Identification of Stress-Related Hair Loss and Prevention Through the Application of a KNN Model Based on Machine Learning

The study presents a machine learning-based approach using the K-Nearest Neighbor (KNN) algorithm to predict hairfall severity and suggest preventive measures, focusing on stress-related factors such as workload, sleep quality, diet, scalp condition, and haircare habits. The model classifies hairfall into four categories: Few, Medium, Many, and A Lot, and provides personalized prevention recommendations. The results show a strong correlation between stress intensity and hairfall severity, highlighting the potential of machine learning in preventive medicine. The study offers an inexpensive and accessible solution, with future plans to include scalp image analysis and integration with wearable stress monitors.