Bridging the literacy gap for surgical consents: an AI-human expert collaborative approach.

Despite the importance of informed consent in healthcare, the readability and specificity of consent forms often impede patients' comprehension. This study investigates the use of GPT-4 to simplify surgical consent forms and introduces an AI-human expert collaborative approach to validate content appropriateness. Consent forms from multiple institutions were assessed for readability and simplified using GPT-4, with pre- and post-simplification readability metrics compared using nonparametric tests. Independent reviews by medical authors and a malpractice defense attorney were conducted. Finally, GPT-4's potential for generating de novo procedure-specific consent forms was assessed, with forms evaluated using a validated 8-item rubric and expert subspecialty surgeon review. Analysis of 15 academic medical centers' consent forms revealed significant reductions in average reading time, word rarity, and passive sentence frequency (all P < 0.05) following GPT-4-faciliated simplification. Readability improved from an average college freshman to an 8th-grade level (P = 0.004), matching the average American's reading level. Medical and legal sufficiency consistency was confirmed. GPT-4 generated procedure-specific consent forms for five varied surgical procedures at an average 6th-grade reading level. These forms received perfect scores on a standardized consent form rubric and withstood scrutiny upon expert subspeciality surgeon review. This study demonstrates the first AI-human expert collaboration to enhance surgical consent forms, significantly improving readability without sacrificing clinical detail. Our framework could be extended to other patient communication materials, emphasizing clear communication and mitigating disparities related to health literacy barriers.

Demographic Representation in 3 Leading Artificial Intelligence Text-to-Image Generators.

Importance: The progression of artificial intelligence (AI) text-to-image generators raises concerns of perpetuating societal biases, including profession-based stereotypes. Objective: To gauge the demographic accuracy of surgeon representation by 3 prominent AI text-to-image models compared to real-world attending surgeons and trainees. Design, Setting, and Participants: The study used a cross-sectional design, assessing the latest release of 3 leading publicly available AI text-to-image generators. Seven independent reviewers categorized AI-produced images. A total of 2400 images were analyzed, generated across 8 surgical specialties within each model. An additional 1200 images were evaluated based on geographic prompts for 3 countries. The study was conducted in May 2023. The 3 AI text-to-image generators were chosen due to their popularity at the time of this study. The measure of demographic characteristics was provided by the Association of American Medical Colleges subspecialty report, which references the American Medical Association master file for physician demographic characteristics across 50 states. Given changing demographic characteristics in trainees compared to attending surgeons, the decision was made to look into both groups separately. Race (non-White, defined as any race other than non-Hispanic White, and White) and gender (female and male) were assessed to evaluate known societal biases. Exposures: Images were generated using a prompt template, "a photo of the face of a [blank]", with the blank replaced by a surgical specialty. Geographic-based prompting was evaluated by specifying the most populous countries on 3 continents (the US, Nigeria, and China). Main Outcomes and Measures: The study compared representation of female and non-White surgeons in each model with real demographic data using χ2, Fisher exact, and proportion tests. Results: There was a significantly higher mean representation of female (35.8% vs 14.7%; P < .001) and non-White (37.4% vs 22.8%; P < .001) surgeons among trainees than attending surgeons. DALL-E 2 reflected attending surgeons' true demographic data for female surgeons (15.9% vs 14.7%; P = .39) and non-White surgeons (22.6% vs 22.8%; P = .92) but underestimated trainees' representation for both female (15.9% vs 35.8%; P < .001) and non-White (22.6% vs 37.4%; P < .001) surgeons. In contrast, Midjourney and Stable Diffusion had significantly lower representation of images of female (0% and 1.8%, respectively; P < .001) and non-White (0.5% and 0.6%, respectively; P < .001) surgeons than DALL-E 2 or true demographic data. Geographic-based prompting increased non-White surgeon representation but did not alter female representation for all models in prompts specifying Nigeria and China. Conclusion and Relevance: In this study, 2 leading publicly available text-to-image generators amplified societal biases, depicting over 98% surgeons as White and male. While 1 of the models depicted comparable demographic characteristics to real attending surgeons, all 3 models underestimated trainee representation. The study suggests the need for guardrails and robust feedback systems to minimize AI text-to-image generators magnifying stereotypes in professions such as surgery.

Understanding melanoma in situ: Lentigo maligna surgical treatment terminology and guideline adherence, a targeted review.

BACKGROUND: Malignant melanoma in-situ, lentigo maligna (MMIS-LM) can be successfully treated with several different surgical techniques; however, the literature is inconsistent in defining them. OBJECTIVE: To comprehensively define and describe the national guideline recommended surgical techniques used to treat MMIS-LM to help clarify and standardize this terminology to ensure compliance with the guidelines. METHODS: A targeted literature review was performed from 1990 to 2022 focusing on articles that discussed the national guideline recommended surgical techniques of wide local excision, Mohs micrographic surgery (MMS), modified Mohs surgery, and staged excision/Slow-Mohs for MMIS-LM, as well as the related methods of tissue processing. National Comprehensive Cancer Network and American Academy of Dermatology guidelines were reviewed to identify how the techniques need to be employed to be compliant with guideline recommendations. RESULTS: We describe the various surgical and tissue processing techniques and discuss advantages and disadvantages of each. LIMITATIONS: This paper was styled as a narrative review defining and clarifying terminology and technique and does not investigate these topics more broadly. CONCLUSION: Understanding the methodology and terminology for these surgical procedures and tissue processing methods is critical so that both general dermatologists and surgeons can employ these techniques effectively for optimal patient care.

Host and primary tumor factors for the development of multiple cutaneous squamous cell carcinomas among a retrospective cohort in Rhode Island.

INTRODUCTION: Risk factors for a primary cutaneous squamous cell carcinoma (CSCC) are well-established; however, the host and primary tumor risk factors for subsequent CSCC have not been fully explored. METHODS: We performed a retrospective chart review of patients diagnosed with CSCC in an academic dermatology clinic in Rhode Island from 2016-2019. Logistic regression was used to evaluate the associations between host factors and multiple CSCC and between primary tumor characteristics and the risk of subsequent CSCC. Adjusted odds ratios (aORs) and 95% CIs were calculated. RESULTS: A total of 1312 patients with CSCC diagnoses were included. Host risk factors significantly associated with multiple CSCCs included: aged >80 years (aOR, 2.18; 95% CI, 1.46-3.31); history of: solid organ transplant (aOR, 2.41; 95% CI, 1.20-4.80); skin cancer (aOR, 1.96; 95% CI, 1.52-2.54); other cancer (aOR, 1.49; 95% CI, 1.11-2.00); family history of skin cancer (aOR, 1.36; 95% CI, 1.03-1.78); and actinic keratosis (aOR, 1.52; 95% CI, 1.18-1.95). Tumor location, diameter, histologic differentiation, and treatment were not significant predictors of subsequent CSCCs. LIMITATIONS: Study patients were predominantly White and from a single institution, limiting the generalizability of results. CONCLUSIONS: Certain host characteristics were associated with the development of subsequent CSCC, which may inform clinical guidelines for follow-up.

A Narrative Review of Nicotinamide Adenine Dinucleotide (NAD)+ Intermediates Nicotinamide Riboside and Nicotinamide Mononucleotide for Keratinocyte Carcinoma Risk Reduction.

Oral nicotinamide (NAM) supplementation has been shown to decrease the incidence of keratinocyte carcinoma (KC) in high-risk skin cancer patients. NAM is a nicotinamide adenine dinucleotide (NAD+) intermediate and thus directly leads to increased NAD+. This increase in NAD+ is believed to be responsible for NAM’s impact on keratinocyte carcinoma risk. NAD+ has protective cellular effects and is a necessary cofactor for DNA repair, helping to prevent potentially oncogenic mutations. Nicotinamide riboside (NR) and nicotinamide mononucleotide (NMN) are NAD+ intermediates like NAM; however, their protective roles on cellular DNA and effects on cancer have been under-explored. Research into cellular metabolism and aging suggests that NR and NMN can lead to greater increases in NAD+ vs NAM. NR and NMN are safe and well-tolerated and are consequently currently undergoing investigation as agents able to protect against age-associated disease caused by NAD+ depletion. We hypothesize that oral supplementation with NR or NMN may lead to greater reductions in KC than NAM. J Drugs Dermatol. 2022;21(10): 1129-1132. doi:10.36849/JDD.6870.

Zooming into cosmetic procedures during the COVID-19 pandemic: The provider's perspective.

The COVID-19 pandemic has seen a massive shift toward virtual living, with video-conferencing now a primary means of communication for both work and social events. Individuals are finding themselves staring at their own video reflection, often for hours a day, scrutinizing a distorted image on screen and developing a negative self-perception. This survey study of over 100 board-certified dermatologists across the country elucidates a new problem of Zoom dysmorphia, where patients seek cosmetic procedures to improve their distorted appearance on video-conferencing calls.

Histiocytoid Sweet syndrome harboring an isocitrate dehydrogenase 1 mutation: A case report and retrospective analysis of 29 cases of histiocytoid Sweet syndrome.

Histiocytoid Sweet syndrome (HSS) is a rare histopathologic variant of Sweet syndrome that demonstrates dermal and/or subcutaneous infiltrate with a prominent component of myeloid cells resembling histiocytes. It has been known to occur in association with hematologic neoplasms, including myelodysplastic syndrome (MDS) and acute myelogenous leukemia, but whether it confers an increased risk of such neoplasms is controversial. Here, we describe a case of a HSS that led to the diagnosis of MDS with an isocitrate dehydrogenase 1 (IDH-1) mutation and a corresponding study looking for additional cases of IDH-1 mutations in biopsies of histiocytoid and conventional Sweet syndrome.

Mixing of Injectable Fillers: A National Survey.

BACKGROUND: The mixing of hyaluronic acid or calcium hydroxylapatite fillers with normal saline, plain lidocaine, or lidocaine with epinephrine before injection is a familiar practice among dermatologists. However, the frequency of this practice and rationale behind it has not been well studied. OBJECTIVE: To better elucidate the clinical practice of mixing fillers with other solutions before injecting among dermatologists. METHODS: A survey was electronically distributed to members of the American Society for Dermatologic Surgery. RESULTS: Four hundred seventy-five dermatologists responded to the survey. Thirty-five percent of respondents mix fillers before injection. Solutions used were as follows: plain lidocaine (44%), lidocaine with epinephrine (36%), normal saline (30%), and sterile water (7%). Respondents mix filler for the following reasons: to decrease viscosity (40%), increase anesthesia (30%), decrease swelling (17%), and increase volume (13%). CONCLUSION: Despite the lack of evidence, more than one-third of dermatologists surveyed mix fillers with other solutions before injection. Plain lidocaine is most commonly used. The top reason for mixing fillers is to decrease viscosity and facilitate ease of injection. More scientific data are needed to support this practice and better understand the biophysical changes that occur when mixing fillers with other solutions.