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.

Applications and Best Practices for Geospatial Analysis Research in Dermatology.

Dermatologic diseases often exhibit distinct geographic patterns, underscoring the significant role of regional environmental, genetic, and sociocultural factors in driving their prevalence and manifestations. Geographic information and geospatial analysis enable researchers to investigate the spatial distribution of adverse health outcomes and their relationship with socioeconomic and environmental risk factors that are inherently geographic. Health geographers and spatial epidemiologists have developed numerous geospatial analytical tools to collect, process, visualize, and analyze geographic data. These tools help provide vital spatial context to the comprehension of the underlying dynamics behind health outcomes. By identifying areas with high rates of dermatologic disease and areas with barriers to access to quality dermatologic care, findings from studies utilizing geospatial analysis can inform the design and targeting of policy and intervention to help improve dermatologic healthcare outcomes and promote health equity. This article emphasizes the significance of geospatial data and analysis in dermatology research. We explore the common processes in data acquisition, harmonization, and geospatial analytics while conducting spatially and dermatologically relevant research. The article also highlights the practical application of geospatial analysis through instances drawn from the dermatology literature.

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.

A Screening Proposal for Zoom Dysmorphia in Virtual Settings.

Zoom dysmorphia (ZD) is a facial dysmorphia that is triggered or aggravated by frequent virtual meetings. The frequent use of videoconferencing platforms has been linked to a distorted perception of facial images as individuals have an increased awareness of their appearance, given constant video feedback. As a result, dysmorphic concerns can develop. It is crucial to identify ZD as this condition interferes with an individual's life and can trigger or aggravate body dysmorphic disorder (BDD). A standardized approach for screening ZD in non-psychiatric settings has yet to be defined. We discuss the features of ZD and the challenges of screening for ZD in a virtual setting. To facilitate the recognition of ZD in telehealth consultations, we propose a comprehensive ZD screening questionnaire that includes questions related to typical ZD features and a BDD-focused question. The questionnaire is concise and allows the identification of individuals with a potential ZD. A BDD assessment in such individuals should follow.

Considering Sun Safety Policies in the United States.

As they are collectively the most common malignancies, the personal and systemic burden of skin cancers represent a significant public health concern in the United States. Ultraviolet radiation from the sun as well as from artificial sources such as tanning beds is a carcinogen well-known to increase the risk of developing skin cancer in individuals. Public health policies can help mitigate these risks. In this perspectives article, we review sunscreen and sunglasses standards, tanning bed utilization, and workplace sun protection guidelines in the US and provide focused examples for improvement from Australia and the United Kingdom where skin cancer is a well-documented public health concern. These comparative examples can inform interventions in the US that have the potential to modify exposure to risk factors associated with skin cancer.

Factors associated with the use of adjuvant radiation therapy in stage III melanoma.

Objective: The role of radiation therapy (RT) in melanoma has historically been limited to palliative care, with surgery as the primary treatment modality. However, adjuvant RT can be a powerful tool in certain cases and its application in melanoma has been increasingly explored in recent years. The aim of this study is to explore national patterns of care and associations surrounding the use of adjuvant RT for stage III melanoma. Methods: The National Cancer Data Base (NCDB) was used to identify patients who were diagnosed with stage III melanoma between 2004 and 2014. Exclusion criteria included those with distant metastatic disease, in-situ histology, no confirmed positive nodes, palliative intent therapy, and dosing regimens inconsistent with National Comprehensive Cancer Network (NCCN) guidelines for adjuvant RT in melanoma. Patients treated with and without adjuvant RT were compared and factors associated with use of adjuvant RT were identified using multivariable logistic regression analyses. Results: A total of 7,758 cases of stage III melanoma were analyzed, of which 11.7% received adjuvant RT. The mean age of the overall cohort was 58.5 years, and the majority of patients were male (64.7%), white (96.6%), on private insurance (51.3%), and presented to a non-high-volume facility (90.3%). Multivariable regression analyses revealed that patients who present to the hospital in 2009-2014 as compared to 2004-2008 (odds ratio [OR] 1.61, 95% confidence interval [CI] 1.36-1.92), had 4 or more positive nodes (OR 4.30, 95% CI 3.67-5.04), and had microscopic residual tumor (OR 2.11, 95% CI 1.46-3.04) were more likely to receive adjuvant RT. Factors that were negatively associated with receiving adjuvant RT included female gender (OR 0.72, 95% CI 0.61-0.85) and median income of at least $63,000 (OR 0.66, 95% CI 0.52-0.83). Conclusions: This study demonstrates the rising use of RT for stage III melanoma in recent years and identifies demographic, social, clinical, and hospital-specific factors associated with patients receiving adjuvant RT. Further investigation is needed to explore disease benefits to improve guidance on the utilization of RT in melanoma.

Integrated transcriptome and trajectory analysis of cutaneous T-cell lymphoma identifies putative precancer populations.

The incidence of cutaneous T-cell lymphoma (CTCL) increases with age, and blood involvement portends a worse prognosis. To advance our understanding of the development of CTCL and identify potential therapeutic targets, we performed integrative analyses of paired single-cell RNA and T-cell receptor (TCR) sequencing of peripheral blood CD4+ T cells from patients with CTCL to reveal disease-unifying features. The malignant CD4+ T cells of CTCL showed highly diverse transcriptomic profiles across patients, with most displaying a mature Th2 differentiation and T-cell exhaustion phenotype. TCR-CDR3 peptide prediction analysis suggested limited diversity between CTCL samples, consistent with a role for a common antigenic stimulus. Potential of heat diffusion for affinity-based trajectory embedding transition analysis identified putative precancerous circulating populations characterized by an intermediate stage of gene expression and mutation level between the normal CD4+ T cells and malignant CTCL cells. We further revealed the therapeutic potential of targeting CD82 and JAK that endow the malignant CTCL cells with survival and proliferation advantages.

Time to surgical closure of complex infectious wounds: a single-center retrospective cohort study.

INTRODUCTION: Surgical management of NSTIs can result in complex wounds, and closure of these wounds is often difficult or complicated. Although surgical factors influencing mortality and LOS have been well described, little is known about patient, wound, and surgical factors associated with time to closure. OBJECTIVE: The purpose of this study is to identify patient, wound, and surgical factors that may influence time to closure of NSTIs. MATERIALS AND METHODS: The records of patients who presented to a tertiary care center over an 11-year period (2007-2017) with an NSTI requiring surgical closure were retrospectively reviewed. RESULTS: Forty-seven patients met the inclusion criteria. The average time to closure was 31.1 days, with an average of 4.8 procedures. Most patients were middle aged (mean, 50.3 years; range, 20-81 years), immunocompetent, and nondiabetic upon admission. Closure was achieved mainly with autograft. The percent TBSA was described in 19 cases (40%). There was no association between substance use (alcohol, smoking, or other), anticoagulant medication use, or medical comorbidities and time to closure. On multivariable analysis, flap closure (P =.02) and increased number of surgical procedures (P =.003)-the latter reflecting the need for an increased number of debridements-were associated with increased time to closure. CONCLUSIONS: The data in this study suggest that use of local flaps for wound closure and increased number of surgical procedures (particularly debridements) may be predictors of time to closure in patients with an NSTI.

Factors Associated With In-Hospital Mortality in Mycosis Fungoides Patients: A Multivariable Analysis.

Background Mycosis fungoides (MF) is the most common form of cutaneous T-cell lymphoma (CTCL). Although it often has an indolent course, it can progress to more aggressive CTCL forms. There is sparse data in current literature describing specific clinical factors associated with in-hospital mortality in mycosis fungoides patients. An understanding of patients at greatest risk for in-hospital mortality can aid in developing recommendations for prophylaxis and empirical management. Aim We aim to characterize factors associated with in-hospital mortality in MF patients. Materials and methods The Nationwide Emergency Department Sample (NEDS) was queried for MF cases from 2006 to 2015. Baseline demographic and hospital characteristics were stratified based on survival outcomes. Multivariable logistic regression was used to identify factors associated with in-hospital mortality. Results A total of 57,665 patients with MF presenting to the ED between 2006 and 2015 were identified. Sézary syndrome, sepsis, and advanced age were associated with MF in-hospital mortality, while female sex was inversely associated. There was a downtrend in in-hospital mortality among MF patients presenting to the ED from 2006 to 2015. Conclusions Our study highlights factors crucial for risk-stratification for hospitalized MF patients.

Meeting Dermatologic Needs in an Uninsured Population: Lessons Learned from a Referrals Cohort at a Student-Run Free Clinic.

Unmet dermatologic needs of the uninsured patient population are important to identify and address, especially as the COVID-19 pandemic has introduced additional barriers of access to care. We describe the successful collaboration between a student-run free clinic and dermatology practice since 2012, highlighting excellent time to appointment intervals and resolution rates as well as the associated modest financial cost. We believe that the information provided in our report may serve as a proof of concept and facilitate the implementation of such collaborations throughout the United States.