ABSTRACT
BACKGROUND: Dermatologic patient education materials (PEMs) are often written above the national average seventh- to eighth-grade reading level. ChatGPT-3.5, GPT-4, DermGPT, and DocsGPT are large language models (LLMs) that are responsive to user prompts. Our project assesses their use in generating dermatologic PEMs at specified reading levels. OBJECTIVE: This study aims to assess the ability of select LLMs to generate PEMs for common and rare dermatologic conditions at unspecified and specified reading levels. Further, the study aims to assess the preservation of meaning across such LLM-generated PEMs, as assessed by dermatology resident trainees. METHODS: The Flesch-Kincaid reading level (FKRL) of current American Academy of Dermatology PEMs was evaluated for 4 common (atopic dermatitis, acne vulgaris, psoriasis, and herpes zoster) and 4 rare (epidermolysis bullosa, bullous pemphigoid, lamellar ichthyosis, and lichen planus) dermatologic conditions. We prompted ChatGPT-3.5, GPT-4, DermGPT, and DocsGPT to "Create a patient education handout about [condition] at a [FKRL]" to iteratively generate 10 PEMs per condition at unspecified fifth- and seventh-grade FKRLs, evaluated with Microsoft Word readability statistics. The preservation of meaning across LLMs was assessed by 2 dermatology resident trainees. RESULTS: The current American Academy of Dermatology PEMs had an average (SD) FKRL of 9.35 (1.26) and 9.50 (2.3) for common and rare diseases, respectively. For common diseases, the FKRLs of LLM-produced PEMs ranged between 9.8 and 11.21 (unspecified prompt), between 4.22 and 7.43 (fifth-grade prompt), and between 5.98 and 7.28 (seventh-grade prompt). For rare diseases, the FKRLs of LLM-produced PEMs ranged between 9.85 and 11.45 (unspecified prompt), between 4.22 and 7.43 (fifth-grade prompt), and between 5.98 and 7.28 (seventh-grade prompt). At the fifth-grade reading level, GPT-4 was better at producing PEMs for both common and rare conditions than ChatGPT-3.5 (P=.001 and P=.01, respectively), DermGPT (P<.001 and P=.03, respectively), and DocsGPT (P<.001 and P=.02, respectively). At the seventh-grade reading level, no significant difference was found between ChatGPT-3.5, GPT-4, DocsGPT, or DermGPT in producing PEMs for common conditions (all P>.05); however, for rare conditions, ChatGPT-3.5 and DocsGPT outperformed GPT-4 (P=.003 and P<.001, respectively). The preservation of meaning analysis revealed that for common conditions, DermGPT ranked the highest for overall ease of reading, patient understandability, and accuracy (14.75/15, 98%); for rare conditions, handouts generated by GPT-4 ranked the highest (14.5/15, 97%). CONCLUSIONS: GPT-4 appeared to outperform ChatGPT-3.5, DocsGPT, and DermGPT at the fifth-grade FKRL for both common and rare conditions, although both ChatGPT-3.5 and DocsGPT performed better than GPT-4 at the seventh-grade FKRL for rare conditions. LLM-produced PEMs may reliably meet seventh-grade FKRLs for select common and rare dermatologic conditions and are easy to read, understandable for patients, and mostly accurate. LLMs may play a role in enhancing health literacy and disseminating accessible, understandable PEMs in dermatology.
Subject(s)
Dermatology , Patient Education as Topic , Skin Diseases , Humans , Patient Education as Topic/methods , Dermatology/education , Reading , Qualitative Research , Language , Health Literacy , Teaching MaterialsABSTRACT
BACKGROUND/OBJECTIVES: The emergency department (ED) is a common point of care for many pediatric hidradenitis suppurativa (HS) patients; however, ED care may not align with recommended treatment standards. The objective of this study is to describe the care pediatric HS patients receive in the ED compared to both HS management guidelines and the management of pediatric skin and soft tissue abscess (SSTA) patients. METHODS: We performed a retrospective chart review of pediatric HS and SSTA patients who presented to a single pediatric ED. Demographic and ED encounter data including medications, procedures, recommendations, consults, and referrals were collected. RESULTS: 58 HS and 175 SSTA charts were reviewed. 69.5% of patients were female and 93.6% were African American/Black. 29.3% of HS and 61.7% of SSTA encounters involved incision and drainage (I&D); 62.1% of HS and 70.1% of SSTA encounters involved the prescription or administration of oral clindamycin; 3.4% of HS and 0.6% of SSTA encounters involved dermatology consultation in the ED; and 22.4% of HS and 5.1% of SSTA encounters involved outpatient referrals to dermatology. CONCLUSIONS: Our data reveal a pediatric HS and SSTA population that is predominantly female and African American/Black. Significant differences were found in the average ages and number of lesions between HS and SSTA patients. I&D and oral clindamycin were the most common treatments across groups; however, I&D was performed significantly more frequently among SSTA encounters than HS encounters. Our results suggest that subtle knowledge gaps may exist in ED provider management of pediatric HS.
Subject(s)
Hidradenitis Suppurativa , Humans , Female , Child , Male , Hidradenitis Suppurativa/therapy , Hidradenitis Suppurativa/drug therapy , Retrospective Studies , Clindamycin/therapeutic use , Emergency Service, HospitalABSTRACT
Understanding the utility of virtual visits in pediatric dermatology practice has become increasingly important in the telehealth era. We compared the conditions diagnosed in pediatric dermatology between traditional in-person visits and virtual telehealth visits during the initial 8-month phase of the COVID-19 pandemic at an urban medical institution. When given the option, pediatric dermatology patients and their families were more likely to choose telehealth visits for the diagnosis and/or management of acne, hemangiomas, and contact dermatitis; however, they were more likely to choose in-person visits for atopic dermatitis, viral warts, and alopecia areata. These differences may be attributed to clinical features of pediatric skin conditions, treatment options, and other factors which may influence patient preference for telehealth or in-person care for their condition. J Drugs Dermatol. 2022;21(11):1260-1263. doi:10.36849/JDD.6843.
Subject(s)
COVID-19 , Dermatology , Skin Diseases , Telemedicine , Humans , Child , COVID-19/epidemiology , Pandemics , Skin Diseases/diagnosis , Skin Diseases/epidemiology , Skin Diseases/therapyABSTRACT
Fireworks injuries can result in devastating cutaneous burns and may be further complicated in the head and neck region by the presence of specialized deeper structures. In the United States, the head and neck remain the most commonly injured sites, with the majority of these injuries constituting burns. We present an adult patient who suffered an accidental right cheek burn injury and went on to experience a complex pattern of findings including pneumomediastinum, facial nerve palsy, and sialocele formation.