{
  "abstract": "Background: Unnecessary blood preparation before total knee arthroplasty (TKA) and total hip arthroplasty (THA) increases healthcare costs and resource burden. Accurate preoperative transfusion risk prediction can support clinical decision-making and optimise blood bank management.\n\nMethods: We conducted a retrospective cohort study using real-world electronic health records from a tertiary medical centre in Taiwan (2020–2025). A total of 6,089 patients undergoing TKA (n = 4,311) or THA (n = 1,778) were included. Twenty-eight preoperative features were extracted, including haematological indices, demographic variables, comorbidities, and medication use. Four machine learning models (Logistic Regression, Random Forest, XGBoost, LightGBM) were trained using 5-fold stratified cross-validation on an 80% development set and evaluated on a 20% holdout set. Model calibration was assessed using the Hosmer-Lemeshow test. SHAP values were used to interpret feature contributions globally and by surgical subgroup.\n\nResults: The overall transfusion rate was 18.7% (TKA: 15.3%; THA: 27.1%). LightGBM achieved the highest holdout AUROC (0.751; 95% CI: 0.714–0.787), with good calibration (Hosmer-Lemeshow p = 0.297), Brier Score of 0.128, and NPV of 0.891 at the Youden Index threshold. SHAP analysis identified preoperative haemoglobin (Hb), surgery type, and tranexamic acid (TXA) use as the top predictors. A non-linear relationship was observed: transfusion risk increased sharply when preop Hb fell below 12 g/dL.\n\nConclusions: An interpretable LightGBM model demonstrated reliable discrimination and calibration for perioperative transfusion prediction. The high NPV suggests this model can safely identify low-risk patients, potentially reducing unnecessary blood preparation in orthopaedic surgical settings.\n\nKey messages: • A LightGBM model predicts perioperative transfusion risk in TKA/THA with an AUROC of 0.751 and NPV of 0.891, enabling safer reduction of unnecessary blood preparation.\n\n• Preoperative haemoglobin, surgery type, and TXA use are the strongest predictors of transfusion; risk rises sharply when Hb falls below 12 g/dL.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "abstract",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "TT Tien"
    },
    {
      "name": "CY Chen"
    },
    {
      "name": "HE Tzeng"
    },
    {
      "name": "JH Lin"
    },
    {
      "name": "KM Lu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/46y7d8g2s5x8s.bib",
  "cited_by": 0,
  "doi": "10.1093/eurpub/ckag169.1207",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13699739/",
  "id": "46y7d8g2s5x8s",
  "issns": [
    "1101-1262",
    "1464-360X"
  ],
  "landing_url": "https://doi.org/10.1093/eurpub/ckag169.1207",
  "language": "en",
  "licence": "CC-BY-NC-4.0",
  "licence_label": "CC BY-NC 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "6. Poster Displays"
    ],
    [
      "heading",
      "AcademicSubjects/MED00860"
    ],
    [
      "heading",
      "AcademicSubjects/SOC01210"
    ],
    [
      "heading",
      "AcademicSubjects/SOC02610"
    ],
    [
      "heading",
      "DE. Digital health and Artificial Intelligence"
    ],
    [
      "openalex",
      "2704|Blood transfusion and management"
    ]
  ],
  "openalex": "W7223657759",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13699739/pdf/?tool=EBI",
  "pmcid": "PMC13699739",
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Oxford University Press",
  "ris": "https://research.draconitic.com/paper/46y7d8g2s5x8s.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:18Z",
      "native_id": "PMC13699739",
      "source": "pmc",
      "url": "https://doi.org/10.1093/eurpub/ckag169.1207"
    },
    {
      "first_seen": "2026-10-30T12:21:47Z",
      "native_id": "PMC:PMC13699739",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13699739"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2704|Blood transfusion and management",
      "subfield": "general"
    }
  ],
  "title": "Machine Learning for Preoperative Transfusion Risk Prediction in Total Knee and Hip Arthroplasty",
  "title_text": "Machine Learning for Preoperative Transfusion Risk Prediction in Total Knee and Hip Arthroplasty",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:36:16Z",
  "url": "https://research.draconitic.com/paper/46y7d8g2s5x8s",
  "venue": "The European Journal of Public Health",
  "versions": []
}