From Data to Decisions: How AI Is Revolutionizing Clinical Prediction Models in Plastic Surgery

Abstract

SUMMARY: The impact of clinical prediction models within Artificial Intelligence (AI) and machine learning (ML) is significant. With its ability to analyze vast amounts of data and identify complex patterns, machine learning has the potential to improve and implement evidence-based plastic, reconstructive, and hand surgery. Among others, it is capable of predicting the diagnosis, prognosis, and outcomes of individual patients. This modeling aids daily clinical decision making, most commonly at the moment, as decision-support. Therefore, the purpose of this paper is to provide a practice guideline to plastic surgeons implementing AI in clinical decision-making or setting up AI research to develop clinical prediction models using the 7-step approach and the ABCD validation steps of Steyerberg et al. Secondly, we describe two important protocols which are in the development stage for AI research: 1) the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) checklist, and 2) The PROBAST checklist to access potential biases.