AI-driven wound healing analysis and progression tracking in mobile applications: A scalable approach for healthcare accessibility

Kesaraju, Rishi (2025) AI-driven wound healing analysis and progression tracking in mobile applications: A scalable approach for healthcare accessibility. World Journal of Advanced Research and Reviews, 26 (1). pp. 1895-1905. ISSN 2581-9615

Indeed, wound care is the most important aspect of health care management for patients suffering from chronic ailments, such as diabetic ulcer, pressure sore, or surgical wound. Manual assessment, however, is highly resource consuming, prone to errors, and very much impractical in remote or neglected areas. This research shows an artificial intelligence (AI) based mobile tax application, which automates assessment for wound-healing stages and provides real-time personalized recovery updates. It aims mainly at classifying wounds in terms of their stages of healing and to have a predictability on recovery timelines using sequential images in order to facilitate the accessibility and decision-making on the case of wounds. The study implements convolutional neural networks (CNN) for the image classification and long short-term memory (LSTM) networks for the healing trajectory predictions. Based on a curated dataset of 2,500 annotated wound images, the developed models achieve a classification accuracy of 92% and a healing progression prediction error of less than 5%. The results prove that the mobile application can deliver wound-care solutions on scalability, efficiency, and affordability. Future works include further enhancing the dataset for improved model generalization and continuous monitoring of individuals through data from wearable sensors. This study thus speaks of AI driven applications making a difference in future healthcare by minimizing gaps in medical resources and giving patients actionable real time insights.