# Machine Learning Applications Beyond Outcome Prediction in Plastic and Reconstructive Surgery: A Systematic Review of Diagnostic, Intraoperative, and Workflow Optimization Models

## TL;DR

This paper reviews how machine learning is used in plastic surgery for diagnosis, surgery, and workflow, finding promising accuracy but methodological issues.

## Contribution

A systematic review of ML applications in plastic surgery beyond outcome prediction, highlighting model performance and methodological gaps.

## Key findings

- Random forests, neural networks, and gradient boosting achieved AUCs over 0.90 in predicting surgical outcomes.
- Most studies used internal validation and had high or moderate risk of bias.
- Only one study performed external validation, and calibration reporting was limited.

## Abstract

Plastic and reconstructive surgery increasingly depends on data-driven instruments to improve clinical decision-making. Machine learning (ML), through its capacity to analyze intricate, high-dimensional data, presents novel prospects for forecasting surgical outcomes with enhanced accuracy compared to traditional statistical models. This systematic study evaluates the extent, efficacy, and methodological rigor of ML applications in plastic and reconstructive surgery, encompassing burn treatment, microsurgical reconstruction, and breast surgery. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 standards, we searched four main databases for research published between January 2015 and March 2025. Eligible papers used ML models to predict clinical outcomes in plastic or reconstructive surgery and provided quantifiable performance indicators. Data were retrieved using the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) and Prediction Model Risk of Bias Assessment Tool (PROBAST) frameworks, then synthesized narratively. We included eleven studies that had more than 34,000 patients. Random forests, neural networks, and gradient boosting have emerged as the most prevalent and highest-performing models, with several attaining AUCs exceeding 0.90. Notwithstanding encouraging outcomes, the majority of research depended on internal validation, with only one performing external validation. Calibration reporting and data transparency were constrained. The majority of studies exhibited a high or moderate risk of bias. In summary, ML models provide significant prediction accuracy in plastic surgery; yet, they are limited by methodological deficiencies that impede clinical implementation. Future initiatives must prioritize external validation, repeatability, and ethical execution to facilitate the safe and successful incorporation into surgical practice.