A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis.

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.

Management of periocular keratinocyte carcinomas with Mohs micrographic surgery and predictors of complex reconstruction: a retrospective study.

BACKGROUND: Skin cancer is the most frequent cancer worldwide and the most frequent periocular tumor. Keratinocyte Carcinomas (KC) located in periorificial areas, such as periocular tumors, are considered high-risk tumors. Mohs Micrographic Surgery (MMS) is considered the first line for the treatment of high-risk KC, providing a lower recurrence rate than conventional wide excision. OBJECTIVE: To describe the clinical-pathological features of periocular KC treated with MMS in a tertiary university center in Chile. METHODS: A single-center, retrospective study of patients with KC located on the periocular area, that underwent MMS between 2017‒2022. MMS details were recorded. RESULTS: One hundred thirteen patients with periocular carcinomas were included. The mean age was 59 ± 13 years; 52% were women. The most frequent location was the medial canthus (53%), followed by the lower eyelid (30.1%). The most frequent BCC histology was the nodular variant (59.3%). Regarding MMS, the average number of stages was 1.5 ± 0.7, and 54% of the cases required only 1 stage to achieve clear margins. To date, no recurrence has been reported. Tumors larger than 8.5 mm in largest diameter or 43.5 mm2 were more likely to require complex reconstruction. STUDY LIMITATIONS: Retrospective design and a relatively low number of patients in the SCC group. Possible selection bias, as larger or more complex cases, may have been referred to oculoplastic surgeons directly. CONCLUSION: The present study confirms the role of MMS for the treatment of periocular KCs. Periocular KCs larger than 8.5 mm might require complex reconstruction. These results can be used to counsel patients during pre-surgical visits.

Patterns of Recurrence of Cutaneous Melanoma: A Literature Review.

The incidence of melanoma has been dramatically increasing over the last decades. Melanoma is considered to have a high metastatic potential and it can progress via lymphatic vessels or through hematogenous metastasis. Different patterns of recurrence have been described, namely, local, satellite, and in transit metastasis (LCIT), lymphatic metastasis, and systemic metastasis. With a more advanced melanoma stage at diagnosis, there is a higher risk for systemic metastasis in comparison to LCIT; in contrast, early-stage melanoma tends to recur more frequently as LCIT and less commonly as systematic metastasis. The aim of this review was to summarize the patterns of recurrence of cuta-neous melanoma, giving the clinician a practical summary for diagnosis, prognosis, and surveillance. There is a knowledge gap of the common patterns of recurrence that needs to be addressed to better identify patients at high risk of disease recurrence and personalize surveillance strategies as well as patient counseling.

Complementary and alternative therapies in skin cancer a literature review of biologically active compounds.

Complementary and alternative medicine or therapies (CAM) are frequently used by skin cancers patients. Patient's self-administration of CAM in melanoma can reach up to 40%-50%. CAMs such as botanical agents, phytochemicals, herbal formulas ("black salve") and cannabinoids, among others, have been described in skin cancer patients. The objective of this review article was to acknowledge the different CAM for skin cancers through the current evidence, focusing on biologically active CAM rather than mind-body approaches. We searched MEDLINE database for articles published through July 2022, regardless of study design. Of all CAMs, phytochemicals have the best in vitro evidence-supporting efficacy against skin cancer including melanoma; however, to date, none have proved efficacy on human patients. Of the phytochemicals, Curcumin is the most widely studied. Several findings support Curcumin efficacy in vitro through various molecular pathways, although most studies are in the preliminary phase. In addition, the use of alternative therapies is not exempt of risks physicians should be aware of their adverse effects, interactions with standard treatments, and possible complications arising from CAM usage. There is emerging evidence for CAM use in skin cancer, but no human clinical trials support the effectiveness of any CAM in the treatment of skin cancer to date. Nevertheless, patients worldwide frequently use CAM, and physicians should educate themselves on currently available CAMs.