From Pixels to Patients: How AI Is Reshaping Dermatology
Artificial intelligence (AI) has sprinted from sci-fi concept to daily clinical companion. Broadly,
AI refers to computers trained to mimic human reasoning. 1 Generative AI, such as GPT models,
takes a creative leap by producing novel text, images, or audio from patterns it has already
learned.
Medicine, by contrast, is notorious for slow adoption: 75 % of the world’s fax traffic still runs
through health-care systems, and a typical breakthrough languishes 17 years before becoming
routine practice. 2,3 AI could compress that timeline. A 2024 meta-analysis of 12 studies showed
clinicians diagnosing skin cancer with AI support reached 81.1 % sensitivity and 86.1 %
specificity, versus 74.8 % and 81.5 % when working alone; an accuracy boost seen across all
levels of training. 4
Can we work smarter, not harder? When ChatGPT rewrote 12 hypothetical dermatopathology
reports into plain English, 30 physicians judged the translations accurate, understandable, and
unlikely to harm patients. 5 Also, clinical work is complex; for every 8 hours of patient care, we
spend 5 hours on the electronic health record. Ambient AI “scribes” that transcribe clinic visits
now save clinicians about 1 hour of keyboard time per day. 6
Excitement has spurred a flood of mobile tools, yet quality is inconsistent and ethical hurdles
persist. Many dermatology apps do not cite peer-reviewed evidence and do not involve a
dermatologist during development, and many offer no details on validation or privacy
safeguards. Also, many training datasets still skew toward lighter skin tones, leaving skin-of-
color images underrepresented. Rigorous real-world validation and strict privacy protections are
essential before widescale deployment.
Good news! AI is not here to replace us (yet). If used correctly, it can ease administrative
burdens, sharpen diagnostic vision and make practice more efficient. The future of dermatology
lies at the intersection of technology and human expertise. With responsible implementation, AI
can become a powerful ally in the pursuit of more accurate, efficient, and equitable care—and
may finally retire the fax machine once and for all.
References:
1. Sheikh, H., Prins, C., Schrijvers, E. (2023). Artificial Intelligence: Definition and
Background. In: Mission AI. Research for Policy. Springer, Cham.
2. Global Fax Machine Usage Statistics Revealed: Prevalence and Market Trends. Gintux.
https://gitnux.org/fax-machine-usage-statistics/ Updated July 14, 2024. Accessed August
17,2024.
3. Morris Z, Wooding S, Grant J. The answer is 17 years, what is the question:
understanding time lags in translational research. J R Soc Med. 2011;104(12):510-520.
4. Krakowski I, Kim J, Cai ZR, Daneshjou R, Lapins J, Eriksson H, Lykou A, Linos E.
Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis.
NPJ Digit Med. 2024 Apr 9;7(1):78.
5. Zhang Y, Chen R, Nguyen D, Choi S, Gabel C, Leonard N, Yim K, O'Donnell P, Elaba Z,
Deng A, Levin NA. Assessing the ability of an artificial intelligence chatbot to translate
dermatopathology reports into patient-friendly language: A cross-sectional study. J Am
Acad Dermatol. 2024 Feb;90(2):397-399.
6. Ma SP, Liang AS, Shah SJ, Smith M, Jeong Y, Devon-Sand A, Crowell T, Delahaie C,
Hsia C, Lin S, Shanafelt T, Pfeffer MA, Sharp C, Garcia P. Ambient artificial intelligence
scribes: utilization and impact on documentation time. J Am Med Inform Assoc. 2025
Feb 1;32(2):381-385.
Eileen Cheever, MPAS, PA-C, resides with family in Massachusetts. She works at Clearview
Dermatology in Leominster, Massachusetts. She enjoys cheering on her favorite Boston sports
teams and exploring the outdoors with her family.