{
  "abstract": "Objectives Surgical pressure injuries (SPIs) are a significant patient safety risk due to prolonged immobility and tissue hypoperfusion under general anaesthesia. Existing risk assessment tools lack real-time predictive capabilities. This study developed and validated a machine-learning model for SPI prediction and clinical integration.Method This retrospective cohort study analysed electronic health records from 931 surgical inpatients under general anaesthesia between January 2016 and December 2021. SPI cases were identified using ICD-10 codes with 1:1 matching by medical specialty. Data preprocessing included imputation, normalisation and outlier removal. Logistic regression (LR), multilayer perceptron (MLP) and decision tree (DT) models were developed and validated via cross-validation. Model performance was assessed using area under the curve (AUC), accuracy, precision, recall and F1 score.Results Significant SPI predictors included the Charlson Comorbidity Index (p<0.001), number of medication types (p=0.001) and body mass index (p<0.001). The MLP outperformed LR (AUC=0.707) and DT (AUC=0.717), achieving the highest AUC (0.836), accuracy (0.773), precision (0.812), recall (0.688) and F1 score (0.745).Discussion The MLP model effectively identified key SPI risk factors, outperforming LR and DT by capturing non-linear relationships. Its integration into clinical workflows may enhance perioperative risk management through early detection and targeted interventions.Conclusion Machine learning integration can improve early SPI detection and personalised prevention. The MLP model demonstrated the highest potential for real-time SPI risk stratification. Future research should validate this model across diverse surgical populations and develop scalable strategies for clinical implementation.",
  "authors": [
    {
      "affiliations": [
        "Quality Management Center, Tri-Service General Hospital, Taipei City, Taiwan",
        "Graduate Institute of Medical Sciences, National Defense Medical University, Taipei City, Taiwan"
      ],
      "name": "Chia-Yen Li"
    },
    {
      "affiliations": [
        "School of Public Health, National Defense Medical University, Taipei City, Taiwan",
        "Department of Public Health, Kaohsiung Medical University, Kaohsiung, Taiwan"
      ],
      "name": "Chi-Ming Chu"
    },
    {
      "affiliations": [
        "Division of Trauma & Critical Surgery, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan"
      ],
      "name": "Chao-Wen Chen"
    },
    {
      "affiliations": [
        "Department of Cardiovascular Surgery, Tri-Service General Hospital, Taipei City, Taiwan"
      ],
      "name": "Hung-Yen Ke"
    },
    {
      "affiliations": [
        "Graduate Institute of Medical Sciences, National Defense Medical University, Taipei City, Taiwan",
        "Department of Nursing, Tri-Service General Hospital, Taipei City, Taiwan"
      ],
      "name": "Peng-Ching Hsiao"
    },
    {
      "affiliations": [
        "Department of Nursing, Tri-Service General Hospital, Taipei City, Taiwan",
        "School of Nursing, National Defense Medical University, Taipei City, Taiwan"
      ],
      "name": "Hsueh-Hsing Pan"
    }
  ],
  "title": "Comparative performance of logistic regression, multilayer perceptron and decision tree models for predicting surgical pressure injuries: a retrospective cohort study",
  "uid": "fe590dfa-60ee-5caa-99f1-7ed4a98c5e9a"
}