Facial Analysis in Acromegaly Using Machine Learning: Towards Earlier Diagnosis

Abstract Background Acromegaly is a rare and progressive disorder often diagnosed late due to its insidious onset and gradually evolving facial features. Early detection remains a critical unmet need to reduce disease-associated morbidity and mortality. Objective This study aimed to develop and evaluate machine learning models that can identify acromegaly-specific facial features using pre-diagnostic photographs, potentially enabling earlier diagnosis. Methods A total of 489 facial photographs from 92 patients with acromegaly and 254 images from 88 healthy controls were analyzed. A two-stage pipeline was implemented: (1) deep feature extraction using a pre-trained VGG-Face model followed by support vector machine (SVM) classification, and (2) an interpretable model using five landmark-based facial measurements. Separate datasets were created using pre-diagnosis, post-diagnosis, and combined images to evaluate model performance. Results The best classification results were obtained from the pre-diagnosis dataset (mean 7.47 years before diagnosis), with an AUC of 0.982 and accuracy of 91.5%. Interpretability analyses highlighted maxillary, nasal, and orbital regions as key facial zones. The interpretable model, using facial ratios, achieved moderate accuracy (AUC 0.776) while providing clinical insight into contributing features such as face width-to-height ratio and philtrum height. Conclusion Our findings demonstrate that acromegaly-related facial features can be detected years before clinical diagnosis using machine learning. By combining high-performance deep models with interpretable approaches, this study supports the potential for AI-based facial screening tools to aid in early detection of acromegaly.