Artificial Intelligence‐Driven Insights into Electrospinning: Machine Learning Models to Predict Cotton‐Wool‐Like Structure of Electrospun Fibers

The electrospinning process allows the fabrication of nano‐ and microfibers, which are suitable for a variety of applications. These fibers are particularly valuable in tissue engineering for scaffold fabrication, as they mimic the morphology of the native extracellular matrix. The process involves several critical parameters that are essential for producing bead‐free fibers. Traditionally, optimizing the electrospinning process has relied on “trial‐and‐error” approaches and recent advancements have introduced artificial intelligence (AI)‐based tools to predict fiber properties by selecting appropriate input features for the models. In this work, machine learning models are utilized to classify and predict the fabrication of cotton‐wool‐like electrospun fibers. The dataset comprises data from both literature and experimental sources. Among the supervised models tested, the k‐Nearest Neighbors (KNN) algorithm demonstrates superior performance in terms of F1‐score, accuracy, precision, and recall. The results from the model inference validate this approach as valuable support in the experimental design for producing three‐dimensional cotton‐wool‐like electrospun fibers. To further integrate AI models into researchers' experimental routine activities, a toolbox for model training and inference is successfully developed and presented.