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.
This study utilized the Random Forest Algorithm to create a machine learning model aimed at accurately predicting hair loss by considering complex datasets involving genetic, hormonal, lifestyle, and environmental factors, but specific outcomes were not reported.
This study suggests that pre-trained Transformers only outperform syntactic and lexical neural networks on unseen DarkNet sentences after extreme domain adaptation, indicating unexpected advantages from their massive pre-training corpora.
September 2025 in “Matics Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology)” This study found that among various predictive models for baldness risk, Random Forest Regression performed best with the lowest mean squared error and highest R², indicating strong predictive accuracy, especially with complex datasets, while Linear Regression was better suited to simpler datasets.
January 2021 in “arXiv (Cornell University)” This study found that self-supervised pretraining significantly improves accuracy in medical image classifiers for dermatology and chest X-ray tasks, outperforming supervised baselines and showing robustness to distribution shifts with limited labeled data.