In this study, a machine-learning model was evaluated for its ability to categorize various hair conditions, achieving high accuracy and balance between precision and recall, with an overall accuracy of 97% in detecting hair problems.
3 citations
,
November 2023 in “Journal of Computer Science and Engineering (JCSE)” This study observed that using the Fisher score feature selection approach with capsule network models led to a promising 94% accuracy in diabetes detection, indicating its potential as a diagnostic tool.
In this study, researchers developed a computational method called iEdgePathDDA that prioritizes anticancer drug candidates by analyzing changes in gene interactions, demonstrating superior performance compared to existing methods across colorectal, breast, and lung cancer datasets.
July 2026 in “International Journal of Advanced Research in Science Communication and Technology” In this study, the BaldGraphFormer framework, integrating visual and clinical data, outperformed unimodal baselines in early-stage androgenetic alopecia detection, achieving an F1-score of 97.62% and macro-average AUC of 0.992, suggesting its potential to support dermatological decision-making and early intervention.
In this study, researchers developed a deep learning model that efficiently classifies five degrees of harm with high accuracy, achieving up to 98% precision, recall, and F1-score across various harm levels, indicating strong potential for practical application in automated harm evaluation.