Validation of Abrocitinib's efficacy and safety in moderate-to-severe atopic dermatitis across racial, ethnic, and skin type subgroups using machine learning models

Atopic dermatitis (AD) is a chronic skin condition that causes red, itchy, and inflamed patches on the skin. Abrocitinib is a drug approved to treat moderate-to-severe cases of AD. However, previous studies haven't fully explored how patients of different races, ethnic backgrounds, or skin types (measured by Fitzpatrick skin type) respond to this treatment.

This research will analyze data from clinical trials that used abrocitinib to treat AD and will use machine learning, a subfield of artificial intelligence that enables computers to recognize patterns in data and make predictions, similar to how humans learn from experience. Rather than relying on a single mathematical formula, machine learning models analyze large amounts of data to identify trends and relationships that might not be immediately obvious.

In this study, we will use machine learning techniques that improve prediction accuracy by combining multiple simple models. One such technique, called Random Forests, creates multiple decision trees and averages their results to make more reliable predictions. Another technique, Gradient Boosting, builds a sequence of simple models, each improving on the mistakes of the previous one, to enhance overall accuracy.

This study will help doctors understand whether patients from three specific subgroups—racial, ethnic, and skin color groups—experience different treatment responses and side effects. The ultimate goal is to ensure that all patients, regardless of their racial or ethnic background or skin type, receive the most effective and safe treatment for AD.