About

Albert C. Yan, MD, FAAP, FAAD, is a Professor of Pediatrics (General Pediatrics) at the Children's Hospital of Philadelphia. He serves as an Attending Physician in Pediatrics with a specialization in Dermatology at the Hospital of the University of Pennsylvania. Dr. Yan is also the Research Director at the Children's Hospital of Philadelphia, Section of Dermatology, Division of General Pediatrics. His clinical expertise includes pediatric dermatology conditions such as acne vulgaris, atopic dermatitis, genodermatoses, hemangiomas and vascular anomalies, neonatal dermatology, and skin infections including warts, molluscum, tinea, and MRSA. His research focuses on various dermatological issues affecting children, including acne, atopic dermatitis, rare skin diseases, and computer vision applications in dermatology. Dr. Yan has contributed to numerous studies and publications in his field, advancing understanding and treatment of pediatric dermatological conditions.

Research topics

• Dermatology
• Medicine
• Immunology
• Environmental health
• Medical physics
• Internal medicine
• Pathology
• Pediatrics

Selected publications

• Generative Artificial Intelligence Tools: Evaluating Ways to Automate Your SALT (GATEWAYS) Scoring of Alopecia Areata

  Journal of Investigative Dermatology · 2026-03-01

  articleOpen accessSenior author
  PublisherOA PDFDOI

• Pediatric Skin Disease Frequencies and Dermatology Use by Race and Ethnicity in US Children’s Hospitals

  JAMA Dermatology · 2026-05-06

  articleOpen access

  Importance: Understanding which children present with skin disease and reach specialty care is essential for characterizing patterns of disease frequency and care use. Objective: To describe the frequencies of common pediatric skin diseases and patterns of dermatology use, stratified by race and ethnicity, across 8 US children's hospitals participating in the PEDSnet system. Design, Setting, and Participants: This was a multicenter cross-sectional study of 8 US children's hospitals in PEDSnet from January 2009 to July 2022. Data were analyzed from January 3 to March 26, 2024. The study cohort included children with 1 or more dermatology clinic visit or 2 or more non-dermatology clinic visits coded for atopic dermatitis (AD), acne, infantile hemangioma, psoriasis, or hidradenitis suppurativa (HS). Main Outcomes and Measures: Disease frequency per 100 000 children and proportion of children using dermatology care for each condition, stratified by race and ethnicity. Results: Of 536 776 patients, the mean (SD) age was 6.4 (6.3) years, 51.5% were female, and 0.2% were American Indian or Alaska Native, 6.4% Asian, 27.9% Black, 14.1% Hispanic, 0.3% Native Hawaiian or Other Pacific Islander, 8.4% non-Hispanic, 44.3% White, 4.3% multiple races, 5.5% unknown ethnicity, and 16.6% unknown race. Case counts were 377 970 for AD, 139 632 for acne, 54 305 for infantile hemangioma, 11 339 for psoriasis, and 5722 for HS. Electronic health record-derived frequencies varied across race and ethnicity groups. There were 10 469 (95% CI, 10 414-10 524) cases of AD per 100 000 Black children compared with 3099 (95% CI, 3083-3114) per 100 000 White children. There were 290 (95% CI, 280-300) cases of infantile hemangioma per 100 000 Black children compared with 764 (95% CI, 756-772) per 100 000 White children. Black children had a low proportion of dermatology use across all 5 conditions, yet high frequencies of AD, acne, and HS. Conclusions and Relevance: In this study, across all studied conditions, Black children had a low proportion of dermatology use at participating PEDSnet US children's hospitals, despite having high frequencies of AD, acne, and HS. Further research is required to determine whether these patterns represent appropriate specialty care use or reflect gaps in care.

  PublisherOA PDFDOI

• Generative Artificial Intelligence Tools: Evaluating Ways to Automate Your <scp>SALT</scp> ( <scp>GATEWAYS</scp> ) Scoring of Alopecia Areata

  Pediatric Dermatology · 2026-03-09

  articleOpen accessSenior authorCorresponding

  BACKGROUND: Alopecia areata (AA) is an autoimmune disease affecting hair follicles that results in nonscarring hair loss. AA impacts 0.1%-0.2% of the United States population, with pediatric patients accounting for 16.0%-27.7% of all cases. The Severity of Alopecia Tool (SALT), a method of quantifying scalp alopecia, helps guide clinical practice and determine response to therapies in clinical trials. Given the emerging role of image-based assessments of alopecia and growth of multimodal generative artificial intelligence (AI) in dermatology, we aimed to assess the "off-the-shelf" ability of a large-language model, GPT-4o, to automate the generation of image-based SALT scores. METHODS: Chart review of patients with AA seen at the Children's Hospital of Philadelphia's Dermatology Clinic was conducted to identify 4-view images of patients' scalps and provider-derived SALT scores. One-hundred-and-four 4-view image sets were de-identified and provided to GPT-4o, which was prompted to generate SALT scores. Concordance between GPT-4o's and providers' scores was determined using intraclass correlation coefficients (ICC) and concordance correlation coefficients (CCC). RESULTS: ICC and CCC between GPT-4o and in-person provider assessments were 0.815 and 0.866. ICC and CCC between GPT-4o and image-based provider assessments were 0.833 and 0.817. ICC and CCC between two providers were 0.950 and 0.948. These high levels of concordance were confirmed on Bland-Altman plots. CONCLUSIONS: SALT scoring for AA can be challenging due to provider subjectivity, changing sphericity and growth of patients' scalps, particularly among pediatric patients. Our data show the potential adjunct role that "off-the-shelf" generative AI tools may play in SALT scoring without any prior additional explicit training.

  PublisherDOI

• Vascular Anomalies: Satisfaction with Response of Cutaneous Ulcerated Hemangiomas Following Laser (VASCULAR) — Variation by Anatomic Site

  Journal of Investigative Dermatology · 2026-03-01

  articleSenior author
  PublisherDOI

• Automated acne lesion counting from subpar images via memory classifiers

  Archives of Dermatological Research · 2026-01-30

  articleOpen access

  Quantifying acne lesions from photographs is an essential component of acne evaluation. Algorithms are available to automate this process, but they can be easily disrupted by common image noise such as blur or illumination issues. We propose a new automated acne lesions classification method that is capable of withstanding common image corruptions by adapting the memory classifier technique and introducing new expert-defined acne visual features to characterize acne lesions. We then integrate the memory classification algorithm into an end-to-end framework to automatically detect lesions, classify them, and assign an acne severity grade from an image of acne-affected skin. On a dataset consisting of 4658 primary lesions (comedones, papules/pustules, and nodules) taken from 140 lateral facial images from a retrospective de-identified cohort of 63 pediatric and 35 adult patients, the proposed method achieved 87.58% overall classification accuracy. Its performance was similar after adding common noise perturbations to the images. Embedding the classification algorithm within an end-to-end framework to count lesions and grade acne severity from an input image resulted in a mean square error of 0.99 for overall acne severity (against the clinicians’ baseline on an 8-pt severity scale). The results show that the proposed algorithm is both accurate in classifying acne lesion types and capable of withstanding noise perturbations in images. Furthermore, they demonstrate its potential use for automating lesion counting and acne severity grading in research and clinical settings.

  PublisherOA PDFDOI

• Evaluating Novel Diagnostic Generative AI for Models for Evaluation (ENDGAME) of Pediatric Alopecia: A Comparative Study of Scarring and Non-Scarring Types

  Journal of Investigative Dermatology · 2026-03-01

  article
  PublisherDOI

• Multi-center study of long-term evolution of neuroimaging findings in PHACE syndrome

  European Journal of Paediatric Neurology · 2026-02-07

  article
  PublisherDOI

• Leg Length Discrepancy in Patients With Lower Extremity Cutis Marmorata Telangiectatica Congenita: A Multicenter Retrospective Study

  Pediatric Dermatology · 2026-02-18 · 1 citations

  articleOpen access

  OBJECTIVES: To assess the frequency of leg length discrepancy (LLD) in patients with lower extremity cutis marmorata telangiectatica congenita (CMTC), describe associated findings, and characterize LLD management. METHODS: We conducted a retrospective chart review of patients diagnosed with lower extremity CMTC by dermatology and evaluated by orthopedics at Boston Children's Hospital and Children's Hospital of Philadelphia from 1997 to 2024. LLD was assessed by orthopedic examination and/or radiographic imaging. Major LLD was defined as ≥ 2 cm at any age, or between 1 and 2 cm in children 4 years old or younger. Mild LLD was defined as < 2 cm, except when ≥ 1 cm was present by age 4. Kaplan-Meier analysis estimated the probability of developing major LLD by age 15. RESULTS: Twenty-eight patients with lower extremity CMTC were included. LLD was identified in 12 of 28 patients (43%), including 8 confirmed radiographically and 4 diagnosed by clinical assessment alone. Two (7%) were classified as major and 10 (36%) as mild. Limb hypoplasia occurred in 18 of 28 patients (64%). Kaplan-Meier analysis estimated a 7.1% cumulative risk of major LLD by age 15. Three of 12 patients (25%) with LLD were prescribed shoe lifts. CONCLUSION: LLD is common among patients with lower extremity CMTC. Early orthopedic assessment may facilitate timely intervention.

  PublisherOA PDFDOI

• Reply to “Comment on ‘Digitizing Diagnoses: Distinguishing Infantile Hemangiomas From Other Vascular Anomalies’”

  Pediatric Dermatology · 2026-02-06

  articleSenior author

  We very much appreciate the comment and thank you for drawing our attention to this terminological clarification. We would like to acknowledge the discrepancy in our original article and clarify that the model utilized in our study was GPT-4 and not GPT-4o (omni) which was released after our study was completed. We greatly appreciate this attention to detail and agree with the importance of precise terminology to ensure methodological clarity for future reproducibility. Thank you again for this astute comment [1, 2]. The authors have nothing to report. The authors declare no conflicts of interest. Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.

  PublisherDOI

• Characteristics of youth utilizing pediatric dermatology: A cross-sectional PEDSnet study

  Journal of the American Academy of Dermatology · 2025-11-05 · 1 citations

  article
  PublisherDOI

Frequent coauthors

• Paul J. Honig

  University of Pennsylvania

  96 shared

• James R. Treat

  Children's Hospital of Philadelphia

  51 shared

• Warren R. Heymann

  Cooper Medical School of Rowan University

  51 shared

• Aimee Payne

  University of Pennsylvania

  51 shared

• Bruce Pawel

  50 shared

• Terri L. Young

  University of Wisconsin–Madison

  49 shared

• Weijie Li

  Fujian Institute of Oceanography

  49 shared

• Sonia Imaizumi

  Johnson University

  49 shared

Education

• B.A.

  Princeton University

  1989

• M.D.

  University of Pennsylvania School of Medicine

  1993