1 citations
,
January 2021 in “SISTEMASI” This study found that the multi-thresholding method was the most effective for segmenting hair during laser removal, as it clearly distinguished hair patterns with minimal noise.
1 citations
,
March 2025 in “Frontiers in Physiology” This study identified key genes linked to immune cells and potential therapeutic compounds for alopecia areata by evaluating upregulated genes from patient datasets, highlighting T and NK cell involvement in hair follicle attack and suggesting drug candidates through molecular docking and dynamics simulations.
1 citations
,
December 2025 in “Scientific Reports” In this study, researchers developed a predictive model for the onset of alopecia areata by analyzing six datasets to identify key feature genes and employing various machine learning algorithms, ultimately finding the XGBoost model most effective for clinical application.
January 2026 in “Metabolites” This study analyzed gene expression profiles from multiple tissues to explore the molecular connections between obesity and immune-related processes, identifying potential links and pathways that may require further experimental validation to understand their roles in obesity fully.
This study found that integrating machine learning enhances the predictive accuracy of forensic DNA phenotyping from low template DNA, achieving high accuracy for traits like eye color, although challenges remain for admixed populations and complex traits.
