Artificial Intelligence-based Prediction of Pathological Scarring Risk After Surgical Correction of Perioral Scar Deformities in Children Using Multimodal Clinical and Instrumental Data
Year: 2026
Type: article
Abstract: The final aesthetic and functional result of perioral reconstruction in children depends largely on the course of the early postoperative period (Kono et al., 2017; Ozog et al., 2021). Hypertrophic scarring after lip surgery occurs in 10–45% of patients and often requires repeated corrective operations (Papathanasiou et al., 2017; Jahanbin et al., 2019). The ability to identify high-risk patients early would allow the surgeon to start preventive therapy on time and to personalize the postoperative protocol. Currently, the risk of pathological scarring is estimated mainly by clinical judgement and subjective scales such as VSS and POSAS. These tools describe a scar that has already formed, but they do not predict how it will develop. Instrumental methods — photometry, laser Doppler flowmetry (LDF), surface electromyography (sEMG) and ultrasound — provide objective data on tissue perfusion, muscle activity and scar structure. However, these data are numerous and interrelated, and it is difficult for a clinician to combine them into a single forecast. Artificial intelligence (AI) and machine learning methods are well suited to this task, yet they have rarely been applied to scar prediction in pediatric maxillofacial surgery. Aim: to develop and test an artificial intelligence model that predicts the risk of pathological scarring after surgical correction of perioral scar deformities in children and supports the choice of postoperative treatment.
Language: English
Subfield: Dermatology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7235020892
