December 2019 in “Periodicals of Engineering and Natural Sciences (International University of Sarajevo)” This study presents a machine learning algorithm that achieved 89.5% accuracy in predicting hair health using factors like spatial-temporal images, age, and gender.
1 citations
,
September 2024 in “arXiv (Cornell University)” This study reviews methods to ensure the reliability of machine learning models in medical imaging, focusing on bias detection, data drift assessment, and accuracy estimation without ground truth labels to enhance integration into clinical settings.
December 2019 in “Periodicals of Engineering and Natural Sciences (PEN)” This research reported that using J48 algorithms with bagging improves prediction accuracy of hair health through machine learning by analyzing factors like spatial-temporal images, gender, and age, achieving a real-time performance of 89.5%.
35 citations
,
November 2022 in “The Journal of Dermatology” This study found that the prevalence of alopecia areata in Japan increased from 2012 to 2019, with allergic diseases as common comorbidities and a need for more effective treatments, particularly for severe and pediatric cases.
December 2022 in “Research Square (Research Square)” This study discusses the development of deep learning models for diagnosing skin disorders and notes challenges such as lack of data for darker skin tones, without providing new clinical results.