Construction and Evaluation of an Artificial Intelligence Assistant Decision-Making System Focused on the Treat-to-Target Framework and Full Process Management for Atopic Dermatitis: Study Protocol for a Randomized Controlled Trial

<b>Background/Objectives</b>: Atopic dermatitis (AD) is a chronic inflammatory skin disease characterized by recurrent rashes and itching, which seriously affects the quality of life of patients and brings a heavy economic burden to society. The treat-to-target (T2T) strategy was proposed to guide optimal use of systemic therapies in patients with moderate to severe AD, and patients' adherence is emphasized along with combined evaluation from both health providers and patients. While effective treatments for AD are available, non-adherence of treatment is common in clinical practice due to the patients' unawareness of self-evaluation and lack of concern about the specific follow-up time points in clinics, which leads to the treatment failure and repeated relapse of AD. <b>Methods</b>: This project consists of three parts. First, an artificial intelligence (AI) model for diagnosis and severity grading of AD based on deep learning will be trained. Second, an AI assistant decision-making system (AIADMS) in the form of an app will be developed. Third, we design a prospective, randomized controlled trial to test the hypothesis that the AIADMS with implementation of the T2T could help control the disease progression and improve the clinical outcomes. <b>Results</b>: A total of 232 participants diagnosed with moderate to severe AD will be included and allocated into the app group or the control group. In the app group, participants will be assisted in using the app during the process of management and follow-up at the scheduled time points, including 2 weeks, 4 weeks, 8 weeks, 12 weeks, 6 months, and 12 months after treatment. In the control group, the diagnosis, treatment, and follow-up of participants will be carried out according to the current routine on a face-to-face basis. The primary outcome is the overall efficiency rate of treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI at 12 weeks after treatment, which is calculated as the "Total number of participants with effective treatment of 5 treating objectives/total number of participants *100%". Spss20.0 software will be used to analyze the data according to the principle of intent to treat. <b>Trial Registration</b>: The protocol was registered at the National Institutes of Health Clinical Trials Registry with the trial registration number NCT06362629 on 11 April 2024. <b>Conclusions</b>: This study aims to improve AD management by integrating advanced technology, patient engagement, and clinician oversight through AIADMS app to achieve treat-to-target (T2T) goals for effective and safe long-term control.