Development of AI-Based Skincare Strategies for Atopic Dermatitis: Focusing on Erythema Index Severity Levels

Atopic dermatitis (AD) is a chronic skin condition characterized by inflammation that is often influenced by emotional stress and environmental factors. The underlying mechanisms of AD are multifactorial and not yet fully understood. Previous treatments have focused on alleviating acute symptoms, paying little attention to skin care or other lifestyle management approaches. This study proposes a customized skin care strategy using ChatGPT, a generative AI tool based on the erythema index obtained from the CK-MPA skin measurement device. The erythema index is classified into three levels: mild (300–400), moderate (400–500), and severe (500–600). Two prompt frameworks, R-I-S-E (Role–Input–Steps–Expectation) and R-T-F (Role–Task–Format), were applied through ChatGPT to derive management strategies for each level. The R-I-S-E framework is suitable for presenting structured, step-by-step management plans and can be used to design educational and clinical protocols. In contrast, the R-T-F framework provided simple, practical guidelines for patients or caregivers. The results showed that the two frameworks had distinct differences in scope, specificity, and target audience depending on the severity of atopic dermatitis (AD). It was confirmed that ChatGPT can generate consistent, customized, and contextually appropriate strategies based on clearly designed prompts. To ensure objectivity, the prompts were constructed using literature-based keywords related to skincare and environmental management, and their consistency was verified through multiple runs in isolated AI sessions. The most applicable results were selected through expert review by dermatology and aesthetics professionals. However, due to the prompt-driven nature of generative AI, a certain level of domain expertise is required for effective prompt design and interpretation of results. This highlights both the potential and limitations of AI-assisted strategy development in clinical and educational settings.

Authors

Institutions

Publication Details

Journal
Journal of the Korean Society of Cosmetology
Published
2025-08-28
DOI
https://doi.org/10.52660/jksc.2025.31.4.810
Primary Topic
Consumer Perception and Purchasing Behavior
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Development of AI-Based Skincare Strategies for Atopic Dermatitis: Focusing on Erythema Index Severity Levels

D. Song
Journal of the Korean Society of Cosmetology
Consumer Perception and Purchasing Behavior
article

Development of AI-Based Skincare Strategies for Atopic Dermatitis: Focusing on Erythema Index Severity Levels

D. Song
article en

Abstract

Atopic dermatitis (AD) is a chronic skin condition characterized by inflammation that is often influenced by emotional stress and environmental factors. The underlying mechanisms of AD are multifactorial and not yet fully understood. Previous treatments have focused on alleviating acute symptoms, paying little attention to skin care or other lifestyle management approaches. This study proposes a customized skin care strategy using ChatGPT, a generative AI tool based on the erythema index obtained from the CK-MPA skin measurement device. The erythema index is classified into three levels: mild (300–400), moderate (400–500), and severe (500–600). Two prompt frameworks, R-I-S-E (Role–Input–Steps–Expectation) and R-T-F (Role–Task–Format), were applied through ChatGPT to derive management strategies for each level. The R-I-S-E framework is suitable for presenting structured, step-by-step management plans and can be used to design educational and clinical protocols. In contrast, the R-T-F framework provided simple, practical guidelines for patients or caregivers. The results showed that the two frameworks had distinct differences in scope, specificity, and target audience depending on the severity of atopic dermatitis (AD). It was confirmed that ChatGPT can generate consistent, customized, and contextually appropriate strategies based on clearly designed prompts. To ensure objectivity, the prompts were constructed using literature-based keywords related to skincare and environmental management, and their consistency was verified through multiple runs in isolated AI sessions. The most applicable results were selected through expert review by dermatology and aesthetics professionals. However, due to the prompt-driven nature of generative AI, a certain level of domain expertise is required for effective prompt design and interpretation of results. This highlights both the potential and limitations of AI-assisted strategy development in clinical and educational settings.

Journal of the Korean Society of CosmetologyVol. 31(4)
Kyung Hee University Medical Center (KR)
Openalex Percentile: Top 70%
Consumer Perception and Purchasing Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.