Effectiveness of Changing Drug Classes in Patients With Refractory Laryngopharyngeal Reflux Disease.

OBJECTIVE: To investigate the effectiveness of drug class changes in patients with refractory laryngopharyngeal reflux disease (LPRD). STUDY DESIGN: Retrospective case series with prospective data. SETTING: Multicenter study. METHODS: The data of patients treated for a refractory LPRD from September 2017 to December 2023 were collected. The effectiveness of drug class changes was assessed through the reflux symptom score (RSS) change. Signs were evaluated with the Reflux Sign Assessment. The RSS reduction was used to categorize the therapeutic responses as mild (20%-40% RSS reduction), moderate (40.1%-60% RSS reduction), high (60.1%-80%), and complete (>80%). RESULTS: Among the 334 medical records, 74 (22.2%) patients had refractory LPRD defined as no RSS change in the pre- to 3-month posttreatment. The mean age was 52.6 ± 15.5 years. Changing drug class was associated with significant 3- to 6-month posttreatment reductions of RSS and RSA. Thirty patients (39%) did not experience symptom reduction after changing drugs. Changing alginate to magaldrate and magaldrate to alginate was associated with the highest responder rate (76.9%). Changing PPI and alginate/magaldrate molecules led to a response rate of 62.5%. In patients initially treated with a combination of PPI and alginate or magaldrate, changing PPI without changing alginate/magaldrate led to a 37.5% response rate. The baseline RSS was predictive of the 3- and 6-month RSS (therapeutic response). CONCLUSION: Changing drug class, especially alginate-to-magaldrate, may be an effective therapeutic approach for patients with a refractory LPRD.

International expert consensus statement: surgical failure in obstructive sleep apnea.

PURPOSE: Upper airway (UA) surgery is commonly employed in the treatment of patients with obstructive sleep apnea (OSA). The intricate pathophysiology of OSA, variability in sites and patterns of UA collapse, and the interaction between anatomical and non-anatomical factors in individual patients may contribute to possible surgical failures. This clinical consensus statement aims to identify areas of agreement among a development group comprising international experts in OSA surgery, regarding the appropriate definition, predictive factors in patients, and management of surgical failure in OSA treatment. METHODS: A clinical consensus statement (CCS) was developed using the Delphi method by a panel of 35 contributors from various countries. A systematic literature review adhering to PRISMA guidelines was conducted. A survey consisting of 60 statements was then formulated and presented to the experts. RESULTS: Following two rounds of the Delphi process, consensus or strong consensus was achieved on 36 items, while 24 items remained without consensus. Specifically, 5 out of 10 statements reached consensus regarding on the 'Definition of Surgical Success/Failure after OSA Surgery'. Regarding the 'Predictive Factors of Surgical Failure in OSA Surgery', consensus was reached on 10 out of 13 statements. In the context of the 'Diagnostic Workup in OSA Surgery', consensus was achieved on 9 out of 13 statements. Lastly, in 'Treatment in Surgical Failure Cases', consensus was reached on 12 out of 24 statements. CONCLUSION: The management of OSA after surgical failure presents a significant clinical challenge for sleep specialists. This CCS provides valuable guidance for defining, preventing, and addressing surgical failures in the treatment of OSA syndrome.

Accuracy and consistency of ChatGPT-3.5 and - 4 in providing differential diagnoses in oral and maxillofacial diseases: a comparative diagnostic performance analysis.

OBJECTIVE: To investigate the performance of ChatGPT in the differential diagnosis of oral and maxillofacial diseases. METHODS: Thirty-seven oral and maxillofacial lesions findings were presented to ChatGPT-3.5 and - 4, 18 dental surgeons trained in oral medicine/pathology (OMP), 23 general dental surgeons (DDS), and 16 dental students (DS) for differential diagnosis. Additionally, a group of 15 general dentists was asked to describe 11 cases to ChatGPT versions. The ChatGPT-3.5, -4, and human primary and alternative diagnoses were rated by 2 independent investigators with a 4 Likert-Scale. The consistency of ChatGPT-3.5 and - 4 was evaluated with regenerated inputs. RESULTS: Moderate consistency of outputs was observed for ChatGPT-3.5 and - 4 to provide primary (κ = 0.532 and κ = 0.533 respectively) and alternative (κ = 0.337 and κ = 0.367 respectively) hypotheses. The mean of correct diagnoses was 64.86% for ChatGPT-3.5, 80.18% for ChatGPT-4, 86.64% for OMP, 24.32% for DDS, and 16.67% for DS. The mean correct primary hypothesis rates were 45.95% for ChatGPT-3.5, 61.80% for ChatGPT-4, 82.28% for OMP, 22.72% for DDS, and 15.77% for DS. The mean correct diagnosis rate for ChatGPT-3.5 with standard descriptions was 64.86%, compared to 45.95% with participants' descriptions. For ChatGPT-4, the mean was 80.18% with standard descriptions and 61.80% with participant descriptions. CONCLUSION: ChatGPT-4 demonstrates an accuracy comparable to specialists to provide differential diagnosis for oral and maxillofacial diseases. Consistency of ChatGPT to provide diagnostic hypotheses for oral diseases cases is moderate, representing a weakness for clinical application. The quality of case documentation and descriptions impacts significantly on the performance of ChatGPT. CLINICAL RELEVANCE: General dentists, dental students and specialists in oral medicine and pathology may benefit from ChatGPT-4 as an auxiliary method to define differential diagnosis for oral and maxillofacial lesions, but its accuracy is dependent on precise case descriptions.

Oral Cavity Cancer Secondary to Dental Trauma: A Scoping Review.

(1) Background: Oral cavity cancer represents the most common site of origin of head and neck mucosal malignancies. A few limited studies have suggested that chronic irritation, particularly in non-healing ulcers, and fibrotic tissue from poor dentition or ill-fitting dentures had a role in developing mouth cancer. This scoping review aims to evaluate the existing evidence concerning Oral Cavicty Cancer (OCC) in non-smokers/non-drinkers and the relationship with dental trauma. (2) Methods: A scoping review of the PubMed, Embase, and Web of Science databases was completed in adherence with the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews checklist. (3) Results: Of the 33 articles that met inclusion, in 6 of them authors discussed the role of topography in dental trauma, in 11 articles authors discussed the carcinogenesis mechanism involved in chronic mucosal trauma, in 17 articles data on ill-fitting dentures was included, 4 studies dealt with the effect of broken/sharp teeth on mucosal damage, and in 7 studies the role of oral hygiene was covered. Less frequently discussed topics included gender, risk of neck nodes, and the role of potentially malignant oral disorders. (4) Conclusions: The available literature suggests a potential connection between chronic dental trauma and the development of OCC. Studies have highlighted factors such as denture use and ill-fitting dental appliances as contributors to an increased risk of oral cancer. Interestingly, we still miss data to support the hypothesis that women, particularly those without toxic habits like smoking or alcohol consumption, appear to be disproportionately affected by oral cancer related to chronic dental trauma.

Surgical, Functional, and oncological outcomes of transoral robotic surgery for cT1-T3 supraglottic laryngeal Cancers: A systematic review.

BACKGROUND: This systematic review investigated the surgical, functional, and oncological outcomes of transoral robotic supraglottic laryngectomy (TORS-SGL) for cT1-T3 laryngeal squamous cell carcinoma (LSCC). METHODS: Two investigators conducted an updated PubMed, Scopus, and Cochrane Library systematic review for studies investigating the surgical, functional, and oncological outcomes of TORS-SGL using the PRISMA statements. The bias analysis was conducted with the MINORS. RESULTS: Twenty-one studies were included, accounting for 896 patients. TORS-SGL was primarily performed for cT1 (39.1 %), cT2 (46.9 %), and some selected cT3 (7.7 %) LSCCs. Surgical margins were positive in 10.8 % of cases. The mean hospital stay was 8.6 days. Hemorrhage (6.3 %), pneumonia (5.5 %), and aspiration (1.7 %) are the primary complications. The surgical margins were positive in 10.6 % of cases. Feeding tubes, temporary tracheotomy, and definitive percutaneous gastrostomy are found in 65.6 %, 19.7 %, and 5.2 % of patients, respectively. The oral diet is restarted after a mean of 7.2 days. The 5-year OS and DFS of TORS-SGL were estimated to be 78.3 %, and 91.7 %, with 5-year local-relapse-free survival and nodal-relapse-free survival of 90.8 %, and 86.6 %, respectively. CONCLUSION: The TORS-SGL is a safe, and effective surgical approach for cT1-T3 SGL. The functional and surgical outcomes appear comparable with TOLM-SGL. The oncological outcomes of TORS-SGL could be better than TOLM and open SGLs, but further large cohort-controlled studies are needed to draw reliable conclusions.

Chronic Cough Related to Thyroid Cartilage Superior Cornu Abnormality.

Chronic cough is a common troublesome symptom in otolaryngology head and neck surgery practice. In rare cases, chronic cough may be related to anatomical abnormalities. In this article, we report the history of a 64-year-old female with a chronic course due to a curved superior cornu of the thyroid cartilage and related irritation of the laryngeal superior nerve. The cough was atypical and resolved after the surgical resection of the abnormal cornu. There was no recurrence at 9 months post-surgery. The findings of the present case report highlight the need to explore the laryngeal anatomy in patients with chronic cough to identify potential abnormalities, which may be treated surgically.

Survival, Surgical, and functional outcomes of transoral laser microsurgery for cT1-T3 supraglottic laryngeal Cancers: A systematic review.

BACKGROUND: This review aimed to investigate the surgical, functional, and oncological outcomes of transoral laser microsurgery supraglottic laryngectomy (TOLM-SGL) for cT1-T3 laryngeal cancers. METHODS: PubMed, Scopus, and Cochrane Library were searched by two independent investigators for studies investigating the surgical, functional, and oncological outcomes of TOLM-SGL using the PRISMA statements. A bias analysis was carried out with MINORS. RESULTS: Twenty-four studies were included (937 patients), including 206 (25.9 %) cT1, 467 (58.7 %) cT2, and 123 (15.4 %) cT3 cases. Most patients were cN0 (63.9 %). The mean hospital stay of TOLM was 10.1 days. Aspiration (5.5 %), and bleeding (5.3 %) were the most prevalent complications. The laryngeal preservation rate was 93.7 %. Temporary tracheotomy was performed in 18.0 % of patients, with a mean time of decannulation of 6.8 days. A feeding tube was placed in 59.9 % of patients. The oral diet restarted after 6.4 days. Definitive gastrostomy was necessary in 2.4 % of cases. The 5-year OS and DFS were 70.1 % and 82.0 %, respectively. Distant metastasis, local, and regional recurrence occurred in 4.6 %, 11.6 %, and 5.1 % of patients. There was an important heterogeneity between studies for inclusion criteria, patient profiles, TOLM indications, and details of surgical, functional, and oncological outcomes. CONCLUSION: TOLM supraglottic laryngectomy is a safe, and effective procedure associated with adequate functional, surgical, and oncological outcomes. Future studies are needed to define the place of TOLM in advanced LSCC; the role and timing of concomitant bilateral neck dissection, the indications of tracheotomy and feeding tube.

Endoscopic ear surgery in the treatment of chronic otitis media with atelectasis.

PURPOSE: Atelectasis otitis media (AtOM) is a chronic condition where the tympanic membrane (TM) becomes retracted towards the middle ear and the ossicular chain. Surgical treatment for this condition could be indicated based on stage of atelectasis, patient's clinical condition and hearing loss. Over the years, AtOM has been treated with various types of tympanoplasty under microscopic view. The aim of this study is to present the results of endoscopic ear surgery in AtOM. METHODS: Forty-five patients who underwent endoscopic trans-canal tympanoplasty were included in the study. Preoperative features, intraoperative findings and postoperative outcomes were collected. RESULTS: Preoperatively, none of the study's patients were classified with a Sadè Grade I, whereas grades II, III and IV were 3 (6.6%), 23 (32.1%) and 19 (67.8%) respectively. The 3 patients with Sadè grade II showed a conductive hearing loss higher than 20 dB and a continuous ear fullness, therefore they were surgically treated. The postoperative graft success rate was estimated at 95.5%. During follow-up, 2 patients showed a TM perforation (at 6 and 12 months after surgery) whereas 1 patient experienced a recurrence of atelectasis in the TM (16 months after surgery). The overall success rate at the final follow-up was calculated at 88.8%. The average preoperative air-conduction threshold was 51.1 ± 21.5, which reduced to 34.6 ± 22.1 (p = 0.04) at follow-up. The preoperative air-bone gap decreased from 28 ± 7.2 to 11.8 ± 10 (p = 0.002) after surgery. CONCLUSION: Atelectasis otitis media might be suitable for exclusive endoscopic surgical treatment, as it appears to exhibit a low recurrence rate and promising audiological outcomes.

Cost burden for healthcare and patients related to the unawareness towards laryngopharyngeal reflux.

OBJECTIVE: To investigate the impact of physician unawareness towards laryngopharyngeal reflux (LPR) on healthcare costs. METHODS: Patients with a confirmed LPR diagnosis were consecutively recruited from Belgian Hospitals. Demographics and clinical outcomes (impedance-pH testing features, reflux symptom score, and reflux sign assessment) were extracted. The past consultations and additional examinations dedicated to the investigation of laryngopharyngeal symptoms and findings without suspicion of LPR were collected. The estimated costs of consultations and procedures were those indicated in the National Health Insurance Institute's Charges for 2022. Part was reimbursed by the social security system, and the rest was paid by patients. RESULTS: Seventy-six patients were recruited. Seventeen patients (22.4%) had no previous consultation or additional examination for their LPR-symptoms. The estimated mean (standard deviation) costs related to the unawareness of LPR for the healthcare system and patient, were 310.06 ± 370.49 €, and 54.05 ± 46.28 €, respectively. The highest estimated costs were related to gastroenterology consultations and procedures, which did not lead to a confirmation of LPR diagnosis. The total estimated cost for the Belgian healthcare system and patients (11,590,000 million), could range from 359 359 540 € to 1 078 078 620 €; and 62 643 950 € to 187 931 850 €, respectively. The estimated costs related to gastroenterology practice of patients with severe disease were significantly higher than patients with mild disease. CONCLUSION: The unawareness of practitioners toward LPR leads to significant costs for healthcare system and patients. The teaching and awareness towards LPR need to be improved in medical schools and clinical practice.

Influence of Single Nucleotide Polymorphisms on CRS Outcomes: A Preliminary Observational Study.

OBJECTIVE(S): To conduct a preliminary investigation into the relationship between specific SNP variants, type II inflammation, and the effectiveness of dupilumab therapy and surgery in patients with CRS. METHODS: In this prospective study, 48 subjects were enrolled, comprising 32 CRS patients and 16 healthy controls. The CRS patients were subjected to either dupilumab therapy or endoscopic surgery according to EPOS guidelines. SNP variants were identified using the TaqMan SNP genotyping technique. The identified SNP profiles were compared between the control group and CRS patients, and their potential influence on treatment outcomes was evaluated. Treatment responses were assessed based on symptom scores, such as SS-I, SNOT-22, disease progression using the NPS findings, and SNP profiles at a 6-month follow-up. The primary measures included the Nasal Polyp Score, Smell Identification Test (SIT) score, and SNOT-22 outcomes. RESULTS: Dupilumab therapy and surgery significantly decreased NPS, with the last showing superior results. However, dupilumab therapy resulted in a significantly improved SIT score. Significant differences were observed in SNP profiles, particularly with rs1800629 (TNFA), rs2856838 (IL1a), rs17561 (IL1a), and rs1805011 (IL4R). In particular, the expression of rs2856838 and rs1805011 variants in the dupilumab group was associated with significantly better SIT and SNOT-22 outcomes than non-expressors. Also, the surgery group patients expressing the rs2856838 variant reported significant improvements in SNOT-22 scores. CONCLUSION: These preliminary findings suggest that SNP genotypes may guide personalized treatment strategies for CRS. Further larger prospective studies are required to confirm these initial observations. LEVEL OF EVIDENCE: 2 Laryngoscope, 2024.

Endoscopic Features of Chronic Rhinosinusitis in Patients with Gastroesophageal Reflux Disease.

Chronic rhinosinusitis (CRS) is a complex inflammatory condition affecting the nasal and paranasal sinus mucosa. Gastroesophageal reflux disease (GERD) has been implicated as a potential exacerbating factor in CRS, but the specific endoscopic features of nasopharyngeal pathology in this context remain poorly understood. Background and Objectives: Chronic rhinosinusitis is a multifactorial disease with various underlying etiologies, including inflammation, anatomical factors, and environmental triggers. While gastroesophageal reflux disease has been suggested as a potential contributor to chronic rhinosinusitis, the specific endoscopic features indicative of nasopharyngeal pathology in CRS patients with GERD symptoms have not been clearly elucidated. Our aim is to identify specific endoscopic features of nasopharyngeal pathology in patients with CRS associated with GERD symptoms and to propose a method for assessing the influence of gastroesophageal reflux disease on the mucosal layer of the nose and nasopharynx. Materials and Methods: We conducted a cross-sectional observational study involving 521 adult patients presenting with symptoms suggestive of CRS. From this cohort, 95 patients with the highest scores on the Reflux Symptom Index (RSI) and Reflux Symptom Score-12 (RSS-12) questionnaires were selected as the main group. Endoscopic examinations were performed to assess the nasal and nasopharyngeal mucosa. Results: Our study revealed significant alterations in the nasopharyngeal mucosa of patients with CRS associated with GERD symptoms. Increased vascularity of the nasopharyngeal mucosa was observed in 91 patients (95.7%), while hypertrophy was noted in 83 patients (87.4%). Mucus was present in the nasopharynx of 77 patients (81.1%), exhibiting varying characteristics of color and consistency. Asymmetric hypertrophy of the oropharyngeal mucosa was noted in 62 patients (65.3%). Conclusions: We propose a method for assessing the influence of gastroesophageal reflux disease on the mucosal layer of the nose and nasopharynx, which may aid in diagnostic and management decisions. Further research is warranted to explore the potential impact of GERD symptoms on the course and severity of CRS exacerbations.

Examining the Performance of ChatGPT 3.5 and Microsoft Copilot in Otolaryngology: A Comparative Study with Otolaryngologists' Evaluation.

To evaluate the response capabilities, in a public healthcare system otolaryngology job competition examination, of ChatGPT 3.5 and an internet-connected GPT-4 engine (Microsoft Copilot) with the real scores of otolaryngology specialists as the control group. In September 2023, 135 questions divided into theoretical and practical parts were input into ChatGPT 3.5 and an internet-connected GPT-4. The accuracy of AI responses was compared with the official results from otolaryngologists who took the exam, and statistical analysis was conducted using Stata 14.2. Copilot (GPT-4) outperformed ChatGPT 3.5. Copilot achieved a score of 88.5 points, while ChatGPT scored 60 points. Both AIs had discrepancies in their incorrect answers. Despite ChatGPT's proficiency, Copilot displayed superior performance, ranking as the second-best score among the 108 otolaryngologists who took the exam, while ChatGPT was placed 83rd. A chat powered by GPT-4 with internet access (Copilot) demonstrates superior performance in responding to multiple-choice medical questions compared to ChatGPT 3.5.

Prophylactic antibiotics in sialendoscopy: a randomized clinical trial.

OBJECTIVE: Antibiotics have been prescribed routinely in sialendoscopy procedures to reduce the risk of postoperative infection, despite the limited evidence supporting this practice. Being necessary to assess the need for antibiotics in Sialendoscopy, aiming to provide evidence-based guidance to clinicians regarding antibiotic administration in this procedure. MATERIALS & METHOD: A prospective, randomized, double-blind, controlled clinical trial to evaluate the of prophylactic antibiotics in Sialendoscopy was designed. RESULTS: A total of 80 patients were included in this study, including 57 females (71.8%) and 23 males (28.8%). In terms of prophylaxis, 36 patients (45%) received prophylactic treatment, and 44 patients (55%) did not. The occurrence of infectious events was observed in 2 patients (5.6%) with prophylaxis and 4 patients (9.1%) without prophylaxis. However, this difference was not statistically significant (p = 0.556). CONCLUSION: In conclusion, our prospective, randomized clinical trial aimed to address the debate regarding the use of prophylactic antibiotics in sialendoscopy. Our study's findings suggest that the routine use antibiotics may not be necessary to prevent postoperative infections in sialendoscopy procedures. These results have important implications for clinical practice, potentially reducing the unnecessary use of antibiotics and addressing concerns related to antibiotic resistance and adverse drug reactions.

Effectiveness of platelet-rich plasma in long-lasting post-viral olfactory dysfunction: a case-series.

OBJECTIVE: To investigate the platelet-rich plasma (PRP) effectiveness in patients with a long-lasting postviral olfactory dysfunction (LPOD). METHODS: Forty-three consecutive patients with a long-lasting postviral OD were prospectively recruited. The injection of 1 mL of PRP was carried out in both olfactory clefts. The pre- to 6-month post-PRP injection change in olfaction was assessed with the olfactory disorder questionnaire (ODQ) and the threshold, discrimination, and identification (TDI) tests. RESULTS: Forty-three patients received bilateral PRP injections (24 females). The mean age of patients was 58.9 ± 16.8 years. The mean duration of LPOD was 8.7 years. The pre to 6-month post-injection mean TDI significantly improved from 10.3 ± 10.2 to 20.12 ± 12.07 (p = 0.001). The mean ODQ significantly decreased from 29.8 ± 13.0 to 23.4 ± 11.3 (p = 0.013). The average change of the TDI and the ODQ were 9.8 and 6.4, respectively. Age was inversely associated with the 6-month threshold score. CONCLUSION: PRP appears to be a promising therapeutic strategy for long-lasting postviral OD. Our findings support the conduction of controlled randomized trial in this population of patients.

Minimum Effective Duration of Laryngopharyngeal Reflux Disease Treatment: A Prospective Study.

OBJECTIVE: To investigate the minimum therapeutic duration for patients with primary laryngopharyngeal reflux disease (LPRD) through the evaluation of symptom changes at multiple time points. STUDY DESIGN: Prospective uncontrolled. SETTING: University medical center. METHODS: Patients with LPRD at the 24-hour hypopharyngeal-esophageal multichannel intraluminal impedance-pH monitoring were recruited from the European Reflux Clinic. Depending on the type of LPRD, patients were treated with a combination of proton-pump inhibitors, alginate, or magaldrate. Symptoms were evaluated with the reflux symptom score (RSS) at baseline and throughout treatment (1-, 3-, 6-, and 9-month posttreatment). The most appropriate therapeutic duration was determined using the RSS changes. Signs were evaluated with the reflux sign assessment. RESULTS: A total of 159 patients completed the study. The mean age was 49.9 ± 15.7 years. At 1-month posttreatment, 97 patients (61.0%) were considered as early responders to treatment, and the treatment was stopped for 52 patients (32.7%). Of the 62 early nonresponders, 34 patients (21.4%) reached responded to treatment after 3 to 9 months. The cumulative therapeutic success rate at 1-month posttreatment (61.0%) progressively increased to reach a range of 82.4% to 99.3% at 9-month posttreatment. The RSS mainly decreased in the first month of treatment in early responders. In early nonresponders, RSS progressively decreased throughout the 9-month treatment period. The baseline severity of RSS is a strong predictor of therapeutic response. CONCLUSION: A therapeutic regimen of 1 month can be sufficient to treat one third of LPRD patients. The early nonresponders may require 3 to 9 months of treatment.

ChatGPT-4 Consistency in Interpreting Laryngeal Clinical Images of Common Lesions and Disorders.

OBJECTIVE: To investigate the consistency of Chatbot Generative Pretrained Transformer (ChatGPT)-4 in the analysis of clinical pictures of common laryngological conditions. STUDY DESIGN: Prospective uncontrolled study. SETTING: Multicenter study. METHODS: Patient history and clinical videolaryngostroboscopic images were presented to ChatGPT-4 for differential diagnoses, management, and treatment(s). ChatGPT-4 responses were assessed by 3 blinded laryngologists with the artificial intelligence performance instrument (AIPI). The complexity of cases and the consistency between practitioners and ChatGPT-4 for interpreting clinical images were evaluated with a 5-point Likert Scale. The intraclass correlation coefficient (ICC) was used to measure the strength of interrater agreement. RESULTS: Forty patients with a mean complexity score of 2.60 ± 1.15. were included. The mean consistency score for ChatGPT-4 image interpretation was 2.46 ± 1.42. ChatGPT-4 perfectly analyzed the clinical images in 6 cases (15%; 5/5), while the consistency between GPT-4 and judges was high in 5 cases (12.5%; 4/5). Judges reported an ICC of 0.965 for the consistency score (P = .001). ChatGPT-4 erroneously documented vocal fold irregularity (mass or lesion), glottic insufficiency, and vocal cord paralysis in 21 (52.5%), 2 (0.05%), and 5 (12.5%) cases, respectively. ChatGPT-4 and practitioners indicated 153 and 63 additional examinations, respectively (P = .001). The ChatGPT-4 primary diagnosis was correct in 20.0% to 25.0% of cases. The clinical image consistency score was significantly associated with the AIPI score (rs = 0.830; P = .001). CONCLUSION: The ChatGPT-4 is more efficient in primary diagnosis, rather than in the image analysis, selecting the most adequate additional examinations and treatments.