alles over ongeneeslijke ziektes

Hair and nails

Artificial Intelligence-Based Personalization of Treatment Regimen for Hair Loss: A 6-Month Clinical Trial.

3 Small study in people

What this means for you: first signals, nothing more.
Type of study
clinical trial
Studied in
people
Participants
38
Published
2025 in Journal of drugs in dermatology : JDD
Cited
2 times by other research
Who paid
Not declared. PubMed carries no conflict-of-interest statement for most articles; that is not the same as independent.
Source
PubMed 40043278 · doi 10.36849/JDD.8611
The plain-language write-up of this study is still being written. Below is the abstract exactly as the researchers published it.
Abstract by the researchers — original text

Hair loss affects up to 50% of women and 80% of men. The high costs and wait times for professional consultations lead many to seek one-size-fits-all solutions that are frequently ineffective. This study tested an artificial intelligence (AI) model for customizing non-medicated hair loss treatments. In a 24-week trial, 38 women with self-reported hair thinning received personalized product kits based on AI analysis of scalp images and questionnaires. Treatments included various combinations of topical serums, shampoos, oral supplements, and marine collagen peptides. Of the 27 participants who completed the study, significant improvements were observed in hair growth, coverage, and thickness (P<0.001 for all). Hair shedding decreased by 37.3% at 12 weeks and 32.4% at 24 weeks. Scalp transepidermal water loss was reduced by 61.5% at 12 weeks and 69% at 24 weeks. Scanning electron microscopy showed improved hair texture. Participants reported overall hair improvement (88.9%), better scalp health (85.2%), and less hair brittleness (92.6%) (P<0.001 for all). No adverse events were reported. The AI-driven platform effectively delivered personalized hair loss treatments, suggesting a data-driven, customized, and accessible self-served alternative for hair loss management. J Drugs Dermatol. 2025;24(3):233-238. doi:10.36849/JDD.8611.