The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Diagnosing Actinic Keratosis and Squamous Cell Carcinoma With Large Language Models From Clinical Images
Open accessAbstract
Actinic keratosis (AK) is a common ultraviolet (UV)-inducedprecancerous skin lesion that may progress to squamous cellcarcinoma (SCC), a potentially invasive malignancy [1, 2].Clinically differentiating between AK and SCC is challengingdue to overlapping features [3]. With the rise of accessible mul-timodal large language models (LLMs), patients now have ar-tificial intelligence (AI) tools such as ChatGPT to assess theirskin lesions at home. However, the diagnostic reliability of thesemodels in distinguishing AK from SCC remains unclear. Thisstudy evaluates and compares two advanced LLMs in identify-ing and differentiating between AK and SCC using real-worldclinical images
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In actinic keratosis vs. squamous cell carcinoma (112 patients), ChatGPT-4o again outperformed Gemini in accuracy and sensitivity, but both models had low negative predictive value, meaning malignant cases could still be missed despite "negative" outputs.
“In actinic keratosis vs. squamous cell carcinoma (112 patients), ChatGPT-4o again outperformed Gemini in accuracy and sensitivity, but both models had low negative predictive value, meaning malignant cases could still be missed despite “negative” outputs [69].”
From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [69]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Clinical presentation of actinic keratoses and squamous cell carcinoma
Moy, R. L. (2000) · Journal of the American Academy of Dermatology · doi:10.1067/mjd.2000.103343 · Cited by 222
Actinic keratosis – review for clinical practice
de Oliveira, E. C. V., Motta, V. R. V. D. [., Pantoja, P. P. P., Ilha, C. S. D. O., Magalhães, R. F., Galadari, H., & Leonardi, G. R. (2018) · International Journal of Dermatology · doi:10.1111/ijd.14147 · Cited by 99
Diagnostic Performance of GPT ‐4o and Gemini Flash 2.0 in Acne and Rosacea
Boostani, M., Bánvölgyi, A., Goldust, M., Cantisani, C., Pietkiewicz, P., Lőrincz, K. K., Holló, P., Wikonkál, N. M., Paragh, G., & Kiss, N. (2025) · International Journal of Dermatology · doi:10.1111/ijd.17729 · Cited by 47
Self-citationLarge language models in evaluating hidradenitis suppurativa from clinical images
Boostani, M., Bánvölgyi, A., Zouboulis, C. C., Goldfarb, N. I., Suppa, M., Goldust, M., Lőrincz, K. K., Kiss, T., Nádudvari, N., Holló, P., et al. (2025) · Journal of the European Academy of Dermatology and Venereology · doi:10.1111/jdv.20861 · Cited by 35
Self-citationSurgical therapy of cutaneous squamous cell carcinoma: our experience.
Simonacci, F., Bertozzi, N., Grieco, M. P., Grignaffini, E., & Raposio, E. (2018) · Acta bio-medica dell'Ateneo parmense/Acta biomedica · doi:10.23750/abm.v89i2.6189 · Cited by 11
Flagged first, then by citations
Cited by
Sorted by citations
Cantisani, C., Guardo, A. D., Paolino, G., Balázs, N., Boostani, M., Kiss, N., Conforti, C., Feresin, F., Carugno, A., Gargano, L., et al. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15020612 · Cited by 5
Self-citationEvidence Synthesis of Artificial Intelligence Performance in Skin Cancer Diagnosis
Kiss, N., & Boostani, M. (2025) · International Journal of Dermatology · doi:10.1111/ijd.70148 · Cited by 2
Self-citationKerekes, K., Boostani, M., Metyovinyi, Z., Kiss, N., & Medvecz, M. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15020475 · Cited by 2
Self-citationBoostani, M., Gisondi, P., Bellinato, F., Kiss, T., Zouboulis, C. C., Kuraitis, D., Goldfarb, N. I., Nádudvari, N., Farabi, B., Hodosi, B., et al. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1791488 · Cited by 2
Self-citationSzondy, I., Martyin, K., Mohos, G., Kiss, T., Szabo, K., Boostani, M., Goldust, M., Grzybowski, A. E., Bánvölgyi, A., & Kiss, N. (2026) · La Presse Médicale · doi:10.1016/j.lpm.2026.104376 · Cited by 2
Self-citationArtificial Intelligence in Dermatopathology: An Update and Review of the Current Literature
Abu-Dayeh, A., Cazzato, G., & Giubellino, A. (2026) · Diagnostics · doi:10.3390/diagnostics16111702 · Cited by 1
Gualdi, G., Soligon, G., Silvetti, P., Balestra, L., Bertolla, D., Fania, L., Ricci, F., Puviani, M., Sbano, P., & Paradisi, A. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15124553 · Cited by 1
Actinic keratosis staging in multimodal image data
Slian, A., Korecka, K., Polańska, A., & Czajkowska, J. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109364
Liu, J., Ma, X., Qian, Y. P., Wang, J., Zhu, C., & Ma, D. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15093504
Bhatty, M. A., Chakraborty, N. N., Zablonski, K. G., Boone, J. M., Seibert, H., Lal, T., Kakish, H. H., Stevens, M. N., Sheng, I. Y. F., Hanna, A. N., et al. (2026) · Cancers · doi:10.3390/cancers18121893
Bortone, G., Coppolelli, V., Gargano, L., Svara, F., Boostani, M., Nisticò, S. P., Pellacani, G., & Cantisani, C. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1895820
Self-citationImplementation of Total Body Photography for Skin Cancer Early Detection: A Systematic Review
Hussain, N. A. B., Ansah‐Sasraku, F. A., Fernández‐Peñas, P., Gillespie, N. A., Soyer, H. P., Hickman, I. J., & Janda, M. (2026) · International Journal of Dermatology · doi:10.1111/ijd.70679
García, A., Reis, I. V. D., Liébana‐Presa, C., Díaz, E. A., Bermejo‐Martínez, D., & Pérez‐González, S. (2026) · Healthcare · doi:10.3390/healthcare14213587
Metadata
- Authors
- Boostani, M., Pellacani, G., Goldust, M., Nádudvari, N., Rátky, D., Cantisani, C., Lőrincz, K., Bánvölgyi, A., Wikonkál, N. M., Paragh, G., & Kiss, N.
- Affiliations
- Semmelweis University (HU)
- Sapienza University of Rome (IT)
- Yale University (US)
- Department of Dermatology Roswell Park Comprehensive Cancer Center Buffalo New York USA
- Corresponding author
- Kiss, Norbert
- ORCID
- Venue
- International Journal of Dermatology
- Publisher
- Wiley
- Published
- 2025-07-31
- Volume
- 65
- Issue
- 6
- Pages
- 1246-1248
- ISSN
- 0011-9059 (ISSN-L)
- 1365-4632
- OpenAlex
- W4412783689
- Cited by
- 13
- References
- 5
- Citations by year
- 2026: 12 · 2025: 1
- FWCI
- 8.93
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International Journal of Dermatology (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by-nc)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- Topics
- Health Sciences › Medicine › Dermatology › Nonmelanoma Skin Cancer Studies
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Keywords
- actinic keratosis, squamous cell carcinoma, large language models, skin lesion diagnosis, ChatGPT, clinical photographs, precancerous skin lesions, diagnostic reliability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
