Common ENT disorders

A cross-sectional comparative study: ChatGPT 3.5 versus diverse levels of medical experts in the diagnosis of ENT diseases

PURPOSE

With recent advances in artificial intelligence (AI), it has become crucial to thoroughly evaluate its applicability in healthcare. This study aimed to assess the accuracy of ChatGPT in diagnosing ear, nose, and throat (ENT) pathology, and comparing its performance to that of medical experts.

METHODS

We conducted a cross-sectional comparative study where 32 ENT cases were presented to ChatGPT 3.5, ENT physicians, ENT residents, family medicine (FM) specialists, second-year medical students (Med2), and third-year medical students (Med3). Each participant provided three differential diagnoses. The study analyzed diagnostic accuracy rates and inter-rater agreement within and between participant groups and ChatGPT.

RESULTS

The accuracy rate of ChatGPT was 70.8%, being not significantly different from ENT physicians or ENT residents. However, a significant difference in correctness rate existed between ChatGPT and FM specialists (49.8%, p < 0.001), and between ChatGPT and medical students (Med2 47.5%, p < 0.001; Med3 47%, p < 0.001). Inter-rater agreement for the differential diagnosis between ChatGPT and each participant group was either poor or fair. In 68.75% of cases, ChatGPT failed to mention the most critical diagnosis.

CONCLUSIONS

ChatGPT demonstrated accuracy comparable to that of ENT physicians and ENT residents in diagnosing ENT pathology, outperforming FM specialists, Med2 and Med3. However, it showed limitations in identifying the most critical diagnosis.

Evolution of throat symptoms during the COVID-19 pandemic in the US

OBJECTIVES

SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) structure and host tropism have changed over time, and so has the involvement of throat structures. This infodemiological analysis is hence aimed at investigating the evolution of throat symptoms during the COVID-19 pandemic in the US.

METHODS

We searched Google Trends using the medical search terms "ageusia", "hoarseness", "dysphonia", "pharyngitis" and "laryngitis", setting geographical location to "United States", within the past 5 years. The weekly Google Trends score for these symptoms, which reflects their national Web popularity, was divided in three parts, as "pre-COVID" (July 2017 to February 2020), COVID-19 "pre-Omicron" (March 2020 to November 2021), and COVID-19 "Omicron" (December 2021 to July 2022), and then compared.

RESULTS

The volume of searches for ageusia increased in the pre-Omicron period and remained significantly higher also during Omicron prevalence, though a significant decrease (∼30%) occurred with Omicron lineages compared to previous strains. The Google searches for hoarseness and dysphonia were relatively similar between the pre-COVID and pre-Omicron periods, but then significantly increased during Omicron predominance. The Google searches for pharyngitis and laryngitis decreased in the pre-Omicron period, but then considerably increased following Omicron emergence. Omicron endemic spread could be significantly and independently predicted by the volume of searches for pharyngitis, laryngitis and hoarseness.

CONCLUSIONS

The epidemiological burden of throat symptoms has considerably changed after Omicron emergence, with a lower likelihood of developing chemosensory dysfunctions and enhanced risk of throat involvement.

[Establishing an ORL virtual outpatient Dept. during the COVID-19 pandemic]

INTRODUCTION

The COVID-19 pandemic changed medical education: teaching has been mostly converted to online mode. Our aim is to offer a complete high-quality curriculum despite the fact of worldwide cutbacks in education.

METHODS

The department of otorhinolaryngology introduced case-based learning (CBL). CBL is a learning and teaching approach that prepares students for clinical practice through the use of authentic clinical cases and places them in the role of decision maker. CBL combines theory and practice to prepare students as good as possible without intern shadowing. The students were asked to evaluate CBL as a digital format and as a teaching tool for future clinical work and preparation for the ORL exam.

RESULTS

The majority of students (>90%) rated the CBL as a successful digital format. Most students also strongly agreed or agreed that CBL is a good preparation for their future clinical work (>90%) and the ORL exam (>80%). 100% of students CBL confirmed, that they learned something new.

CONCLUSION

Following successful introduction of CBL we will implement a new teaching format. The "ORL virtual outpatient Dept." will include information from virtual, anonymized case studies. We choose diagnosis included in the "ORL virtual outpatient Dept." according to the most common ORL disorders encountered by primary care physicians. The "ORL virtual outpatient Dept." can only bridge the absence of practical training, and, in the future, serve as an additional preparation.

Prevalence of Otolaryngology Diseases in an Urban Homeless Population

OBJECTIVE

Otolaryngology diseases are common among people experiencing homelessness; however, they are seldom evaluated in a specialist setting, and investigations on their prevalence have rarely been conducted. The aim of this retrospective study was to evaluate the prevalence of otolaryngology conditions in an urban homeless population.

STUDY DESIGN

Retrospective study.

SETTING

Primary health care facility.

METHODS

The clinical records of patients referred to the medical facilities of the Primary Care Services of the Eleemosynaria Apostolica, Vatican City, between October 1, 2019, and July 31, 2021, were retrospectively reviewed; those reporting at least 1 otolaryngology disease were included in the study.

RESULTS

A total of 2516 records were retrospectively reviewed, and 484 (19.24%) were included in the study. The most common otolaryngology disease was pharyngotonsillitis (n = 118, 24.13%), followed by rhinitis with nasal obstruction (n = 107, 21.88%), hearing loss (n = 93, 19.01%), otitis (n = 81, 16.56%), abscess (n = 46, 9.40%), and sinusitis (n = 33, 6.74%). Head and neck cancer or precancerous lesions were reported in 34 subjects (7.02%). More than 1 simultaneous otolaryngology disorder was found in nearly 50% of our sample. A wide range of comorbidities was also reported.

CONCLUSIONS

Our results confirm an elevated otolaryngology demand in the homeless population and encourage the development of more efficient and effective strategies for a population-tailored diagnosis and treatment of these conditions.