Use of Artificial Intelligence to Improve the Calculation of Percent Adhesion for Transdermal and Topical Delivery Systems

Abstract

Adhesion is a critical quality attribute and performance characteristic for transdermal and topical delivery systems (TDS). Regulatory agencies recommend in vivo skin adhesion studies to support the approval of TDS in both new drug applications and abbreviated new drug applications. The current assessment approach in such studies is based on the visual observation of the percent adhesion, defined as the ratio of the area of TDS attached to the skin to the total area of the TDS. Visually estimated percent adhesion by trained clinicians or trial participants creates variability and bias. In addition, trial participants are typically confined to clinical centers during the entire product wear period, which may lead to challenges when translating adhesion performance to the real world setting. In this work we propose to use artificial intelligence and mobile technologies to aid and automate the collection of photographic evidence and estimation of percent adhesion. We trained state-of-art deep learning models with advanced techniques and in-house curated data. Results indicate good performance from the trained models and the potential use of such models in clinical practice is further explored.