AI App for Management of Atopic Dermatitis

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

Background: 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 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 it is emphasized patients' adherence and 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.

Hypothesis: An Artificial Intelligence assistant decision-making system (AIADMS) with implementation of the T2T framework could help control the disease progression and improve the clinical outcomes for AD.

Overall objectives:

We aim to develop an AIADMS in the form of smartphone app to integrate T2T approach for both clinicians and patients, and design clinical trials to verify the effectiveness and safety of the app. Methods: This project consists of three parts, AI training model for diagnosis and severity grading of AD based on deep learning, development of Artificial Intelligence assistant decision-making system (AIADMS) in the form of app, and design of a randomized controlled trial to verify the effectiveness and safety of AIADMS App for improvement of the clinical outcomes in AD patients.

Expected results: With application of AIADMS based app, the goal of T2T for patients with AD could be realized better, the prognosis could be improved, and more satisfaction could be achieved for both patients and clinicians.

Impact: This is the first AIADMS based app for AD management running through thediagnosis, patients' self-participation, medical follow-up, and evaluation of achievement of goal of T2T.

Study Overview

• Status: Not yet recruiting
• Conditions: Artificial Intelligence; Atopic Dermatitis
• Intervention / Treatment: Behavioral: Artificial Intelligence assistant decision-making system (AIADMS) App

Detailed Description

The project will be executed at the Department of Dermatovenereology, West China Hospital of Sichuan University. The protocol will be approved by the Biological- Medical Ethical Committee of the West China Hospital of Sichuan University, and written informed consent will be obtained from all participants before we take images of the skin lesions and before we recruit them in clinical trials.

1. Automatic detection and evaluation of AD based on AI deep learning 1.1 Dataset of atopic dermatitis The dataset will be established from more than 10,000 clinical images of AD patients for AI deep learning. Low-quality images will be excluded, and the images contained the surrounding background will be cropped to include only the AD lesions.

   1.2 Labelling the clinical signs of skin lesions The labelling will be completed by three certified dermatologists and three trained algorithm engineers. The dermatologists will label the clinical signs including erythema, papulation, edema, oozing, excoriation, lichenification, and dryness, and severity of each sign will be evaluated and labelled on a four-point scale (0: none, 1: mild, 2: moderate, and 3: severe). The result of each clinical sign in an image will be labelled as an example of erythema-2, edema- 2, or oozing-3. After labelling the images, the dermatologists and algorithm engineers verify the quality of the labelled images from both clinical and labelling rules and cross-validate the accuracy of signs and severity. Images that meet the requirements will be used for model training. During the labelling and model training process, the relevant personnel will be unaware of all the private patient information.

   1.3 Model training The model training will be carried out after labelling of the images.

   An accurate and efficient semantic segmentation model will be trained to distinguish abnormal skin lesion areas to identify all the clinical signs. A fast and accurate pixel level skin segmentation model will be trained to determine the ratio of the lesion area to the overall skin area. Besides, an efficient and practical method to convert the segmented skin lesion area into real skin area units will be created to achieve the accurate restoration of the true size as much as possible from the distortion of the skin lesion because of the shooting distance, angle, or automatic enhancement. The dataset will be divided for training, validation, and testing. Images of 6,500 of 10,000 will be used in training and validation of the proposed model, and images of the remaining 3,500 of 10,000 will be used for testing. After training, combined with the different questionnaire items filled by patients, the evaluative tools including EASI, SCORED, POEM, pp-NRS, and DLQI will be calculated by the model.

2. Development of the AIADMS app The app will support the Android system and IOS system, and it will be designed as two versions for both patients and clinicians with the distinguished login entrance. The fundamental function of the app will include "Push", "Reminder", "Upload", "Evaluation", and "Data management".

   2.1 The "Push" function is designed to transmit information to patients and medical staff. The pushed information could be received and displayed on the screen of the mobile phone even if the app is not opened and the mobile phone is in the locked screen state, and the users can set the time of receiving the pushed information by themselves. For example, the predetermined time point for follow-up in clinics will bepresented as "You should come to see the doctor on next Monday, July 25, 2023". The "Push" function can activate the use of app, increase the viscosity of users, and drive the utilization of other functional modules.

   2.2 The "Reminder" function is mainly used for reminding the patients of taking medicine, uploading photos of skin lesions, self-evaluation, and scheduled follow-up.

   2.3 The "Upload" function is designed to help patients participate in the systemic treatment. They can upload their photos of skin lesions, the description of progresses of AD, or questionnaires.

   2.4 The "Evaluation" function is developed to provide information for both patients and medical staff. By uploading photos of skin lesions and filling in the different questionnaire items, the app will automatically evaluate the severity of lesions and calculate the EASI, POEM, PP-NRS, SCORAD, or DLQI scores. This function could help patients know more about their situation of the disease, and take part in self- evaluation and self-care as the T2T strategy recommended.

   2.4 The "Data management" function is designed for medical staff to manage the patients more conveniently and design the medical research. They can log in to the app platform website to collect and export data, carry out statistical analysis and big data mining. App itself can also make simple statistics and management of data. For example, data such as EASI, POEM and PP-NRS score at the time points of before treatment, 2 weeks, 4 weeks, 12 weeks and 6 months after treatment could be automatically generated into statistical reports to presented in the form of histograms or curves. App can also be further improved and updated to the new version through the analysis of users' habits, and the function modules could be optimized with the high frequency of use and the feedback from both medical staff and patients.

3. Effectiveness and safety of AIADMS App for improvement of the clinical outcomes in AD patients: a randomized controlled trial.

This trial is a single centered, prospective, randomized controlled trial that test the superiority of the implementation of T2T strategy by application of AIADMS app in patients with AD in term of improvement of clinical outcomes.

This would the first AI assisted tool for AD during the process of diagnosis, management, and follow-up. It will provide solid evidence for the application of AI in dermatology worldwidely.

• Study Type: Interventional
• Enrollment (Estimated): 232
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Jingyi Li, M.D.; Phone Number: +86-18980605704; Email: jingyili@wchscu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Diagnosed with AD, aged 1~75 years; be able to communicate in Chinese; with basic reading and writing skills; participants or the guardian have smartphones or pads and are familiar with the use skills.

Exclusion Criteria:

• Mental illness; personality disorder; language barrier; hearing impairment; communication difficulties; with serious coexisting diseases, such as cardiopulmonary insufficiency, liver dysfunction, renal dysfunction, blood system diseases, tumors, or other diseases; other situations that not suitable for participating in clinical trial.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: App group; Participants will be assisted to use the app during the process of management, and be followed-up at the scheduled time points including 2 weeks, 4 weeks, 8 weeks, 12 weeks, 6 months and 12 months after treatment, and the evaluation of five treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI should be done on the day of follow-up.	Behavioral: Artificial Intelligence assistant decision-making system (AIADMS) App; Participants will be assisted to use the Artificial Intelligence assistant decision-making system (AIADMS) app during the process of management of AD, and be followed-up at the scheduled time points including 2 weeks, 4 weeks, 8 weeks, 12 weeks, 6 months and 12 months after treatment, and the evaluation of five treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI should be done on the day of follow-up.
No Intervention: Control group; The diagnosis, treatment, and follow-up of participants will be carried out according to the current routine on face-to-face basis. The time points of the participants follow-up will be determined by the responsible dermatologist, and the evaluation of five treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI will be done and recorded on the day of follow-up.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The overall efficiency rate of treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI at 12 weeks after treatment	The overall efficiency is calculated as "Total number of participants with effective treatment of 5 treating objectives / total number of participants *100%". Criteria for effective treatment are as below: ① PP-NRS absolutely score ≤4, ② EASI -50, EASI -75, or EASI≤7, ③ SCORAD-50, SCORAD-75, or SCORAD ≤24, ④ POEM absolutely score ≤7, ⑤ DLQI absolutely score ≤5.	12 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The seperated efficiency rate of treating objectives including PP-NRS, EASI, SCORAD, POEM, and DLQI	The seperated efficiency rate of treating objectives is calculated as "Total number of participants with effective treatment of 5 treating objectives / total number of participants *100%".	12 months
The economic consumption	The economic consumption will include the travel expenses, expenses with lost working days, accommodation expenses, medical expenses, etc	12 months
Satisfaction evaluation	On completion of the study, participants in the App group of the study and healthcare providers will complete respective questionnaires about their use of and satisfaction with the app. Analysis of the satisfaction will be performed collection of the questionnaires.	12 months

Collaborators and Investigators

• Sponsor: West China Hospital
• Investigators: Principal Investigator: Jingyi Li, M.D., West China hospital

Study record dates

Study Major Dates

• Study Start (Estimated): September 1, 2024
• Primary Completion (Estimated): December 31, 2028
• Study Completion (Estimated): August 31, 2029

Study Registration Dates

• First Submitted: April 8, 2024
• First Submitted That Met QC Criteria: April 8, 2024
• First Posted (Actual): April 12, 2024

Study Record Updates

• Last Update Posted (Actual): April 12, 2024
• Last Update Submitted That Met QC Criteria: April 8, 2024
• Last Verified: April 1, 2024

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Atopic dermatitis; app; Treat to Target (T2T) strategy
• Additional Relevant MeSH Terms: Skin Diseases; Immune System Diseases; Hypersensitivity, Immediate; Genetic Diseases, Inborn; Skin Diseases, Genetic; Hypersensitivity; Skin Diseases, Eczematous; Dermatitis; Eczema; Dermatitis, Atopic
• Other Study ID Numbers: WCH240407

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No