{
  "abstract": "Introduction Persistent postsurgical pain (PPSP) affects up to 15% of patients after major surgery, impairing physical function, quality of life and increasing risk for long-term opioid use. Current PPSP prediction models rely on static or retrospective data and fail to incorporate dynamic perioperative factors. The Personalised Prediction of Persistent Postsurgical Pain (P5) study aims to develop individualised, multimodal prediction models by integrating preoperative behavioural, psychophysical and neurocognitive assessments and high-frequency symptom monitoring.Methods and analysis P5 is a prospective, single-centre cohort study enrolling 2500 adults aged 18–75 undergoing major surgery at a tertiary academic hospital. Participants complete baseline surveys, cognitive testing and quantitative sensory testing preoperatively. Ecological momentary assessments (EMAs) are collected via smartphone three times per day through 30 days postoperatively, capturing pain, mood, catastrophising and medication use. Participants are assessed on postoperative day 1 and complete online surveys at 3 and 6 months, evaluating pain persistence, interference, neuropathic symptoms and related outcomes. Clinical and perioperative data are extracted from the electronic health record. The primary outcome is PPSP at 3 months. Predictive models will be developed using supervised machine learning and dynamic structural equation modelling to extract latent features from EMA data. Model performance will be assessed using area under the receiver operating characteristic curve, area under the precision-recall curve and SHapley Additive exPlanations for interpretability.Ethics and dissemination This study has received ethics approval from the Washington University School of Medicine Institutional Review Board #202101123. Informed consent is required. Results will be submitted for publication in peer-reviewed journals and presented at research conferences.Trial registration number NCT04864275.",
  "authors": [
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA"
      ],
      "name": "Katherine J Holzer"
    },
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA"
      ],
      "name": "Harutyun Alaverdyan"
    },
    {
      "affiliations": [
        "Computer Science & Engineering, Washington University in St Louis McKelvey School of Engineering, St. Louis, Missouri, USA",
        "AI for Health Institute, Washington University in St Louis, St. Louis, Missouri, USA"
      ],
      "name": "Ziqi Xu"
    },
    {
      "affiliations": [
        "Biomedical Data Science and Psychiatry, Dartmouth College Geisel School of Medicine, Hanover, New Hampshire, USA"
      ],
      "name": "Madelyn R Frumkin"
    },
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA"
      ],
      "name": "Karen A Frey"
    },
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA"
      ],
      "name": "Stephen H Gregory"
    },
    {
      "affiliations": [
        "Psychology and Neuroscience, The University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA"
      ],
      "name": "Thomas L Rodebaugh"
    },
    {
      "affiliations": [
        "Computer Science & Engineering, Washington University in St Louis McKelvey School of Engineering, St. Louis, Missouri, USA",
        "AI for Health Institute, Washington University in St Louis, St. Louis, Missouri, USA"
      ],
      "name": "Chenyang Lu"
    },
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA",
        "AI for Health Institute, Washington University in St Louis, St. Louis, Missouri, USA"
      ],
      "name": "Christopher R King"
    },
    {
      "affiliations": [
        "Psychological and Brain Sciences, Washington University in St Louis, St. Louis, Missouri, USA"
      ],
      "name": "Denise Head"
    },
    {
      "affiliations": [
        "Computer Science & Engineering, Washington University in St Louis McKelvey School of Engineering, St. Louis, Missouri, USA",
        "AI for Health Institute, Washington University in St Louis, St. Louis, Missouri, USA",
        "Institute for Informatics, Data Science, and Biostatistics, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA"
      ],
      "name": "Thomas Kannampallil"
    },
    {
      "affiliations": [
        "Department of Anesthesiology, Washington University School of Medicine in Saint Louis, St. Louis, Missouri, USA",
        "AI for Health Institute, Washington University in St Louis, St. Louis, Missouri, USA"
      ],
      "name": "Simon Haroutounian"
    }
  ],
  "title": "Protocol for Personalised Prediction of Persistent Postsurgical Pain",
  "uid": "30434dd4-29da-5db7-885e-a8784cde93c9"
}