Citations

Background/Objectives: Facial analysis is critical for preoperative planning in facial plastic surgery, but traditional methods can be time consuming and subjective. This study investigated the potential of Artificial Intelligence (AI) for objective and efficient facial analysis in plastic surgery, with a specific focus on Multimodal Large Language Models (MLLMs). We evaluated their ability to analyze facial skin quality, volume, symmetry, and adherence to aesthetic standards such as neoclassical facial canons and the golden ratio. Methods: We evaluated four MLLMs—ChatGPT-4o, ChatGPT-4, Gemini 1.5 Pro, and Claude 3.5 Sonnet—using two evaluation forms and 15 diverse facial images generated by a Generative Adversarial Network (GAN). The general analysis form evaluated qualitative skin features (texture, type, thickness, wrinkling, photoaging, and overall symmetry). The facial ratios form assessed quantitative structural proportions, including division into equal fifths, adherence to the rule of thirds, and compatibility with the golden ratio. MLLM assessments were compared with evaluations from a plastic surgeon and manual measurements of facial ratios. Results: The MLLMs showed promise in analyzing qualitative features, but they struggled with precise quantitative measurements of facial ratios. Mean accuracy for general analysis were ChatGPT-4o (0.61 ± 0.49), Gemini 1.5 Pro (0.60 ± 0.49), ChatGPT-4 (0.57 ± 0.50), and Claude 3.5 Sonnet (0.52 ± 0.50). In facial ratio assessments, scores were lower, with Gemini 1.5 Pro achieving the highest mean accuracy (0.39 ± 0.49). Inter-rater reliability, based on Cohen’s Kappa values, ranged from poor to high for qualitative assessments (κ > 0.7 for some questions) but was generally poor (near or below zero) for quantitative assessments. Conclusions: Current general purpose MLLMs are not yet ready to replace manual clinical assessments but may assist in general facial feature analysis. These findings are based on testing models not specifically trained for facial analysis and serve to raise awareness among clinicians regarding the current capabilities and inherent limitations of readily available MLLMs in this specialized domain. This limitation may stem from challenges with spatial reasoning and fine-grained detail extraction, which are inherent limitations of current MLLMs. Future research should focus on enhancing the numerical accuracy and reliability of MLLMs for broader application in plastic surgery, potentially through improved training methods and integration with other AI technologies such as specialized computer vision algorithms for precise landmark detection and measurement.

ImportanceUnderstanding the global barriers to otolaryngology–head and neck surgery (OHNS) care is crucial in addressing disparities in access to care, particularly in low-income and middle-income countries (LMICs).ObjectiveTo characterize barriers to comprehensive otolaryngology care across World Bank income groups.Design, Setting, and ParticipantsUsing an online cross-sectional survey that was administered by the Global OHNS Initiative via international and national professional societies, personal contacts, and social media, this study captured the perceptions of otolaryngologists regarding barriers to OHNS care at the levels of the country, health sector, clinician, and patient. Participants included otolaryngologists from the 194 World Health Organization member states and Taiwan. Eligibility criteria included a medical degree and specialized training in managing conditions of the ear, nose, and throat. The nonresponse rate was not recorded. The data collection period spanned from October 2022 to June 2023.ExposuresExposures included World Bank income group classification.Main Outcomes and MeasuresThe primary outcomes were Likert scale responses regarding frequency of barriers to OHNS care. The a priori hypothesis was that LMICs would report more frequent barriers to OHNS care.ResultsThe study involved 146 otolaryngologists (47 female individuals [32%]), with 69 (47%) from high-income countries and 77 (53%) from LMICs. Male individuals represented 45 high-income country respondents (65%) and 54 LMIC respondents (70%). Barriers were reported across income groups at all levels of the health system, with a higher frequency in LMICs. Several barriers were reported to be more substantial in LMICs, such as the national volume and distribution of otolaryngologists, financial compensation for clinicians, and patient stigma, and others were common across income settings, such as the availability of operating rooms and inflexible working hours. Common concerns included national and health sector barriers: OHNS workforce, referral networks, government support; clinician barriers: excessive clinician workloads, understaffing, poor administration support; patient barriers: distance to health care facilities, financial burdens such as medical costs and foregone wages, stigma, and health literacy.Conclusions and RelevanceThe results of this cross-sectional study suggest that there are barriers to otolaryngology care globally that affected all levels of the health care system. This work may inform prioritization of otolaryngology within research and policy, and it emphasizes the need for effective strategies to expand access to otolaryngology care, particularly in lower-income settings.

Background: Anatomically accurate illustrations are imperative in medical education, serving as crucial tools to facilitate comprehension of complex anatomical structures. While traditional illustration methods involving human artists remain the gold standard, the rapid advancement of Generative Artificial Intelligence (GAI) models presents a new opportunity to automate and accelerate this process. This study evaluated the potential of GAI models to produce craniofacial anatomy illustrations for educational purposes. Methods: Four GAI models, including Midjourney v6.0, DALL-E 3, Gemini Ultra 1.0, and Stable Diffusion 2.0 were used to generate 736 images across multiple views of surface anatomy, bones, muscles, blood vessels, and nerves of the cranium in both oil painting and realistic photograph styles. Four reviewers evaluated the images for anatomical detail, aesthetic quality, usability, and cost-effectiveness. Inter-rater reliability analysis assessed evaluation consistency. Results: Midjourney v6.0 scored highest for aesthetic quality and cost-effectiveness, and DALL-E 3 performed best for anatomical detail and usability. The inter-rater reliability analysis demonstrated a high level of agreement among reviewers (ICC = 0.858, 95% CI). However, all models showed significant flaws in depicting crucial anatomical details such as foramina, suture lines, muscular origins/insertions, and neurovascular structures. These limitations were further characterized by abstract depictions, mixing of layers, shadowing, abnormal muscle arrangements, and labeling errors. Conclusions: These findings highlight GAI’s potential for rapidly creating craniofacial anatomy illustrations but also its current limitations due to inadequate training data and incomplete understanding of complex anatomy. Refining these models through precise training data and expert feedback is vital. Ethical considerations, such as potential biases, copyright challenges, and the risks of propagating inaccurate information, must also be carefully navigated. Further refinement of GAI models and ethical safeguards are essential for safe use.

ABSTRACTImportanceHighlighting the global disparities in otolaryngology training and, ultimately, service delivery, emphasizing the need for equitable access to training resources and programs.ObjectiveTo describe the relationship between the quality, content, and location of otolaryngology–head and neck surgery training and education and the resulting impact on the delivery of otolaryngology care globally.DesignAn online cross‐sectional survey to otolaryngologists, gathering information on their training and education experiences, and factors influencing their choice of training location and practice.SettingThe online survey was available in multiple languages, distributed via national and international professional otolaryngology societies, snowballing and social media.ParticipantsThe respondents were practicing otolaryngologists representing all seven World Health Organization regions.ExposuresWorld Bank income groups classification.Main Outcomes and MeasuresOur expected outcome was that subspecialty training and access to educational resources were significantly readily available to respondents from high‐income countries, leading to more confidence in performing complex procedures post training.ResultsA total of 91 participants were included in the analysis, with 47 (52%) practicing in high‐income countries and 44 (48%) in low‐ and middle‐income countries. Sixty‐one participants (67%) were male. Subspecialty training and access to educational resources were significantly less available in low‐ and middle‐income countries, leading to lower confidence among low‐ and middle‐income countries physicians in performing complex procedures. High‐income country respondents reported better access to diverse training resources and felt more prepared for a broader range of procedures.Conclusion and RelevanceSignificant disparities exist in OHNS training resources and subspecialty training opportunities between high‐ and low‐middle‐income countries. There is a critical need to integrate complementary training and educational modalities into local systems. Addressing the shortage of educational resources and promoting open‐access initiatives in low‐middle‐income countries are essential steps toward enhancing surgical education and improving global otolaryngology healthcare outcomes.

ABSTRACT Objective Availability of surgical equipment and access to essential clinical services remains an important barrier to surgical care delivery, particularly in low‐ and middle‐income countries (LMICs). This study aims to characterize the relative availability of essential equipment for otolaryngology‐head and neck surgery (OHNS) care across World Bank income groups. Methods We conducted a cross‐sectional survey on otolaryngologists' perceptions on the availability of surgical equipment and ancillary services in their respective practice settings per a 5‐point Likert scale ranging from never to always available. The study was disseminated online via professional societies, personal contacts, and social media. Eligible participants included otolaryngologists from 194 WHO‐recognized countries, which were grouped by World Bank income group classification and WHO region. Results The study involved 146 otolaryngologists, 69 (47%) from high‐income countries (HICs), and 77 (53%) from LMICs. LMIC respondents were predominantly from the African and South‐East Asian regions, which comprised 48% and 7.8% of all LMIC respondents, respectively. Results revealed significant differences in the availability of otologic, rhinologic, and endoscopic airway equipment between HICs and LMICs. Differences existed among commonly used equipment such as tympanomastoidectomy equipment and rigid bronchoscopy, to subspecialized equipment such as functional endoscopic sinus surgery equipment and cochlear implants ( p < 0.05 each). Conclusions The study highlighted key disparities in the availability of essential equipment for baseline OHNS care, especially for pediatric airway and otologic conditions. These results can be used to guide investment and advocacy efforts to improve specialty‐specific surgical infrastructure relative to the global burden of OHNS diseases in low‐resource settings. Level of Evidence 3

Artificial intelligence (AI) is not merely a tool for the future of clinical medicine; it is already reshaping the landscape, challenging traditional paradigms, and expanding the horizons of what is achievable in healthcare [...]

Accurate identification of surgical instruments is crucial for efficient workflows and patient safety within the operating room, particularly in preventing complications such as retained surgical instruments. Artificial Intelligence (AI) models have shown the potential to automate this process. This study evaluates the accuracy of publicly available Large Language Models (LLMs)—ChatGPT-4, ChatGPT-4o, and Gemini—and a specialized commercial mobile application, Surgical-Instrument Directory (SID 2.0), in identifying surgical instruments from images. The study utilized a dataset of 92 high-resolution images of 25 surgical instruments (retractors, forceps, scissors, and trocars) photographed from multiple angles. Model performance was evaluated using accuracy, weighted precision, recall, and F1 score. ChatGPT-4o exhibited the highest accuracy (89.1%) in categorizing instruments (e.g., scissors, forceps). SID 2.0 (77.2%) and ChatGPT-4 (76.1%) achieved comparable accuracy, while Gemini (44.6%) demonstrated lower accuracy in this task. For precise subtype identification of instrument names (like “Mayo scissors” or “Kelly forceps”), all models had low accuracy, with SID 2.0 having an accuracy of 39.1%, followed by ChatGPT-4o (33.69%). Subgroup analysis revealed ChatGPT-4 and 4o recognized trocars in all instances. Similarly, Gemini identified surgical scissors in all instances. In conclusion, publicly available LLMs can reliably identify surgical instruments at the category level, with ChatGPT-4o demonstrating an overall edge. However, precise subtype identification remains a challenge for all models. These findings highlight the potential of AI-driven solutions to enhance surgical-instrument management and underscore the need for further refinements to improve accuracy and support patient safety.

Background: Chordoma is a rare bone cancer with limited treatment options. Clinical trials are crucial for developing effective therapies, but their success depends on including diverse patient populations. The objective of this study was to systematically evaluate the reporting of racial, ethnic, and socioeconomic diversity in United States clinical trials exploring treatment for chordoma. Methods: A literature search was conducted through PubMed/Medline, Cochrane, Epistemonikos, and ClinicalTrials.gov databases for published US chordoma trials up until 19 August 2024. The data collected included trial characteristics and racial and ethnic data, as well as socioeconomic indicators when available. Methodological Index for Non-Randomized Studies (MINORS) and Revised Cochrane Risk-of-Bias Tool for Randomized Trials (RoB2) analyses were adopted to assess the methodological quality. The N-1 Chi-squared (χ2) test was implemented to compare the reported racial and ethnic data with the most recent US Census Bureau data. Results: Five trials involving 111 patients (median age: 63 years; 34% female) were included. Four studies (80%) were single-arm non-randomized studies with one study (25%) having a high methodological quality and three (75%) having a moderate quality based on the MINORS analysis. Most patients (91%, n = 82) were White/Caucasian, representing a proportion which was significantly higher than the reported 75% in the US population (p = 0.0005). Black/African American patients (2%, n = 2) were significantly underrepresented compared to the 14% in the US population (p = 0.0015). Regarding ethnicity, Hispanic/Latino patients (7%, n = 6) were significantly underrepresented compared to the 20% in the US population (p = 0.0021). No measures of socioeconomic status were reported. Conclusions: This systematic review highlighted the need for improved racial and ethnic diversity in chordoma trials and the better reporting of socioeconomic data. The underrepresentation of minority groups may obscure potential disparities in disease incidence, treatment access, and clinical outcomes.