Effectiveness of a Machine Learning-Enabled Skincare Recommendation for Mild-to-Moderate Acne Vulgaris: 8-Week Evaluator-Blinded Randomized Controlled Trial.

Background: Acne vulgaris (AV) is one of the most common skin disorders, with a peak incidence in adolescence and early adulthood. Topical treatments are usually used for mild to moderate AV; however, a lack of adherence to topical treatment is seen in patients due to various reasons. Therefore, personalized skincare recommendations may be beneficial for treating mild-to-moderate AV. Objective: This study aimed to evaluate the effectiveness of a novel machine learning approach in predicting the optimal treatment for mild-to-moderate AV based on self-assessment and objective measures. Methods: A randomized, evaluator-blinded, parallel-group study was conducted on 100 patients recruited from an internet-based database and randomized in a 1:1 ratio (groups A and B) based on their consent form submission. Groups A and B received customized product recommendations using a Bayesian machine learning model and self-selected treatments, respectively. The patients submitted self-assessed disease scores and photographs after the 8-week treatment. The primary and secondary outcomes were photograph evaluation by two board-certified dermatologists using the Investigator Global Assessment (IGA) scores and quality of life (QoL) measured using the Dermatology Life Quality Index (DLQI), respectively. Results: Overall, 99 patients were screened, and 68 patients (mean age: 27 years, SD 4.56 years) were randomized into groups A (customized) and B (self-selected). IGA scores significantly improved after treatment in group A but not in group B (mean difference in IGA score; group A=0.32, P=.04 vs group B=0.09, P=.54). The DLQI significantly improved in group A from 7.75 at baseline to 3.5 (P<.001) after treatment but reduced in group B from 7.53 to 5.3 (P>.05). IGA scores and the DLQI were significantly correlated in group A, but not in group B. A total of 3 patients reported adverse reactions in group B, but none in group A. Conclusions: Using a machine learning model for personalized skincare recommendations significantly reduced symptoms and improved severity and overall QoL of patients with mild-to-moderate AV, supporting the potential of machine learning-based personalized treatment options in dermatology.