TY - GEN
T1 - Longitudinal Treatment-Aware Multimodal AI for Dermatology
T2 - 24th International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2026
AU - Sheikh, Ahmed
AU - Househ, Mowafa
N1 - Publisher Copyright:
© 2026 The Authors.
PY - 2026/6/29
Y1 - 2026/6/29
N2 - The field of dermatological AI has rapidly advanced from simple single-image classifiers to large, multimodal foundation models. Despite achieving high diagnostic accuracy, current systems mostly analyze a single point in time and do not incorporate patient history or previous treatments. This review explores the evidence for longitudinal, treatment-aware, and multimodal large language model (LLM) approaches in dermatology, with an emphasis on chronic inflammatory conditions such as eczema, acne, psoriasis, and rosacea. Researchers examined five databases, PubMed, ACM, IEEE Xplore, Web of Science, and Scopus, covering studies from 2020 to 2026. Using PRISMA-ScR guidelines, 30 studies were selected from 1,644 citations. The review identifies five key themes: (1) shift from static to longitudinal AI; (2) multimodal vision-language integration; (3) treatment-aware decision support systems; (4) temporal reasoning capabilities; and (5) benchmarks and evaluation methods. Currently, no models combine longitudinal imaging, medication logs, and LLM reasoning specifically for chronic inflammatory skin diseases. This review highlights five major research gaps and calls for longitudinal, treatment-annotated benchmarks to advance progress in the field.
AB - The field of dermatological AI has rapidly advanced from simple single-image classifiers to large, multimodal foundation models. Despite achieving high diagnostic accuracy, current systems mostly analyze a single point in time and do not incorporate patient history or previous treatments. This review explores the evidence for longitudinal, treatment-aware, and multimodal large language model (LLM) approaches in dermatology, with an emphasis on chronic inflammatory conditions such as eczema, acne, psoriasis, and rosacea. Researchers examined five databases, PubMed, ACM, IEEE Xplore, Web of Science, and Scopus, covering studies from 2020 to 2026. Using PRISMA-ScR guidelines, 30 studies were selected from 1,644 citations. The review identifies five key themes: (1) shift from static to longitudinal AI; (2) multimodal vision-language integration; (3) treatment-aware decision support systems; (4) temporal reasoning capabilities; and (5) benchmarks and evaluation methods. Currently, no models combine longitudinal imaging, medication logs, and LLM reasoning specifically for chronic inflammatory skin diseases. This review highlights five major research gaps and calls for longitudinal, treatment-annotated benchmarks to advance progress in the field.
KW - Dermatology
KW - Longitudinal AI
KW - Multimodal Large Language Models
KW - Temporal Reasoning
KW - Treatment-Aware AI
UR - https://www.scopus.com/pages/publications/105045182768
U2 - 10.3233/SHTI260949
DO - 10.3233/SHTI260949
M3 - Conference contribution
C2 - 42394111
AN - SCOPUS:105045182768
T3 - Studies in Health Technology and Informatics
SP - 763
EP - 767
BT - Health Sciences Informatics Leads and Empowers the Digital Health Transformation - 24th International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2026
A2 - Mantas, John
A2 - Hasman, Arie
A2 - Gallos, Parisis
A2 - Haux, Reinhold
A2 - Karitis, Konstantinos
PB - IOS Press BV
Y2 - 3 July 2026 through 5 July 2026
ER -