Aesthetic plastic surgery · 2026
Scrolling for Surgery: Artificial Intelligence-Powered Evaluation of Labiaplasty Discourse on TikTok.
СтатьяНаблюдательное исследованиеНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Escandón Lauren, Flaherty Emily, Santore Lee Ann, De la Cruz Ku Gabriel, Ciudad Pedro, Manrique Oscar J, Escandón Joseph M
Аннотация
BACKGROUND: Labiaplasty has experienced growing popularity, with over 10,800 procedures performed annually in the USA. Discussions about this surgery are shifting to social media, particularly TikTok, where health information is often presented with limited regulation or oversight. This raises concerns about the accuracy, quality, and influence of labiaplasty-related content.
METHODS: We conducted a cross-sectional observational study analyzing the 110 most relevant TikTok videos under the term "labiaplasty" (July-August 2025). Video characteristics, engagement metrics (likes, shares, comments), and creator types were recorded. Content quality was assessed using the Global Quality Scale (GQS) by human reviewers and an AI model (ChatGPT-4.5-turbo). Sentiment analysis of video comments was performed by two human raters and the AI model. Statistical analyses included Wilcoxon signed-rank and Mann-Whitney U tests.
RESULTS: Surgeons (52%) and patients (40%) produced most videos, primarily on educational (39%) or postoperative (28%) content. Overall, median human-rated GQS was 3.5 [IQR, 2.13-4.88], while the AI median was 3 [IQR, 2-4]. Videos with ≥2000 likes were more often created by patients (52% vs. 32%, p=0.012) and had significantly lower GQS scores (human: 2.5 vs. 4, p=0.003; AI: 2 vs. 3, p<0.001). Human inter-rater reliability for sentiment classification was slight (κ=0.161), with minimal agreement between AI and humans (κ=0.077).
CONCLUSION: Labiaplasty content on TikTok is predominantly generated by surgeons and patients, yet lower-quality videos achieve higher engagement. Surgeons should proactively create accurate, relatable content to counterbalance misinformation. Refinement of AI tools is needed for reliable quality and sentiment assessment on social media.
LEVEL OF EVIDENCE IV: 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 .
METHODS: We conducted a cross-sectional observational study analyzing the 110 most relevant TikTok videos under the term "labiaplasty" (July-August 2025). Video characteristics, engagement metrics (likes, shares, comments), and creator types were recorded. Content quality was assessed using the Global Quality Scale (GQS) by human reviewers and an AI model (ChatGPT-4.5-turbo). Sentiment analysis of video comments was performed by two human raters and the AI model. Statistical analyses included Wilcoxon signed-rank and Mann-Whitney U tests.
RESULTS: Surgeons (52%) and patients (40%) produced most videos, primarily on educational (39%) or postoperative (28%) content. Overall, median human-rated GQS was 3.5 [IQR, 2.13-4.88], while the AI median was 3 [IQR, 2-4]. Videos with ≥2000 likes were more often created by patients (52% vs. 32%, p=0.012) and had significantly lower GQS scores (human: 2.5 vs. 4, p=0.003; AI: 2 vs. 3, p<0.001). Human inter-rater reliability for sentiment classification was slight (κ=0.161), with minimal agreement between AI and humans (κ=0.077).
CONCLUSION: Labiaplasty content on TikTok is predominantly generated by surgeons and patients, yet lower-quality videos achieve higher engagement. Surgeons should proactively create accurate, relatable content to counterbalance misinformation. Refinement of AI tools is needed for reliable quality and sentiment assessment on social media.
LEVEL OF EVIDENCE IV: 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 .