Background: With rising incidence of skin cancer and relatively increased mortality rates, an improved diagnosis of such a potentially fatal disease is of vital importance. Although frequently curable, it nevertheless places a considerable burden upon healthcare systems. Among the various types of skin cancers, non-melanoma skin cancer is most prevalent. Despite such prevalence and its associated cost, scant proof concerning the diagnostic accuracy via Artificial Intelligence (AI) for non-melanoma skin cancer exists. This study meta-analyzes the diagnostic test accuracy of AI used to diagnose non-melanoma forms of skin cancer, and it identifies potential covariates that account for heterogeneity between extant studies.
Methods: Various electronic databases (Scopus, PubMed, ScienceDirect, SpringerLink, and Dimensions) were examined to discern eligible studies beginning from March 2022. Those AI studies predictive of non-melanoma skin cancer were included. Summary estimates of sensitivity, specificity, and area under receiver operating characteristic curves were used to evaluate diagnostic accuracy. The revised Quality Assessment of Diagnostic Studies served to assess any risk of bias.
Results: A literature search produced 39 eligible articles for meta-analysis. The summary sensitivity, specificity, and area under receiver operating characteristic curve of AI for diagnosing non-melanoma skin cancer was 0.78, 0.98, & 0.97, respectively. Skin cancer typology, data sources, cross validation, ensemble models, types of techniques, pre-trained models, and image augmentation became significant covariates accounting for heterogeneity in terms of both sensitivity and/or specificity.
Conclusions: Meta-analysis results revealed that AI is predictive of non-melanoma with an acceptable performance, but sensitivity may become improved. Further, ensemble models and pre-trained models are employable to improve true positive rating.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10375663 | PMC |
| http://dx.doi.org/10.1186/s12911-023-02229-w | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Surgical management of endometrial cancer in patient with musculocontractural Ehlers-Danlos Syndrome harboring pathogenic variants in CHST14 (mcEDS-CHST14): A case report.
Gynecol Oncol Rep
February 2025
Department of Obstetrics and Gynecology, Shinshu University School of Medicine, 3-1-1 Asahi, Matsumoto, Nagano 390-8621, Japan.
Introduction: Musculocontractural Ehlers-Danlos syndrome (mcEDS) is a rare autosomal recessive connective tissue disorder caused by systemic depletion of dermatan sulfate. Symptoms characteristic of mcEDS include multiple contractures, fragile skin with subcutaneous bleeding, and hypermobile joints, which suggest difficulty in perioperative management. However, safe surgical techniques and perioperative management of this disorder remain unknown because of its rarity.
View Article and Find Full Text PDFEfficacy of Transcutaneous Electrical Acupoint Stimulation on Modulating Upper Extremity Sympathetic Skin Response in Alleviating Cancer Survivors With Chemotherapy-Induced Peripheral Neuropathy: A Propensity Score-Matched Cohort Study.
J Pain Res
January 2025
Department of Pain Management Center, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, People's Republic of China.
Objective: Chemotherapy-induced peripheral neuropathy (CIPN) is a common side effect of chemotherapy and it is currently intractable We compared the efficacy of transcutaneous electrical acupoint stimulation (TEAS) against non-TEAS groups and investigated the variables that predict effective relief of upper extremity pain in cancer survivors with CIPN.
Methods: We retrospectively collected data of cancer survivors who developed CIPN between May 2017 to March 2022. All eligible CIPN patients were divided into TEAS group (received TEAS) and non-TEAS group (did not receive TEAS) in our department.
Editorial: Key players of the immune system in skin inflammation-allergy and autoimmunity.
Front Allergy
January 2025
Division of Allergy and Clinical Immunology, School of Medicine, University of Virginia, Charlottesville, VA, United States.
A Multifunctional MIL-101-NH(Fe) Nanoplatform for Synergistic Melanoma Therapy.
Int J Nanomedicine
January 2025
Department of Pharmacy, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan, 646000, People's Republic of China.
Background: Melanoma is an aggressive form of skin cancer, and single-modality treatments often fail to prevent tumor recurrence and metastasis. Combination therapy has emerged as an effective approach to improve treatment outcomes.
Methods: In this study, we developed a multifunctional nanoplatform, MIL@DOX@ICG, utilizing MIL-101-NH(Fe) as a carrier to co-deliver the chemotherapeutic agent doxorubicin (DOX) and the photosensitizer indocyanine green (ICG).
We examined the risk of subsequent malignant neoplasms (SMNs) in 1720 patients with hematologic cancers given allogeneic hematopoietic grafts from 03/1998 to 08/2023 after nonmyeloablative conditioning regimens. With a median follow-up of 12 years, the cumulative incidence of SMNs was 17% (95% CI, [15%, 19%]). Most SMNs (n = 543) were non-melanoma skin cancers seen in 208 patients; unfortunately, information on these cancers was not available in the Surveillance, Epidemiology, and End Results (SEER) database for comparison with such tumors in the general population.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!