Abstract
Male pattern hair loss (MPHL) is a common dermatological condition with significant psychological and clinical impacts. Traditional grading systems, such as the Norwood-Hamilton and Basic and Specific (BASP) classifications, rely on subjective assessments, limiting accuracy and reproducibility. This study introduces an AI-based grading framework that incorporates a novel area ratio metric to provide a more objective and standardized assessment of MPHL severity. A total of 761 images from 257 patients were analyzed to develop and evaluate an AI-based framework for grading MPHL. The framework utilizes the area ratio metric as a quantitative alternative to the traditional BASP length ratio. Model performance was assessed using precision and recall metrics, with bounding box and mask evaluations validating the accuracy and consistency of hair loss region identification. The AI model achieved an average precision of 97.6% in bounding box evaluations and 96.1% in mask assessments, demonstrating high accuracy in identifying hair loss regions. However, challenges in detecting smaller regions were reflected in slightly lower recall values for mask evaluations. Stratification accuracy was consistently high for Grades I, II, IV, and VI, with variability observed in intermediate grades due to boundary overlap. The novel area ratio metric outperformed the BASP length ratio, particularly in higher MPHL grades, offering a more reliable and objective framework for hair loss classification. This study shows that AI can improve MPHL diagnostics by using a data-driven and standardized grading system. The area ratio metric enhances precision and consistency, especially in advanced MPHL grades, offering better diagnostic accuracy and supporting personalized hair loss treatments.