Nanofiber-Based Wound Healing Drug Delivery

Abstract

Nanofiber-based wound dressings have emerged as promising drug delivery platforms because of their high surface-area-to-volume ratio, tunable porosity, and ability to provide sustained therapeutic release. Despite rapid advances in nanofabrication, current wound management strategies largely rely on standardized formulations that overlook patient-specific wound characteristics. Recent developments in artificial intelligence (AI) have enabled predictive healthcare solutions; however, few studies integrate explainable machine learning with nanofiber drug delivery optimization. This study addresses this gap by proposing an Explainable AI (XAI)-assisted framework that predicts wound healing efficiency from nanofiber formulation attributes while providing interpretable decision support for clinicians. The proposed framework combines electrospun material characteristics, drug release kinetics, wound microenvironment indicators, and digital wound imaging features to optimize therapeutic outcomes. A gradient boosting architecture enhanced with SHAP-based interpretability is conceptually designed to estimate Date of Publication: 04-01-2026 healing progression and recommend personalized formulation adjustments. The framework aims to improve treatment precision, reduce unnecessary dressing changes, and facilitate transparent AI-assisted clinical decision-making. The proposed research demonstrates how explainable predictive analytics can accelerate the translation of intelligent nanofiber systems into digital healthcare environments