Ethical considerations for artificial intelligence in dermatology: a scoping review.

The field of dermatology is experiencing the rapid deployment of artificial intelligence (AI), from mobile applications (apps) for skin cancer detection to large language models like ChatGPT that can answer generalist or specialist questions about skin diagnoses. With these new applications, ethical concerns have emerged. In this scoping review, we aimed to identify the applications of AI to the field of dermatology and to understand their ethical implications. We used a multifaceted search approach, searching PubMed, MEDLINE, Cochrane Library and Google Scholar for primary literature, following the PRISMA Extension for Scoping Reviews guidance. Our advanced query included terms related to dermatology, AI and ethical considerations. Our search yielded 202 papers. After initial screening, 68 studies were included. Thirty-two were related to clinical image analysis and raised ethical concerns for misdiagnosis, data security, privacy violations and replacement of dermatologist jobs. Seventeen discussed limited skin of colour representation in datasets leading to potential misdiagnosis in the general population. Nine articles about teledermatology raised ethical concerns, including the exacerbation of health disparities, lack of standardized regulations, informed consent for AI use and privacy challenges. Seven addressed inaccuracies in the responses of large language models. Seven examined attitudes toward and trust in AI, with most patients requesting supplemental assessment by a physician to ensure reliability and accountability. Benefits of AI integration into clinical practice include increased patient access, improved clinical decision-making, efficiency and many others. However, safeguards must be put in place to ensure the ethical application of AI.

The use of artificial intelligence (AI) in dermatology is rapidly increasing, with applications in dermatopathology, medical dermatology, cutaneous surgery, microscopy/spectroscopy and the identification of prognostic biomarkers (characteristics that provide information on likely patient health outcomes). However, with the rise of AI in dermatology, ethical concerns have emerged. We reviewed the existing literature to identify applications of AI in the field of dermatology and understand the ethical implications. Our search initially identified 202 papers, and after we went through them (screening), 68 were included in our review. We found that ethical concerns are related to the use of AI in the areas of clinical image analysis, teledermatology, natural language processing models, privacy, skin of colour representation, and patient and provider attitudes toward AI. We identified nine ethical principles to facilitate the safe use of AI in dermatology. These ethical principles include fairness, inclusivity, transparency, accountability, security, privacy, reliability, informed consent and conflict of interest. Although there are many benefits of integrating AI into clinical practice, our findings highlight how safeguards must be put in place to reduce rising ethical concerns.

Part 1: Management of Antithrombotic Medications in Dermatologic Surgery.

Perioperative management of antithrombotic agents requires practical and medical considerations. Discontinuing antithrombotic therapies increases the risk of thrombotic adverse events including cerebrovascular accidents, myocardial infarction, pulmonary embolism, deep vein thrombosis, and retinal artery occlusion. Conversely, continuation of antithrombotic therapy during surgical procedures has associated bleeding risks. Currently, no guidelines exist regarding management of antithrombotic agents in the perioperative period for cutaneous surgeries and practice differs by surgeon. Here, we review the data on antithrombotic medications in patients undergoing cutaneous surgery including medication-specific surgical and postoperative bleeding risk if the medications are continued, and thromboembolic risk if the medications are interrupted. Specifically, we focus on vitamin K antagonist (VKA) (warfarin), direct-acting oral anticoagulants (DOAC) (rivaroxaban, apixaban, edoxaban, dabigatran), antiplatelet medications (aspirin, clopidogrel, prasugrel, ticagrelor, dipyridamole), unfractionated heparin, low molecular weight heparin (enoxaparin and dalteparin), fondaparinux, bruton tyrosine kinase inhibitors (BTKi) (ibrutinib, acalabrutinib), and dietary supplements (i.e., garlic, ginger, gingko).

Part 2: Management of Intraoperative and Perioperative Bleeding.

With an increase in number of patients on antithrombotic therapies, management of bleeding during dermatologic surgery is increasingly important. As described in Part 1, perioperative discontinuation of antithrombotic therapies may increase the risk of embolic events thus the risks and benefits must be weighed carefully when deciding whether to continue or suspend therapy. However, continuing oral anticoagulants may result in increased intraoperative and postoperative bleeding. Here we describe various methods to effectively achieve hemostasis which include: 1) mechanical methods to compress the vasculature 2) pharmacologic agents that induce vasoconstriction 3) physiologic agents that augment clot formation and 4) physical agents that promote platelet aggregation.

Postoperative Bleeding Complications Associated With Novel Oral Anticoagulants in Mohs Micrographic Surgery.

BACKGROUND: Novel oral anticoagulants (NOACs) are commonly prescribed, recently developed anticoagulants, but limited data exist on NOAC-related bleeding complications in Mohs micrographic surgery (MMS). OBJECTIVE: To assess the risk of postoperative bleeding in patients taking NOACs compared with patients taking no antithrombotic medications. METHODS/MATERIALS: A 5-year retrospective chart review of all MMS cases performed by a single surgeon was conducted. Patient and surgery characteristics, anticoagulant use, and bleeding complications were recorded. RESULTS: Two thousand one hundred eighty-one MMS cases in 1,545 patients were included. There were 696/2,181 cases in which patients were taking at least 1 antithrombotic medication, with 149 on NOAC monotherapy and 15 on NOAC and aspirin combination therapy. Bleeding complications occurred in 22/2,181 cases. Patients on NOAC monotherapy did not have an increased risk of bleeding complications compared with patients on no antithrombotic medications (odds ratio [OR]:1.70, 95% confidence interval [CI]: 0.36-7.97, p = .50). In contrast, patients on NOAC and aspirin combination therapy exhibited an increased bleeding risk (OR: 20.5, 95% CI: 3.99-105.7, p < .001). CONCLUSION: Novel oral anticoagulant use alone during MMS was not associated with an increased postoperative bleeding risk, supporting the safety of continuing NOAC therapy during MMS. However, NOAC and aspirin combination therapy was associated with a high postoperative bleeding risk. Nonetheless, these bleeding events did not lead to adverse long-term outcomes.

Risk factors for developing depressive symptoms in the immediate postoperative period after Mohs micrographic surgery.

PURPOSE: Mohs micrographic surgery (MMS) is a highly efficacious, tissue sparing method of skin cancer removal. Nevertheless, in the months to years after MMS, psychosocial distress has been described. The present study addressed the immediate period after MMS and assessed the frequency and risk factors for development of depressive symptoms. METHODS: Subjects undergoing MMS at two physician practices (JL, FS) were included in this prospective cohort study. Preoperatively, a standardized depression screening, the Patient Health Questionnaire-8 (PHQ-8), was administered. After MMS, the PHQ-8 was readministered at weeks 1, 2, 4, 6, and 12. Average PHQ-8 score by week and change from baseline PHQ-8 score were the primary outcomes. RESULTS: Sixty-three subjects were included of which 49 (78%) had a facial site. Twenty-two subjects (35%) had some increase in score during the 12-week follow-up period, of which 18 had a facial site. The oldest subjects (83-99 years, n = 14) had significantly higher PHQ-8 scores at week 4 (p < 0.01) and week 6 (p = 0.02) than all other age groups. There were no differences in scores between location groups. CONCLUSIONS: One-third of subjects had some increase in score during the follow-up period. Those in the oldest age cohort were at highest risk of increased score. In contrast to prior literature, those with facial sites were not at higher risk. This difference may be explained by increased masking during the ongoing COVID-19 pandemic. Ultimately, consideration of patients' psychologic status in the immediate postoperative period after MMS, particularly in the elderly population, may enhance perceived patient outcomes.

Surgical management of dermatofibrosarcoma protuberans.

Dermatofibrosarcoma protuberans (DFSP) is an uncommon, locally aggressive cutaneous malignancy. Complete resection is the primary treatment but there is debate over the optimal method. Wide local excision was traditionally the standard of care; however, National Comprehensive Cancer Network guidelines now recommend Mohs micrographic surgery as the preferred approach. Medical therapy with imatinib can be used in advanced or unresectable disease. This review will discuss the current management of DFSP, focusing on optimal surgical approach.

Biomarkers in melanoma and non-melanoma skin cancer prevention and risk stratification.

The rates of melanoma and non-melanoma skin cancer (NMSC) have been increasing over the last twenty years in the United States, and this has been attributed to increased ultraviolet radiation exposure (UVR). Given these rising rates, preventative measures have become increasingly important to reduce the incidence and promote early detection of these cancers. Skin cancer prevention remains a challenging task to accomplish mainly due to the lack of reliable and sensitive methods to provide objective risk information that can educate and motivate individuals to avoid sunburn. Currently, minimal erythema dose (MED) is used as a marker of UVR. However, it is not an ideal marker because significant cancer-related molecular damage can occur after UVR exposure that cannot be detected by MED. Thus, over the recent years there has been significant interest in development of biomarkers indicative of exposure to UVR to improve early detection of cutaneous malignancies. Here, we will discuss emerging biomarkers for melanoma and NMSC that can help with risk stratification and targeted prevention and treatment.

Predictors of time to definitive surgery and survival in Merkel cell carcinoma: analysis of the US National Cancer Database.

BACKGROUND: Merkel cell carcinoma (MCC) is an aggressive cancer, and it has been suggested that earlier treatment would allow for better patient outcomes. However, the causes of delays in the initiation of treatment and the effects of delayed treatment on survival of patients have not fully been explored, and the effects of treatment delays for MCC are not yet fully understood. AIM: To determine the effect of time to treatment initiation (TTI) on mortality in MCC and to determine the predictors of TTI itself. METHODS: This was a retrospective cohort analysis of the US National Cancer Database (NCDB) for cases of MCC from 2004 to 2016, excluding individuals with Stage IV MCC, as surgery is not the preferred treatment for this group. The time difference between initial biopsy of MCC and definitive surgery (TTI) was stratified into five groups by 30-day intervals. RESULTS: In total, 12 157 patients [7491 (61.6%) men, 4666 (38.4%) women; mean ± SD age 74.4 ± 10.9 years] were included in the study. A risk for longer TTI was seen in black individuals (OR = 1.7, 95% CI 1.2-2.6) and in elderly individuals aged > 70 years (OR = 1.7, 95% CI 1.2-2.5). Kaplan-Meier survival analysis showed that individuals with TTI < 30 days had a significantly longer overall survival than those with TTI > 120 days (6.1 vs. 4.8 years, P < 0.001). However, after controlling for clinical and tumour factors in Cox multivariable analysis, no difference in survival was noted for TTI < 30 days and TTI > 120 days [hazard ratio (HR) = 0.9, 95% CI 0.8-1.1). Worse outcomes were also associated with increasing age (HR = 2.0, 95% CI 1.7-2.5), male sex (HR = 1.2, 95% CI 1.2-1.3), higher Charlson-Deyo comorbidity score (HR = 1.4, 95% CI 1.3-1.5), lack of radiation therapy (HR = 0.8, 95% CI 0.8-0.9), lack of private insurance (HR = 0.7, 95% CI 0.6-1.0), and use of surgical technique other than Mohs micrographic surgery or wide local excision (HR = 1.2, 95% CI 1.2-1.3). CONCLUSION: Although TTI is a useful prognostic metric in isolated survival analysis, its utility declines when other factors are controlled for in the analysis. Age, radiotherapy, type of surgery performed, comorbidities, tumour size and lymph node involvement may be important predictors of survival.

UV biomarker genes for classification and risk stratification of cutaneous actinic keratoses and squamous cell carcinoma subtypes.

Currently, there is no sensitive molecular test for identifying transformation-prone actinic keratoses (AKs) and aggressive squamous cell carcinoma (SCC) subtypes. Biomarker-based molecular testing represents a promising tool for risk stratifying these lesions. We evaluated the utility of a panel of ultraviolet (UV) radiation-biomarker genes in distinguishing between benign and transformation-prone AKs and SCCs. The expression of the UV-biomarker genes in 31 SCC and normal skin (NS) pairs and 10 AK/NS pairs was quantified using the NanoString nCounter system. Biomarker testing models were built using logistic regression models with leave-one-out cross validation in the training set. The best model to classify AKs versus SCCs (area under curve (AUC) 0.814, precision score 0.833, recall 0.714) was constructed using a top-ranked set of 13 UV-biomarker genes. Another model based on a 15-gene panel was developed to differentiate histologically concerning from less concerning SCCs (AUC 1, precision score 1, recall 0.714). Finally, 12 of the UV-biomarker genes were differentially expressed between AKs and SCCs, while 10 genes were uniquely expressed in the more concerning SCCs. UV-biomarker gene subsets demonstrate dynamic utility as molecular tools to classify and risk stratify AK and SCC lesions, which will complement histopathologic diagnosis to guide treatment of high-risk patients.

Immune checkpoint inhibitor therapy in solid organ transplant recipients: A patient-centered systematic review.

BACKGROUND: The use of immunotherapies in the treatment of metastatic cancers has significantly advanced oncology. However, due to safety concerns, solid organ transplant recipients (SOTRs) are routinely excluded from immunotherapy trials; thus, there is limited data for these agents in this population. METHODS: A systematic review was performed to evaluate the safety and efficacy of immunotherapies in SOTRs with metastatic cancers. Fisher's exact test and Kruskal-Wallis test were used for analysis. RESULTS: In total, 37% of patients experienced organ rejection, and 14% died as a result of graft rejection. Nivolumab was associated with the highest rejection rate (52.2%), followed by pembrolizumab (26.7%) and ipilimumab (25%; P = .1774). The highest rejection rate was seen in patients with kidney transplants (40.1%), then liver (35%) and heart (20%) transplants (P = .775), and 64% of patients succumbed to the progression of malignancy. For all cases, rates of progression or death secondary to disease were highest for ipilimumab (75%), followed by nivolumab (43%) and pembrolizumab (40%; P = .1892). The overall response rate was highest for pembrolizumab (40%), followed by nivolumab (30%) and ipilimumab (25%; P = .7929). LIMITATIONS: The small sample size. CONCLUSION: Physicians must be cautious when administering immunotherapy to SOTRs. However, rejection is not the most common cause for death in this population.

An expert panel consensus on opioid-prescribing guidelines for dermatologic procedures.

BACKGROUND: Opioid overprescribing is a major contributor to the opioid crisis. The lack of procedure-specific guidelines contributes to the vast differences in prescribing practices. OBJECTIVE: To create opioid-prescribing consensus guidelines for common dermatologic procedures. METHODS: We used a 4-step modified Delphi method to conduct a systematic discussion among a panel of dermatologists in the fields of general dermatology, dermatologic surgery, and cosmetics/phlebology to develop opioid prescribing guidelines for some of the most common dermatologic procedural scenarios. Guidelines were developed for opioid-naive patients undergoing routine procedures. Opioid tablets were defined as oxycodone 5-mg oral equivalents. RESULTS: Postoperative pain after most uncomplicated procedures (76%) can be adequately managed with acetaminophen and/or ibuprofen. Group consensus identified no specific dermatologic scenario that routinely requires more than 15 oxycodone 5-mg oral equivalents to manage postoperative pain. Group consensus found that 23% of the procedural scenarios routinely require 1 to 10 opioid tablets, and only 1 routinely requires 1 to 15 opioid tablets. LIMITATIONS: These recommendations are based on expert consensus in lieu of quality evidence-based outcomes research. These recommendations must be individualized to accommodate patients' comorbidities. CONCLUSIONS: Procedure-specific opioid prescribing guidelines may serve as a foundation to produce effective and responsible postoperative pain management strategies after dermatologic interventions.

Cutaneous metastasis of hepatocellular carcinoma following liver transplantation.

Cutaneous metastases from hepatocellular carcinoma (HCC) are extremely rare and can represent a sign of an underlying malignancy or relapse/progression from an existing tumor. We report a case of a cutaneous metastasis arising in a patient with metastatic HCC following orthotopic liver transplantation. Diagnosis is a multistep process as cutaneous HCC metastases must be differentiated from primary cutaneous malignancies as well as other cutaneous metastases. Making this even more challenging, HCC metastases have heterogeneous clinical and histologic appearances. Therefore, the use of immunohistochemical stains, including hepatocyte paraffin-1, arginase-1, and glypican-3, and correlation with the clinical context are essential for a correct diagnosis.

Evaluating the Utility of Routine Imaging in Squamous Cell Carcinoma of the Nail Unit.

BACKGROUND: Squamous cell carcinoma (SCC) is the most common malignant tumor of the nail unit. No guidelines currently exist regarding the role of imaging in this specific location. OBJECTIVE: To investigate the utility of routine imaging in SCC of the nail apparatus. METHODS: A multi-institutional retrospective review of patients treated for nail unit SCC was performed. Data were collected on patient characteristics, tumor qualities, treatment, and radiographic imaging. A change in treatment was defined as more aggressive treatment (amputation) rather than local excision or Mohs micrographic surgery (MMS). RESULTS: One hundred seven patients with nail unit SCC were identified. Approximately 44/107 (41.1%) of patients were imaged and 63/107 (58.9%) were not. Mohs micrographic surgery was the most common primary treatment (66.4%). Mohs micrographic surgery was more commonly performed in nonimaged patients, and amputation was more commonly performed in imaged patients (p < .001). Bony changes were identified in 13/44 (29.5%) of imaged patients. In 8/44 (18.2%), imaging findings caused a change in treatment. In 99/107 (92.5%) of the cohort, imaging was either not performed or did not change management. CONCLUSION: In select cases, imaging may help guide patient management. Sufficient evidence does not yet exist to support routine imaging for patients with nail unit SCC.

Sebaceous carcinoma: evidence-based clinical practice guidelines.

Sebaceous carcinoma usually occurs in adults older than 60 years, on the eyelid, head and neck, and trunk. In this Review, we present clinical care recommendations for sebaceous carcinoma, which were developed as a result of an expert panel evaluation of the findings of a systematic review. Key conclusions were drawn and recommendations made for diagnosis, first-line treatment, radiotherapy, and post-treatment care. For diagnosis, we concluded that deep biopsy is often required; furthermore, differential diagnoses that mimic the condition can be excluded with special histological stains. For treatment, the recommended first-line therapy is surgical removal, followed by margin assessment of the peripheral and deep tissue edges; conjunctival mapping biopsies can facilitate surgical planning. Radiotherapy can be considered for cases with nerve or lymph node involvement, and as the primary treatment in patients who are ineligible for surgery. Post-treatment clinical examination should occur every 6 months for at least 3 years. No specific systemic therapies for advanced disease can be recommended, but targeted therapies and immunotherapies are being developed.

Effect of Postoperative Telephone Calls on Patient Satisfaction and Scar Satisfaction After Mohs Micrographic Surgery.

BACKGROUND: Mohs micrographic surgery is considered the gold standard for high-risk nonmelanoma skin cancer. Postoperative telephone follow-up (TFU) is linked to higher patient satisfaction; however, there are no randomized, blinded studies examining whether TFU after Mohs surgery improves patient satisfaction. OBJECTIVE: To perform a randomized single-blinded prospective survey study examining whether patient satisfaction or scar satisfaction varied between Mohs patients who received a postoperative call and patients who did not. METHODS: Patients were enrolled into "post-op call" or "no post-op call" groups. Both arms completed surveys at suture removal and 3-month follow-up visits. RESULTS: One hundred four subjects were enrolled, and demographics, the number of Mohs stages, and type of repair were controlled. At suture removal, both arms reported similar overall high satisfaction on the 5-point Likert scale (4.90 "call arm" vs 4.88 "no-call arm", p = .80). Patient and Observer Scar Assessment Scale (POSAS) scores were 3.37 in the "call arm" versus 3.81 in the "no-call arm", p = .31. At 3-month follow-up, results were similar. CONCLUSION: High overall satisfaction was reported in both arms. The TFU group reported higher overall satisfaction, but this difference was not significant. Scar satisfaction did not vary statistically between the arms, but POSAS scores in the call arm trended favorably.

Fall risk assessment and injury prevention in the Mohs surgery clinic: a review of the literature and recommendations for improving patient safety.

Patient falls remain a major cause of adverse events in the medical setting. Many patients receiving Mohs micrographic surgery are at high risk, both for falling and resultant injuries. Although the incidence of patient falls in dermatologic surgery is low, falls can have significant consequences for both patient and provider. Therefore, effective interventions to improve organizational safety are critical. Though there is a considerable amount of research pertaining to fall prevention strategies, the majority of studies have been confined to the inpatient setting and long-term care facilities. Implementation of fall prevention initiatives in the outpatient setting has rarely been evaluated and no studies have focused on the Mohs patient population to date. METHODS: We reviewed the literature pertaining to fall risk and prevention guidelines in the inpatient and outpatient settings as it applies to the dermatologic surgery environment. RESULTS: Herein we will discuss patient risk factors for falling relevant to the Mohs setting and review existing validated fall risk assessment tools and strategies for fall prevention. CONCLUSION: Identifying fall risk factors can improve patient safety and reduce falls in the dermatologic surgery clinic.