RESUMO
OBJECTIVES: This systematic review and meta-analysis aimed to estimate the rate of taste disturbance following cochlear implantation. METHODS: The review was designed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Included studies psychophysically measured taste. DerSimonian and Laird random-effects models were used. An overall mean from studies reporting a single mean of taste strip performance was calculated using inverse variance method for pooling. RESULTS: Of 380 studies identified, 9 were included across which 55 cases of postoperative taste disturbance were reported in 498 patients. Taste was tested at variable timepoints, from <1 week to ≥6 months postoperatively. The overall rate of postoperative taste disturbance was 13.5% (95% CI, 7.6-20.7%) with high heterogeneity between studies (I2 = 62%). DISCUSSION: 13.5% might indicate a higher prevalence of taste disturbance following cochlear implantation compared to the general population. However, the confidence we can assign to our calculated rate is limited by significant heterogeneity and potential publication bias. Studies reporting mean taste strip scores generally found reduced taste function on the side of the tongue ipsilateral to implantation, but this reduction wasn't statistically significant. CONCLUSION: Further research, employing more robust and standardised methodologies, is necessary to accurately ascertain the rate and nature of taste disturbance following cochlear implantation.
RESUMO
OBJECTIVE: The present study challenges the appropriateness of considering invasion of the palatoglossus muscle (PGM) as a criterion for staging oropharyngeal squamous cell carcinoma (OPSCC) as T4. STUDY DESIGN: Retrospective observational study. SETTING: Tertiary University Hospital. METHODS: This retrospective study included nonmetastatic OPSCC patients treated with curative intent at the University of Trieste, Italy from 2015 to 2021. Patients were categorized into 4 groups: (1) tumors classified as T1-T2 by both International Cancer Control (UICC) and American Joint Committee on Cancer (AJCC)-TNM; (2) T1-T2 tumors upgraded to T4 solely by UICC due to oropharyngeal PGM infiltration; (3) T1-T2 tumors upgraded to T4 by both UICC and AJCC due to oral PGM infiltration; (4) tumors classified as T3-T4 by both UICC and AJCC. Kaplan-Meier analysis estimated overall survival (OS) and disease-free survival (DFS). Multivariable Cox models, adjusted for clinical factors, assessed the impact of palatoglossus invasion on outcomes over 5 years. RESULTS: A total of 121 consecutive patients with primary OPSCC were included (median [interquartile range] age 65 years [58-74]; 63% male). While patients with upgraded T4 category due to infiltration of the oral portion of the PGM exhibited a prognosis superimposable on that of other patients with advanced stage disease, those with upgraded T4 category due to infiltration of the oropharyngeal portion of the PGM displayed OS and DFS comparable to T1-T2 patients. CONCLUSION: Our findings highlight that invasion of the oropharyngeal portion of the PGM may not be a suitable criterion for staging OPSCC as T4. Further research involving larger and independent patient cohorts is strongly encouraged to corroborate these observations.
RESUMO
Mild cognitive impairment (MCI) is a significant concern as it is a risk factor for AD progression, and early detection is vital in order to delay dementia onset and enable potential therapeutic interventions. Olfactory impairment is recognized as a predictive biomarker in neurodegenerative processes. The aims of this study were to explore the degree of entorhinal cortical atrophy (ERICA) and the severity of MCI symptoms; to analyze magnetic resonance imaging (MRI) results for the entorhinal cortex, parahippocampal gyrus, peri entorhinal cortex, and the cerebellar tentorium; and to perform a comprehensive neuropsychological and psychophysical assessment. The main results highlighted that in our sample-multidomain amnesic MCI patients with hyposmic symptomatology-we found that ERICA scores were associated with the severity of anxiety symptomatology. One possible hypothesis to explain this observation is that anxiety may contribute to neurodegenerative processes by inducing chronic stress and inflammation. Future research should consider the longitudinal development of neuropsychological scores, anxiety disorders, and brain atrophy to determine their potential predictive value for MCI progression. These findings suggest the importance of psychological factors in MCI progression and the utility of neuropsychological assessment alongside neuroimaging techniques for early detection and follow-up in MCI patients.
RESUMO
PURPOSE: The choice of surgical approach for floor of the mouth (FOM) cancer, particularly for intermediate-stage tumors (cT2-cT3), remains controversial. This study aims to evaluate a method considering mylohyoid muscle (MM) invasion as a determinant for surgical approach selection, utilizing magnetic resonance imaging (MRI) preoperatively and frozen section (FS) analysis intraoperatively. METHODS: This observational retrospective cohort study analyzed patients undergoing surgical resection of cT2 and cT3 FOM squamous cell carcinoma (SCC) between January 2013 and June 2023. MM infiltration assessed by preoperative MRI determined the surgical approach: clear infiltration led to compartmental surgery (CS), while doubtful or absent infiltration led to transoral surgery (TOS). Conversion from TOS to CS occurred intraoperatively based on macroscopic evidence or positive FS. Data collected included demographic, clinical, surgical, and pathological variables. Survival analysis was conducted using Kaplan-Meier method. RESULTS: Among 44 patients included, majority had cT2 tumors (59.1%). MM resection was necessary in 22.7% of cases. Overall survival (OS) and progression-free survival (PFS) did not significantly differ between TOS and CS groups. Radiological depth of invasion (rDOI) < 10 mm is correlated with MM preservation in 89% of cases, while rDOI > 10 mm is correlated with MM resection only in 23.8% of cases. Pathological depth of invasion (pDOI) discrepancies were observed in the two groups: in CS group is shown a higher pDOI (> 10 mm) confirmation (90%). Surgical complications and functional outcomes differed between TOS and CS groups. CONCLUSION: Considering MM invasion for surgical approach selection in cT2-cT3 FOM tumors appears oncologically safe, with better functional outcomes in muscle preservation. Preoperative MRI for MM assessment combined with intraoperative FS analysis provides reliable guidance for surgical decision-making.
Assuntos
Secções Congeladas , Imageamento por Ressonância Magnética , Neoplasias Bucais , Invasividade Neoplásica , Estadiamento de Neoplasias , Humanos , Masculino , Feminino , Estudos Retrospectivos , Imageamento por Ressonância Magnética/métodos , Pessoa de Meia-Idade , Neoplasias Bucais/cirurgia , Neoplasias Bucais/patologia , Neoplasias Bucais/diagnóstico por imagem , Idoso , Soalho Bucal/cirurgia , Soalho Bucal/patologia , Soalho Bucal/diagnóstico por imagem , Carcinoma de Células Escamosas/cirurgia , Carcinoma de Células Escamosas/patologia , Carcinoma de Células Escamosas/diagnóstico por imagem , Idoso de 80 Anos ou mais , Músculos do Pescoço/patologia , Músculos do Pescoço/cirurgia , Músculos do Pescoço/diagnóstico por imagem , AdultoRESUMO
PURPOSE: This study evaluates the efficacy of two advanced Large Language Models (LLMs), OpenAI's ChatGPT 4 and Google's Gemini Advanced, in providing treatment recommendations for head and neck oncology cases. The aim is to assess their utility in supporting multidisciplinary oncological evaluations and decision-making processes. METHODS: This comparative analysis examined the responses of ChatGPT 4 and Gemini Advanced to five hypothetical cases of head and neck cancer, each representing a different anatomical subsite. The responses were evaluated against the latest National Comprehensive Cancer Network (NCCN) guidelines by two blinded panels using the total disagreement score (TDS) and the artificial intelligence performance instrument (AIPI). Statistical assessments were performed using the Wilcoxon signed-rank test and the Friedman test. RESULTS: Both LLMs produced relevant treatment recommendations with ChatGPT 4 generally outperforming Gemini Advanced regarding adherence to guidelines and comprehensive treatment planning. ChatGPT 4 showed higher AIPI scores (median 3 [2-4]) compared to Gemini Advanced (median 2 [2-3]), indicating better overall performance. Notably, inconsistencies were observed in the management of induction chemotherapy and surgical decisions, such as neck dissection. CONCLUSIONS: While both LLMs demonstrated the potential to aid in the multidisciplinary management of head and neck oncology, discrepancies in certain critical areas highlight the need for further refinement. The study supports the growing role of AI in enhancing clinical decision-making but also emphasizes the necessity for continuous updates and validation against current clinical standards to integrate AI into healthcare practices fully.
RESUMO
BACKGROUND: The widespread diffusion of Artificial Intelligence (AI) platforms is revolutionizing how health-related information is disseminated, thereby highlighting the need for tools to evaluate the quality of such information. This study aimed to propose and validate the Quality Assessment of Medical Artificial Intelligence (QAMAI), a tool specifically designed to assess the quality of health information provided by AI platforms. METHODS: The QAMAI tool has been developed by a panel of experts following guidelines for the development of new questionnaires. A total of 30 responses from ChatGPT4, addressing patient queries, theoretical questions, and clinical head and neck surgery scenarios were assessed by 27 reviewers from 25 academic centers worldwide. Construct validity, internal consistency, inter-rater and test-retest reliability were assessed to validate the tool. RESULTS: The validation was conducted on the basis of 792 assessments for the 30 responses given by ChatGPT4. The results of the exploratory factor analysis revealed a unidimensional structure of the QAMAI with a single factor comprising all the items that explained 51.1% of the variance with factor loadings ranging from 0.449 to 0.856. Overall internal consistency was high (Cronbach's alpha = 0.837). The Interclass Correlation Coefficient was 0.983 (95% CI 0.973-0.991; F (29,542) = 68.3; p < 0.001), indicating excellent reliability. Test-retest reliability analysis revealed a moderate-to-strong correlation with a Pearson's coefficient of 0.876 (95% CI 0.859-0.891; p < 0.001). CONCLUSIONS: The QAMAI tool demonstrated significant reliability and validity in assessing the quality of health information provided by AI platforms. Such a tool might become particularly important/useful for physicians as patients increasingly seek medical information on AI platforms.
RESUMO
Background: Long COVID has brought numerous challenges to healthcare, with olfactory dysfunction (OD) being a particularly distressing outcome for many patients. The persistent loss of smell significantly diminishes the affected individual's quality of life. Recent attention has been drawn to the potential of platelet-rich plasma (PRP) therapy as a treatment for OD. This comprehensive review aims to evaluate the effectiveness of PRP therapy in ameliorating OD, especially when associated with long-term COVID-19. Methods: We executed a comprehensive search of the literature, encompassing clinical trials and observational studies that utilized PRP in treating OD limited to COVID-19. We retrieved and comprehensively discussed data such as design, participant demographics, and reported outcomes, focusing on the efficacy and safety of PRP therapy for OD in COVID-19 patients. Results: Our comprehensive analysis interestingly found promising perspectives for PRP in OD following COVID-19 infection. The collective data indicate that PRP therapy contributed to a significant improvement in olfactory function after COVID-19 infection. Conclusions: The evidence amassed suggests that PRP is a promising and safe therapeutic option for OD, including cases attributable to Long COVID-19. The observed uniform enhancement of olfactory function in patients receiving PRP highlights the necessity for well-designed, controlled trials. Such studies would help to refine treatment protocols and more definitively ascertain the efficacy of PRP in a broader, more varied patient cohort.
RESUMO
PURPOSE: The aim of this study was to provide an updated European narrative review spanning the last decade, focusing on the cost-effectiveness of cochlear implants (CIs) for adults with severe to profound post-lingual hearing loss. METHODS: This review encompasses both prospective and retrospective approaches, as well as cross-sectional and longitudinal trials conducted on CIs in adults. All studies related to European countries (Austria, Germany, Switzerland, the Netherlands, Sweden, the UK and Poland) were conducted in English and were published between 2012 and June 2023. RESULTS: Nine studies were included in the analysis. The patients' ages ranged from 18 years to over 67 years, with sample sizes ranging from 20 to 100 patients; two of these studies were focused on single-sided deafness in adults. The Markov model was identified as the most commonly utilized analysis method. CONCLUSIONS: This review identified a general consensus on CI cost-effectiveness, despite substantial variability among countries in factors such as observation time horizons, cost-effectiveness thresholds, methods of cost collection, discount rates, CI eligibility criteria and country-specific health systems. Generally, CIs yield positive societal benefits for working-age individuals, potentially less for seniors. Early unilateral CI enhances cost-effectiveness, highlighting the importance of prompt candidate identification. A consistent undersupply of CIs relative to the percentage of potential recipients emerged across countries. Therefore, further investigation into subcategories such as single-sided deafness is warranted, along with country-specific cost analyses. Emphasizing the significance of detailed information on health systems and associated costs and benefits is crucial for facilitating comparisons across different settings.
RESUMO
The innate immune system is crucial in fighting SARS-CoV-2 infection, which is responsible for coronavirus disease 2019 (COVID-19). Therefore, deepening our understanding of the underlying immune response mechanisms is fundamental for the development of novel therapeutic strategies. The role of extra-oral bitter (TAS2Rs) and sweet (TAS1Rs) taste receptors in immune response regulation has yet to be fully understood. However, a few studies have investigated the association between taste receptor genes and COVID-19 symptom severity, with controversial results. Therefore, this study aims to deepen the relationship between COVID-19 symptom presence/severity and TAS1R and TAS2R38 (TAS2Rs member) genetic variations in a cohort of 196 COVID-19 patients. Statistical analyses detected significant associations between rs307355 of the TAS1R3 gene and the following COVID-19-related symptoms: chest pain and shortness of breath. Specifically, homozygous C/C patients are exposed to an increased risk of manifesting severe forms of chest pain (OR 8.11, 95% CI 2.26-51.99) and shortness of breath (OR 4.83, 95% CI 1.71-17.32) in comparison with T/C carriers. Finally, no significant associations between the TAS2R38 haplotype and the presence/severity of COVID-19 symptoms were detected. This study, taking advantage of a clinically and genetically characterised cohort of COVID-19 patients, revealed TAS1R3 gene involvement in determining COVID-19 symptom severity independently of TAS2R38 activity, thus providing novel insights into the role of TAS1Rs in regulating the immune response to viral infections.
RESUMO
Objective: To translate and validate an Italian version of the Questionnaire of Olfactory Disorders (IT-QOD). Materials and methods: This is a prospective, multicentre study that involved patients with olfactory dysfunction (OD). Both cases and controls underwent administration of the IT-QOD, Sino-Nasal Outcome Test-22 (SNOT-22) and psychophysical evaluation of orthonasal and retronasal olfactory function. Results: The IT-QOD was administered to 96 patients and 38 controls. The Cronbach's alpha exceeded 0.90, indicating satisfactory internal consistency. The test-retest reliability was found to be high for both parosmia (rs = 0.944) and life quality (rs = 0.969). Patients with OD had significantly higher IT-QOD scores compared to healthy individuals (p < 0.001), indicating strong internal validity. The external validity was also satisfactory, as shown by the significant correlation with SNOT-22 (rs = -0.54) and the threshold, discrimination, and identification score (rs = -0.63). Conclusions: The IT-QOD was demonstrated to be reliable and valid to assess the impact of OD on the quality of life of Italian-speaking patients.
Assuntos
Transtornos do Olfato , Qualidade de Vida , Humanos , Estudos Prospectivos , Reprodutibilidade dos Testes , Transtornos do Olfato/diagnóstico , Inquéritos e Questionários , ItáliaRESUMO
OBJECTIVE: To investigate the effectiveness of platelet-rich plasma (PRP) injection into the olfactory clefts of coronavirus disease 2019 (COVID-19) patients with persistent olfactory dysfunction (OD). STUDY DESIGN: Controlled study. SETTING: Multicenter study. METHODS: From March 2022 to November 2022, COVID-19 patients with persistent OD were recruited from three European hospitals to undergo PRP injections into the olfactory clefts. Olfactory function was evaluated at baseline and 10 weeks postinjection with the Olfactory Disorder Questionnaire (ODQ) and threshold, discrimination, and identification (TDI) test. Data were compared with a control group of untreated patients. RESULTS: Eighty-one patients who underwent PRP injection and 78 controls were included. Sixty-five PRP patients (80.3%) experienced subjective smell improvement after a mean duration of 3.4 ± 1.9 weeks. The parosmia, life quality statement, and ODQ sub- and total scores significantly decreased from pre- to 10-week postinjection in the PRP group. The TDI sub- and total scores significantly increased 10 weeks postinjection. In controls, the ODQ score did not change over time, while the discrimination, identification, and total TDI scores significantly increase after 10 weeks of follow-up. The 10-week TDI and ODQ scores were significantly better in the PRP group compared with the controls. CONCLUSION: Patients who underwent PRP injection reported better 10-week subjective and objective smell outcomes than controls. Future randomized-controlled studies using saline injection into the olfactory cleft of controls are needed to determine the superiority of PRP over placebo.
Assuntos
COVID-19 , Transtornos do Olfato , Plasma Rico em Plaquetas , Humanos , COVID-19/complicações , Olfato , Transtornos do Olfato/etiologia , Transtornos do Olfato/terapia , Projetos de PesquisaRESUMO
This case-control study estimates the 3-year prevalence of measured olfactory dysfunction and gustatory dysfunction associated with SARS-CoV-2 infection.
Assuntos
COVID-19 , Transtornos do Olfato , Humanos , Olfato , SARS-CoV-2 , Estudos de Coortes , Transtornos do Olfato/epidemiologia , Transtornos do Olfato/etiologia , Distúrbios do Paladar/etiologiaRESUMO
INTRODUCTION: The presence of cervical lymph node metastases is an unfavorable prognostic factor in head and neck squamous cell carcinoma (HNSCC) and a potential cause of treatment failure. Occult lymph node metastasis occurs in approximately 15-20% of HNSCC patients with a clinically negative neck (cN0), greatly impacting on their prognosis. The present study aimed to investigate the role of pre-treatment peripheral blood markers in predicting clinically occult cervical lymph node metastasis. METHODS: This multicenter, retrospective study was performed in a cohort of 472 patients diagnosed with cN0 HNSCC who underwent up-front surgery. Baseline neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), lymphocyte-to-monocyte ratio (LMR), systemic inflammatory marker (SIM), and systemic immune-inflammation index (SII) were calculated from available blood parameters. RESULTS: Oro-hypopharyngeal and oral cancers, locally advanced stage, moderately (G2), and poorly (G3) differentiated grade were associated with an increased risk of pathological lymph node involvement. NLR, LMR, PLR, SIM, and SII were significantly associated at multivariable analysis. NLR >2.12 was the most reliable at predicting occult lymph node metastasis (OR = 5.22; 95% CI: 2.14-12.75). We describe a predictive score integrating cancer site, local stage, and NLR which is effective at predicting positive lymph node pathological status. CONCLUSIONS: The present study provides evidence that pre-treatment peripheral blood markers, in particular NLR, represent reliable predictors of clinically occult cervical lymph node metastasis in cN0 HNSCC. Therefore, the present study provides a novel useful predictive score for directing the elective management of the neck in patients with cN0 HNSCC.
Assuntos
Neoplasias de Cabeça e Pescoço , Linfócitos , Humanos , Carcinoma de Células Escamosas de Cabeça e Pescoço/patologia , Metástase Linfática/patologia , Estudos Retrospectivos , Linfócitos/patologia , Prognóstico , Linfonodos/patologia , Neoplasias de Cabeça e Pescoço/patologiaRESUMO
OBJECTIVES: The aim of this study was to determine the impact of the involvement of the superior pharyngeal constrictor muscle (SPCM) evaluated by magnetic resonance imaging (MRI) on outcome in oropharyngeal squamous cell carcinomas (OPSCCs). METHODS: A retrospective study including consecutive patients with OPSCC treated with curative intent. RESULTS: A total of 82 consecutive patients with OPSCC met inclusion criteria. At multivariate analysis, patients with SPCM infiltration were at significantly higher risk of death (HR: 3.37, CI: 1.21-9.38) and progression (HR: 3.39, CI: 1.38-8.32). In a multivariate model conditioned on HPV status, a significantly higher risk of death and progression was observed by combining both SPCM and HPV status with patients harboring an HPV-negative OPSCC with SPCM infiltration showing the poorest outcome. CONCLUSION: MRI evidence of SPCM involvement significantly and independently increases the risk of death and progression in subjects with OPSCC. Considering both MRI-assessed SPCM infiltration and HPV status significantly improved risk stratification in these malignancies.
Assuntos
Carcinoma de Células Escamosas , Neoplasias de Cabeça e Pescoço , Neoplasias Orofaríngeas , Infecções por Papillomavirus , Humanos , Carcinoma de Células Escamosas de Cabeça e Pescoço , Prognóstico , Carcinoma de Células Escamosas/patologia , Infecções por Papillomavirus/patologia , Estudos Retrospectivos , Neoplasias Orofaríngeas/patologia , Papillomaviridae , Músculos/metabolismo , Músculos/patologiaRESUMO
The emergence of SARS-CoV-2 has brought olfactory dysfunction to the forefront of public awareness, because up to half of infected individuals could develop olfactory dysfunction. Loss of smell-which can be partial or total-in itself is debilitating, but the distortion of sense of smell (parosmia) that can occur as a consequence of a viral upper respiratory tract infection (either alongside a reduction in sense of smell or as a solo symptom) can be very distressing for patients. Incidence of olfactory loss after SARS-CoV-2 infection has been estimated by meta-analysis to be around 50%, with more than one in three who will subsequently report parosmia. While early loss of sense of smell is thought to be due to infection of the supporting cells of the olfactory epithelium, the underlying mechanisms of persistant loss and parosmia remain less clear. Depletion of olfactory sensory neurones, chronic inflammatory infiltrates, and downregulation of receptor expression are thought to contribute. There are few effective therapeutic options, so support and olfactory training are essential. Further research is required before strong recommendations can be made to support treatment with steroids, supplements, or interventions applied topically or injected into the olfactory epithelium in terms of improving recovery of quantitative olfactory function. It is not yet known whether these treatments will also achieve comparable improvements in parosmia. This article aims to contextualise parosmia in the setting of post-viral olfactory dysfunction, explore some of the putative molecular mechanisms, and review some of the treatment options available.
RESUMO
The cochlear implant (CI) is a widely accepted option in patients with severe to profound hearing loss receiving limited benefit from traditional hearing aids. CI surgery uses a default setting for frequency allocation aiming to reproduce tonotopicity, thus mimicking the normal cochlea. One emerging instrument that may substantially help the surgeon before, during, and after the surgery is a surgical planning software product developed in collaboration by CASCINATION AG (Bern, Switzerland) and MED-EL (Innsbruck Austria). The aim of this narrative review is to present an overview of the main features of this otological planning software, called OTOPLAN®. The literature was searched on the PubMed and Web of Science databases. The search terms used were "OTOPLAN", "cochlear planning software" "three-dimensional imaging", "3D segmentation", and "cochlear implant" combined into different queries. This strategy yielded 52 publications, and a total of 31 studies were included. The review of the literature revealed that OTOPLAN is a useful tool for otologists and audiologists as it improves preoperative surgical planning both in adults and in children, guides the intraoperative procedure and allows postoperative evaluation of the CI.
RESUMO
INTRODUCTION: No studies have reported data on 3-year prevalence and recovery rates of self-reported COVID-19-related olfactory and gustatory dysfunction. The aim of the present study was to estimate the 3-year prevalence and recovery rate of self-reported COVID-19-related chemosensory dysfunction in a cohort of patients with antecedent mild COVID-19. METHODS: This is a prospective observational study, measuring the prevalence of altered sense of smell or taste at follow-up and their variation from baseline, on adult patients consecutively assessed at Treviso and Trieste University Hospitals, who tested positive for SARS-CoV-2 RNA by polymerase chain reaction during March 2020. RESULTS: Overall, out of 403 respondents, 267 patients (66.3%) reported an altered sense of smell or taste (SNOT-22 > 0) at baseline, while 56 (13.9%), 29 (7.2%), and 21 (5.2%) reported such alterations at 6-24 months, 2 years, and 3 years, respectively. Among the 267 patients with COVID-19-associated smell or taste dysfunction at baseline, 246 (92.1%) reported complete resolution at 3 years. Of the patients who still experienced smell or taste dysfunction 2 years after COVID-19, 27.6% and 37.9% recovered completely and partially, respectively, at the 3-year follow-up. CONCLUSION: Among subjects with antecedent mildly symptomatic SARS-CoV-2 infection, the 3-year prevalence and recovery rate of COVID-19-related alteration in sense of smell or taste was 5% and 92%, respectively. In approximately two-thirds of patients experiencing chemosensory dysfunction still 2 years after COVID-19, it is still possible to observe a delayed complete or partial recovery after a period of 3 years, while the remaining one-third of individuals continues to have unchanged persistent chemosensory alteration.
Assuntos
COVID-19 , Transtornos do Olfato , Adulto , Humanos , COVID-19/complicações , COVID-19/epidemiologia , Olfato , Seguimentos , SARS-CoV-2 , RNA Viral , Transtornos do Olfato/diagnóstico , Transtornos do Olfato/epidemiologia , Transtornos do Olfato/etiologia , Distúrbios do Paladar/epidemiologia , Distúrbios do Paladar/etiologia , PaladarRESUMO
OBJECTIVE: To investigate the accuracy of Chat-Based Generative Pre-trained Transformer (ChatGPT) in answering questions and solving clinical scenarios of head and neck surgery. STUDY DESIGN: Observational and valuative study. SETTING: Eighteen surgeons from 14 Italian head and neck surgery units. METHODS: A total of 144 clinical questions encompassing different subspecialities of head and neck surgery and 15 comprehensive clinical scenarios were developed. Questions and scenarios were inputted into ChatGPT4, and the resulting answers were evaluated by the researchers using accuracy (range 1-6), completeness (range 1-3), and references' quality Likert scales. RESULTS: The overall median score of open-ended questions was 6 (interquartile range[IQR]: 5-6) for accuracy and 3 (IQR: 2-3) for completeness. Overall, the reviewers rated the answer as entirely or nearly entirely correct in 87.2% of cases and as comprehensive and covering all aspects of the question in 73% of cases. The artificial intelligence (AI) model achieved a correct response in 84.7% of the closed-ended questions (11 wrong answers). As for the clinical scenarios, ChatGPT provided a fully or nearly fully correct diagnosis in 81.7% of cases. The proposed diagnostic or therapeutic procedure was judged to be complete in 56.7% of cases. The overall quality of the bibliographic references was poor, and sources were nonexistent in 46.4% of the cases. CONCLUSION: The results generally demonstrate a good level of accuracy in the AI's answers. The AI's ability to resolve complex clinical scenarios is promising, but it still falls short of being considered a reliable support for the decision-making process of specialists in head-neck surgery.