "name": "Jialiang Wen"
    },
    {
      "affs": [
        0
      ],
      "name": "Haojie Si"
    },
    {
      "affs": [
        0
      ],
      "name": "Jingyu Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuzhou Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Delun Yang"
    },
    {
      "affs": [
        0
      ],
      "name": "Yicheng Wang"
    },
    {
      "affs": [
        4
      ],
      "name": "Minglei Yang"
    },
    {
      "affs": [
        5
      ],
      "name": "Huikang Xie"
    },
    {
      "affs": [
        0
      ],
      "name": "Junqi Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "Long Xu"
    },
    {
      "affs": [
        0
      ],
      "name": "Deping Zhao"
    },
    {
      "affs": [
        0
      ],
      "name": "Chang Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0av8qzmgjk47k.bib",
  "cited_by": 0,
  "doi": "10.21037/tlcr-2026-0984",
  "fulltext_url": "https://europepmc.org/articles/PMC13743462",
  "id": "0av8qzmgjk47k",
  "issns": [
    "2218-6751",
    "2226-4477"
  ],
  "landing_url": "https://europepmc.org/article/MED/42999415",
  "language": "eng",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2740|Lung Cancer Diagnosis and Treatment"
    ]
  ],
  "openalex": "W7223402795",
  "pdf_url": "https://europepmc.org/articles/PMC13743462?pdf=render",
  "pmcid": "PMC13743462",
  "pmid": "42999415",
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0av8qzmgjk47k.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T15:20:41Z",
      "native_id": "MED:42999415",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42999415"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "journal-openalex:2730|Lung Cancer Research Studies",
      "subfield": "oncology"
    }
  ],
  "title": "Explainable machine learning for predicting grade ≥3 treatment-related adverse events in resectable non-small cell lung cancer receiving neoadjuvant chemoimmunotherapy: predominant contribution of hematologic toxicity.",
  "title_text": "Explainable machine learning for predicting grade ≥3 treatment-related adverse events in resectable non-small cell lung cancer receiving neoadjuvant chemoimmunotherapy: predominant contribution of hematologic toxicity.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T15:20:41Z",
  "url": "https://research.draconitic.com/paper/0av8qzmgjk47k",
  "venue": "Translational lung cancer research",
  "versions": []
}