Daily Cosmetic Research Analysis
Analyzed 18 papers and selected 3 impactful papers.
Summary
Analyzed 18 papers and selected 3 impactful articles.
Selected Articles
1. Evaluating Large Language Models as Medical Consultation Tools for Double Eyelid Surgery: A Cross-Language Study in English and Chinese.
Across 16 common patient questions, 15 LLMs were benchmarked in English and Chinese using expert multidimensional scoring and appropriate nonparametric statistics. ERNIE-Bot, ChatGPT-4o, and Gemini-2.0-Flash led in English, while DeepSeek-R1 dominated in Chinese, indicating LLMs can meaningfully support preoperative counseling for double eyelid surgery with model- and language-dependent performance.
Impact: Introduces a structured, cross-language benchmarking of LLMs for a high-volume cosmetic procedure, highlighting immediate opportunities and boundaries for AI-augmented patient education.
Clinical Implications: Clinics can triage and standardize pre-consultation information for blepharoplasty using top-performing LLMs with surgeon oversight, potentially reducing workload and improving patient understanding.
Key Findings
- Top English performers: ERNIE-Bot, ChatGPT-4o, Gemini-2.0-Flash across most dimensions.
- Top Chinese performers: DeepSeek-R1 (leading), with DeepSeek-V3, Gemini-2.0-Flash, and ERNIE-Bot in the first tier.
- Lower-performing models showed significant gaps versus leaders by Friedman and Nemenyi tests.
- Expert scoring covered professionalism, patient friendliness, informativeness, practicality, and logical clarity.
Methodological Strengths
- Cross-language evaluation with 15 LLMs and 16 real-world questions
- Expert multidimensional scoring and appropriate nonparametric statistical comparisons
Limitations
- No assessment of patient outcomes, safety, or legal/ethical compliance in real clinical settings
- Topic-limited (double eyelid surgery) and results may drift as models update
Future Directions: Fine-tune LLMs on specialty datasets, prospectively validate in clinic with patient-centered outcomes, and develop surgeon-LLM workflows and guardrails for safe deployment.
BACKGROUND: Double eyelid surgery is a common cosmetic procedure that creates a crease in the upper eyelid. Due to insufficient understanding of the procedure, numerous consultations have emerged, placing a heavy burden on plastic surgeons. The rise of large language models (LLMs) offers a potential solution to this issue. METHODS: This study collected sixteen questions commonly of concern to individuals seeking the surgery via an online questionnaire and assessed the efficacy of fifteen popular LLMs in answering these questions with both English and Chinese inputs. All responses from the LLMs were scored multidimensionally by three expert eyelid plastic surgeons across dimensions including professionalism, patient friendliness, informativeness, practicality, and logical clarity. The scoring results were statistically analyzed using the Friedman test and Nemenyi post-hoc test. RESULTS: With English input, ERNIE-Bot, ChatGPT-4o, and Gemini-2.0-Flash consistently ranked among the top three across most evaluation dimensions. In contrast, Claude-3.7-Sonnet, HuatuoGPT, ZoeGPT, CompliantGPT, and BastionGPT ranked lower across all dimensions, with performance significantly lagging behind the top performers. For Chinese input, DeepSeek-R1 maintained a leading position across all dimensions, forming the first tier alongside DeepSeek-V3, Gemini-2.0-Flash, and ERNIE-Bot. Meanwhile, Claude-3.5-Haiku, ZoeGPT, Llama3.3-70B-Instruct, CompliantGPT, HuatuoGPT, and BastionGPT ranked lower in multiple dimensions, with a significant gap relative to first-tier models. CONCLUSION: This study demonstrated LLMs' potential as medical consultation tools for double eyelid surgery, providing useful guidance for both English and Chinese users. Future research should focus on fine-tuning LLMs with more specialized medical data and exploring workflows for surgeon-LLM collaboration to validate their clinical utility. LEVEL OF EVIDENCE V: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
2. Costs, Coverage, and Complications: Disparities in Inpatient Alloplastic Facial Implants in the US Healthcare System.
National inpatient data (2016–2020) reveal income-, insurance-, and geography-linked disparities in access to alloplastic facial implants. Complications are uncommon but costs are high; rural and low-income patients are especially disadvantaged, notably for facial feminization surgery, underscoring the need for standardized coverage and better outpatient data.
Impact: Quantifies structural inequities in a mix of functional and aesthetic facial implants, informing payer policy, coverage decisions, and health system planning for gender-affirming care.
Clinical Implications: Encourages payers and health systems to standardize coverage, expand access (especially for facial feminization), and monitor outcomes across inpatient and outpatient settings to reduce inequities.
Key Findings
- Lower-income patients were more likely publicly insured, had longer length of stay, and were underrepresented in cosmetic and gender dysphoria-related procedures.
- Higher-income, urban patients more frequently self-paid for elective implants, clustering in large metropolitan and Pacific regions.
- Overall inpatient complication rates were low, but costs were high; rural and low-income patients faced pronounced barriers, especially for facial feminization surgery.
Methodological Strengths
- Use of a national inpatient database (HCUP-NIS) spanning 5 years
- Socioeconomic, insurance, and geographic stratification with cost and complication metrics
Limitations
- Small cohort size (n=68) and restriction to inpatient cases; outpatient procedures not captured
- Retrospective design with potential coding/misclassification bias and unmeasured confounders
Future Directions: Link inpatient and outpatient datasets, incorporate qualitative work with marginalized groups, and evaluate the impact of standardized coverage policies on access and outcomes.
This study investigates how socioeconomic status, insurance type, and geography shape access to inpatient synthetic facial implant surgery in the United States. Using HCUP-NIS data from 2016 to 2020 (n=68), the authors show that lower-income patients are more likely to be publicly insured, experience significantly longer hospital stays, and are underrepresented in cosmetic and gender dysphoria-related procedures, while higher-income, urban patients more often self-pay for elective implants clustered in large metropolitan and Pacific regions. Despite low overall complication rates, inpatient admissions are associated with high costs, and rural and low-income patients face pronounced barriers to care, particularly for facial feminization surgery. This work highlights the need for broader outpatient data capture, qualitative research among marginalized groups, and standardized insurance coverage policies to promote equitable, cost-effective access to functional and aesthetic facial implant procedures.
3. Physico-chemical behaviour and microbiological suitability of residual smectitic soils mixed with two mineralized waters for therapeutic and dermocosmetic applications.
Comparative physicochemical and microbiological profiling of peloids made from three smectitic soils and two mineralized waters showed marked increases in conductivity and organic matter with seawater and higher cation exchange capacity with thermo-mineral water. Despite alkaline pH and stable zeta potential, Pb/Co/Ni/V exceeded cosmetic/pharma limits and fungal counts were slightly above recommendations in thermo-mineral formulations.
Impact: Provides actionable safety signals for dermocosmetic muds, emphasizing heavy metal exceedances and microbiological quality that must be addressed before therapeutic or cosmetic use.
Clinical Implications: Clinicians and spas should require dermal bioaccessibility testing and microbiological control before recommending peloid therapies; current formulations may not meet cosmetic/pharmaceutical safety thresholds.
Key Findings
- Seawater raised electrical conductivity from 0.3–0.5 to 68.0–73.8 mS/cm and increased organic matter to ~7%.
- Thermo-mineral water increased cation exchange capacity to 55.2–86.6 meq/100 g; pH remained alkaline and zeta potential stable.
- Pb, Co, Ni, and V exceeded cosmetic/pharmaceutical limits; fecal indicators were absent but thermo-mineral peloids had slightly elevated fungal content.
Methodological Strengths
- Comprehensive physicochemical and microbiological assessment across multiple formulations
- Direct comparison of seawater versus thermo-mineral water effects on peloid properties
Limitations
- No dermal bioaccessibility testing or in vivo safety assessment to quantify patient exposure risk
- Thermal and rheological properties not evaluated, limiting clinical handling insights
Future Directions: Conduct dermal bioaccessibility and toxicokinetic studies, implement microbial mitigation, and evaluate thermal/rheological properties to define safe, clinically suitable peloid formulations.
Peloid is a matured mud with healing and/or cosmetic properties, composed of a complex mixture of mineral or seawater with a clay-based material, that requires quality control prior to its application in therapeutic and dermocosmetic treatments. In this research, physico-chemical and biological analyses were performed to assess influence of the two mineralized waters on three residual smectitic soils. Seawater increased the electrical conductivity values of peloids (from 0.3 to 0.5 mS/cm to 68.0-73.8 mS/cm) and their organic matter content (from 2.6 to 4.7% to around 7%), whereas thermo-mineral water enhanced the cation exchange capacity (from 38.4 to 70.0 meq/100 g to 55.2-86.6 meq/100 g). The pH of peloids remained alkaline, and zeta potential values were stable throughout the maturation period. The concentrations of Pb, Co, Ni and V in samples exceed the acceptable limits established for cosmetic and pharmaceutical products, hence further dermal bioacessibility assessment are required to substantiate their clinical safety before therapeutic use. Moreover, fecal indicator bacteria were not detected in the peloids, however thermo-mineral water peloids showed fungal contents slightly above recommended microbiological limits. The physico-chemical and microbiological characterization suggests that these peloids have potential therapeutic values, although further thermal and rheological characterization are required to assess their suitability.