SCRATCH-AI: A Tool to Predict Honey Wound Healing Properties

In this work, we propose SCRATCH-AI, a tool which relies on interpretable machine learning (ML) methods (namely, Bayesian networks and decision trees) to classify honey samples into wound healing categories. Classification explores the impact of botanical origins (i.e., honey type) and key chemical–biological characteristics such as antioxidant activity on healing, assessed through wound recovery metrics. The obtained classification performance results are very encouraging. Moreover, the models provide non-trivial insights about the causal dependencies of some specific honey features on wound healing properties and show the effect of different honey types (other than the well known Manuka) on cicatrization. The tool is inherently interpretable (due to the chosen ML techniques) and made user-friendly by a carefully designed graphical interface. We believe that the information provided by our tool will allow biologists and clinicians to better utilize honey, with the ultimate goal of leveraging honey capability to accelerate healing and reduce infection risks in clinical practice.