This study found that applying transfer learning with CNN architectures like AlexNet, VGG16, and ResNet50 achieved 99% accuracy in classifying multiclass hair disorders, suggesting a potential technological aid for dermatologists in diagnosing and treating hair conditions.
March 2026 in “FMDB Transactions on Sustainable Health Science Letters” This study developed a method using Convolutional Neural Networks to detect nutritional deficiencies, such as iron, zinc, biotin, and vitamins, through high-resolution images of hair and nails, achieving an 89% accuracy rate in identifying these deficiencies.
3 citations
,
May 2023 in “Endocrine Abstracts” This study identified three subgroups of women with PCOS with distinct androgen profiles, finding that the subgroup with adrenal-derived androgen excess had the highest insulin resistance and rates of hirsutism and hair loss.
October 2023 in “Journal of the Endocrine Society” In this study, distinct androgen excess subtypes were identified in women with PCOS, with the adrenal androgen excess cluster showing significantly higher rates of insulin resistance and type 2 diabetes, suggesting 11-oxygenated androgens as potential drivers of metabolic risk.
December 2024 in “International Journal of experimental research and review” In this study, the integration of obesity-related features and machine learning techniques significantly enhanced cardiovascular disease detection, with the XGBoost classifier achieving a 74% accuracy rate and improved metrics compared to other models.