Abstract
Androgenetic alopecia (AGA), the most common form of hair loss, has been linked to dysbiosis of the scalp microbiome. In this study, we collected microbiome samples from the frontal baldness and occipital regions of patients with varying stages of AGA and conducted a comprehensive analysis of bacterial and fungal communities using 16S rRNA and ITS1 sequencing. Our results revealed that although the scalp microbiome dynamics in healthy subjects correlated strongly with chronological age, this trend was disrupted in AGA patients due to severe microbial imbalances, emphasizing the significant impact of AGA on the scalp microecology. Notably, microbial dysbiosis was not confined to the localized areas of hair loss but extended across the entire scalp. Moreover, the degree of dysbiosis was consistent with the severity of AGA. Leveraging multi-kingdom microbial features and machine learning, we developed a microbial index of scalp health (MiSCH), which effectively detects AGA and stratifies its severity. More importantly, MiSCH was able to identify high-risk individuals, those with significantly disrupted microbiome structures but no overt AGA phenotypic characteristics, thereby offering opportunities for early diagnosis, risk assessment, and personalized treatment of AGA.IMPORTANCEBy analyzing the bacteria and fungi on the scalp, this study shows how androgenetic alopecia (AGA) disrupts the balance of microbes not just in the hair loss areas, but across the entire scalp. Thus, we introduce the microbial index of scalp health (MiSCH), which leverages microbiome data for the early detection and severity prediction of AGA. This method is especially valuable for identifying people at risk of developing more severe hair loss, even before visible symptoms appear. By combining microbiome analysis with machine learning, this research offers a potential breakthrough for early diagnosis and personalized treatments, changing how we approach hair loss and offering new hope for managing the condition more effectively.