{
  "abstract": "Objectives We assessed the feasibility of utilising machine learning (ML) methods to automate triage of vascular referrals from primary care.Methods General practitioners (GP) provided hypothetical patient referral letters for peripheral vascular disease and varicose veins, which were augmented to include non-vascular referrals with realistic noise. Vascular surgeons triaged the letters to identify referral type (RT) and clinical urgency (CU). Support vector machine (SVM), k-nearest neighbours (kNN), Random Forest (RF), Multi-Layer Perceptron (MLP), with and without functional API, and transformers (BERT, ClinicalBERT) were used to perform multi-class classification identifying RT and CU. Performance assessed using precision, recall, F1-scores, and t-tests over different dataset configurations.Results Sixty-three GP letters were augmented to 408 letters by synthetic letter generation. BERT achieved the highest combined F1 score (0.8776 ± 0.0156) on the full dataset, followed by SVM (0.8345 ± 0.0402), ClinicalBERT (0.8309 ± 0.0204), MLP (0.8112 ± 0.0434), RF (0.8043 ± 0.0347), kNN (0.7821 ± 0.0456), andFunctional API (0.7670 ± 0.0164). For CU classification, BERT demonstrated superior performance (0.7579) compared to SVM (0.6716), ClinicalBERT (0.6540), MLP (0.6325), RF (0.6086), kNN (0.5924), and Functional API (0.5617). While combined scores appeared similar, statistical analysis revealed significant differences between models. Excluding non-vascular cases maintained consistent model rankings demonstrating generalisability.Conclusions Transformer-based and classical machine learning models demonstrate viability for automated vascular referral triage. Further, larger studies with real patient- level referral letters are recommended.",
  "authors": [
    {
      "affiliations": [
        "University of Portsmouth, Bart’s Health NHS Trust"
      ],
      "name": "Freddie Barrett-Danes"
    },
    {
      "affiliations": [
        "Vascular Surgeon & Clinical Informatician, Bart’s Health NHS Trust"
      ],
      "name": "Sobath Premaratne"
    },
    {
      "affiliations": [
        "School of Computing, University of Portsmouth, UK"
      ],
      "name": "Elisavet Andrikopoulou"
    }
  ],
  "title": "3 Automated triage of primary care referrals to vascular surgery using machine learning",
  "uid": "6cfc747b-16e4-59fe-b254-c6729b4dc160"
}