Prospective Cohort Study Identifies Medical Predictors of Treatment-Related Oral Toxicities in Oral and Oropharyngeal Cancer Patients.

The dental treatment of patients with oral cavity and oropharyngeal squamous cell carcinoma (OOPSCC) may be challenging for dentists. This study aimed to characterize systemic changes in patients with OOPSCC undergoing dental treatment prior to cancer therapy, with a specific focus on laboratory assessments. The primary objectives included identifying potential adverse events, such as infections or bleeding, resulting from dental procedures. Additionally, the study aimed to correlate baseline patient characteristics with treatment-related toxicities. This was a prospective cohort study that included 110 OOPSCC patients referred to the Dental Oncology Service at São Paulo State Cancer Institute, Brazil, between November/2019 and December/2020. Comorbidities, sociodemographic data, medication in use, cancer treatment-related toxicities, and altered laboratory tests results were correlated. The most common comorbidities and altered laboratory results were hypertension, dyslipidemia, diabetes, as well as elevated levels of C-reactive protein, hemoglobin, and hematocrit. Toxicities exhibited a progressive pattern over time, encompassing oral mucositis (OM), xerostomia, dysphagia, dysgeusia, trismus, and radiodermatitis. No correlation between comorbidities and cancer treatment-related toxicities, a positive correlation between medications in use and OM, and a negative correlation between medications and dysgeusia were found. OM was associated with altered thyroxine (T4) and free thyroxine (FT4), calcium, urea, creatinine, alkaline phosphatase, and syphilis. Family income and housing were OM predictors. Altered T4/FT4/urea/calcium/alkaline phosphatase/creatinine/syphilis may be useful clinical predictors of OM. Despite the elevated prevalence of comorbidities and abnormal laboratory findings, dental treatment prior to cancer treatment yielded no adverse events.

Large language models for generating medical examinations: systematic review.

BACKGROUND: Writing multiple choice questions (MCQs) for the purpose of medical exams is challenging. It requires extensive medical knowledge, time and effort from medical educators. This systematic review focuses on the application of large language models (LLMs) in generating medical MCQs. METHODS: The authors searched for studies published up to November 2023. Search terms focused on LLMs generated MCQs for medical examinations. Non-English, out of year range and studies not focusing on AI generated multiple-choice questions were excluded. MEDLINE was used as a search database. Risk of bias was evaluated using a tailored QUADAS-2 tool. RESULTS: Overall, eight studies published between April 2023 and October 2023 were included. Six studies used Chat-GPT 3.5, while two employed GPT 4. Five studies showed that LLMs can produce competent questions valid for medical exams. Three studies used LLMs to write medical questions but did not evaluate the validity of the questions. One study conducted a comparative analysis of different models. One other study compared LLM-generated questions with those written by humans. All studies presented faulty questions that were deemed inappropriate for medical exams. Some questions required additional modifications in order to qualify. CONCLUSIONS: LLMs can be used to write MCQs for medical examinations. However, their limitations cannot be ignored. Further study in this field is essential and more conclusive evidence is needed. Until then, LLMs may serve as a supplementary tool for writing medical examinations. 2 studies were at high risk of bias. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

[Correlation between defects in medical care and data of causal analysis]. / Vzaimosvyaz' mezhdu defektami meditsinskoi pomoshchi i dannymi prichinno-sledstvennogo analiza.

The article is devoted to the current legal responsibility of medical staff. It is noted that this issue has not been sufficiently studied and requires further research. The article identifies an attempt to assess statistically significant correlation between defects of medical care provision and data of causal analysis as a research task. The practical experience on 215 conclusions of commission forensic medical examinations, in which doctors of surgical specialties were considered on «medical cases¼, has been summarized. A high statistically significant correlation between defects in treatment, diagnosis, organization of medical care, management of medical records and data of causal relationship has been established on the basis of performed scientific researches. The idea that, despite possible subjectivism, the causal relationship is confirmed by factual data on revealed defects in medical care obtained from the study, has been proven.

Performance of ChatGPT on Chinese national medical licensing examinations: a five-year examination evaluation study for physicians, pharmacists and nurses.

BACKGROUND: Large language models like ChatGPT have revolutionized the field of natural language processing with their capability to comprehend and generate textual content, showing great potential to play a role in medical education. This study aimed to quantitatively evaluate and comprehensively analysis the performance of ChatGPT on three types of national medical examinations in China, including National Medical Licensing Examination (NMLE), National Pharmacist Licensing Examination (NPLE), and National Nurse Licensing Examination (NNLE). METHODS: We collected questions from Chinese NMLE, NPLE and NNLE from year 2017 to 2021. In NMLE and NPLE, each exam consists of 4 units, while in NNLE, each exam consists of 2 units. The questions with figures, tables or chemical structure were manually identified and excluded by clinician. We applied direct instruction strategy via multiple prompts to force ChatGPT to generate the clear answer with the capability to distinguish between single-choice and multiple-choice questions. RESULTS: ChatGPT failed to pass the accuracy threshold of 0.6 in any of the three types of examinations over the five years. Specifically, in the NMLE, the highest recorded accuracy was 0.5467, which was attained in both 2018 and 2021. In the NPLE, the highest accuracy was 0.5599 in 2017. In the NNLE, the most impressive result was shown in 2017, with an accuracy of 0.5897, which is also the highest accuracy in our entire evaluation. ChatGPT's performance showed no significant difference in different units, but significant difference in different question types. ChatGPT performed well in a range of subject areas, including clinical epidemiology, human parasitology, and dermatology, as well as in various medical topics such as molecules, health management and prevention, diagnosis and screening. CONCLUSIONS: These results indicate ChatGPT failed the NMLE, NPLE and NNLE in China, spanning from year 2017 to 2021. but show great potential of large language models in medical education. In the future high-quality medical data will be required to improve the performance.

A Novel Evaluation Model for Assessing ChatGPT on Otolaryngology-Head and Neck Surgery Certification Examinations: Performance Study.

BACKGROUND: ChatGPT is among the most popular large language models (LLMs), exhibiting proficiency in various standardized tests, including multiple-choice medical board examinations. However, its performance on otolaryngology-head and neck surgery (OHNS) certification examinations and open-ended medical board certification examinations has not been reported. OBJECTIVE: We aimed to evaluate the performance of ChatGPT on OHNS board examinations and propose a novel method to assess an AI model's performance on open-ended medical board examination questions. METHODS: Twenty-one open-ended questions were adopted from the Royal College of Physicians and Surgeons of Canada's sample examination to query ChatGPT on April 11, 2023, with and without prompts. A new model, named Concordance, Validity, Safety, Competency (CVSC), was developed to evaluate its performance. RESULTS: In an open-ended question assessment, ChatGPT achieved a passing mark (an average of 75% across 3 trials) in the attempts and demonstrated higher accuracy with prompts. The model demonstrated high concordance (92.06%) and satisfactory validity. While demonstrating considerable consistency in regenerating answers, it often provided only partially correct responses. Notably, concerning features such as hallucinations and self-conflicting answers were observed. CONCLUSIONS: ChatGPT achieved a passing score in the sample examination and demonstrated the potential to pass the OHNS certification examination of the Royal College of Physicians and Surgeons of Canada. Some concerns remain due to its hallucinations, which could pose risks to patient safety. Further adjustments are necessary to yield safer and more accurate answers for clinical implementation.

Association between long working hours and engagement in preventive healthcare services in Korean workers: Findings from the Korean National Health and Nutrition Examination Survey.

BACKGROUND: Engagement in preventive healthcare services is crucial for preventing diseases. We explored how working hours are associated with engagement in preventive healthcare services, with a focus on gender differences. METHODS: This cross-sectional study used data from the 2007-2012 Korean National Health and Nutrition Examination Survey. The dependent variable was engagement in each of the five preventive healthcare services (health check-ups, influenza vaccination, and stomach, breast, and cervical cancer screenings). We estimated the prevalence ratios (PRs) and 95% confidence intervals (CIs) using robust Poisson regression. RESULTS: The study analyzed 19,819 workers (9119 women). The adjusted PRs (95% CI) of the association between working ≥55 h per week and engagement in preventive healthcare services among men were 0.95 (0.90-1.00) for health check-ups, 0.86 (0.77-0.96) for influenza vaccination, and 0.95 (0.87-1.03) for stomach cancer screening compared to working 35-40 h per week. Among women, the adjusted PRs (95% CI) of the association between working ≥55 h per week and engagement in preventive healthcare services were 0.84 (0.78-0.91) for health check-ups, 0.82 (0.73-0.92) for influenza vaccination, and 0.88 (0.80-0.97) for stomach, 0.85 (0.78-0.94) for breast, and 0.82 (0.74-0.91) for cervical cancer screenings. CONCLUSION: Long working hours were negatively associated with engagement in preventive healthcare services, and the association was pronounced among female workers. Efforts to promote preventive healthcare participation among individuals with long working hours are necessary, and it is essential to consider the unique vulnerabilities of women when developing such policies.

Distinct age-related differences among victims in cases of suspected child abuse.

Evidence describing age-related differences among children with suspected physical and sexual child abuse is lacking. We describe findings in severe cases of suspected abuse. Cases with 756 children <15 years old were included during 2001-2013 at the Department of Forensic Medicine, Aarhus University, using forensic evaluation documents, medical records, and court proceedings. Eight percent of children <4 years old died from child abuse, 36% through violence resulting in death, and 64% by manslaughter, whereas 1% > 4 years old died, solely by manslaughter. External injuries were mainly located to head and torso in children <4 years old, changing to the upper and lower extremities in older children. Child sexual abuse was suspected in 52% of cases with living children <4 years old, 83% of children 4-7 years of age, 88% of children 8-11 years of age, and 93% of children >12 years old. Anogenital findings were mainly caused by other medical conditions in children <4 years old, hymenal clefts in the superior half of the hymenal rim were almost exclusively found in children between 8 and 11 years of age, whereas both superficial and complete hymenal clefts in the inferior half of the hymenal rim were found in children >12 years old. The present study describes age-related differences in victims of suspected child abuse. Fatal versus nonfatal child physical abuse and the significance of hymenal findings in child sexual abuse could be studied further.

Forensic-medical characteristics of penetrating wounds as manifestations of explosive trauma in the case of decomposed bodies examination.

The Russian invasion of Ukraine in 2022 caused a significant spike in the number of deaths from blast injury. The impossibility of evacuating the bodies of dead servicemen or civilians from the battlefield for a long time leads to the fact that forensic experts often have to deal with the examination of bodies in a state of decomposed changes. At the same time, the material and technical support of forensic medical institutions in different parts of Ukraine is heterogeneous: most experts do not have access to laboratory or instrumental research methods and can only rely on macroscopic research data. This article provides an overview of the cases of expert examination of cases of explosive trauma of decomposed bodies using macroscopic, microscopic, chemical and instrumental research, which indicates the high efficiency of their use for the purpose of solving expert questions of various nature. At the same time, the identified morphological characteristics of the damage are not purely specific and indicate the action of a blunt solid object with a limited contact surface, which had high kinetic energy and significant penetrating capacity.

[On the study of postmortem tissue changes' dynamics according to impedance metrics data]. / K voprosu izucheniya dinamiki postmortal'nykh izmenenii tkanei po dannym impedansometrii.

OBJECTIVE: To find a way and form of presenting impedance metrics data to clarify prescription of death coming in a comprehensive assessment. MATERIAL AND METHODS: The impedance of biological objects was measured depending on prescription of death coming in standardized conditions (air temperature +4 °C, humidity 45%). The main examined postmortem period was 1 months. Measurements were made on 3 diagnostic zones of biological object and for 5 current frequency of the study. A total of 2100 readings were taken. RESULTS AND CONCLUSION: The studies performed in standardized conditions have showed that using impedance metrics method to diagnose prescription of death coming is possible. The analysis of only absolute impedance values is not sufficient to clarify prescription of death coming due to its undulating changes. The additional use of relative coefficients, characterizing impedance dispersion, is suggested. The study of possible using the impedance indicators of corpse's tissues to determine prescription of death coming should be performed with consideration to pathomorphology of degradation. Further study of impedance dynamics when corpse is under different conditions is necessary for development of a working algorithm to determine prescription of death coming based on tissue impedance.

[History of forensic medical examination service in Belarus in the Soviet period (1918-1991)]. / Istoriya sudebno-meditsinskoi ekspertizy Belarusi v sovetskii period (1918­1991).

The article presents a part of historical path (1918-1991) of forensic medical examination in the Republic of Belarus, the history of origin, formation and development of forensic medical service and the academical departments of forensic medicine in the BSSR. The creation date of the state forensic medical service on the territory of Belarus can be considered as 3 of July 1918 yr. Since then, the service has passed from the judicial and administrative subdivision of the department of public healthcare of Executive Committee of Vitebsk Council of Workers, Peasant and Red Army Deputies (1918), the department of forensic medicine of the PCH of the BSSR (1919), forensic medical department at the Central Chemical and Biological Station of the PCH of the BSSR (1921) to the Institute of Scientific and Forensic Examination of the BSSR (1929), Central Forensic Medical Laboratory of the PCH of the BSSR (1931) and Republican Bureau of Forensic Medical Examination under the Ministry of Healthcare of the BSSR (1952). The historical stages of the existence of the forensic medical service and its state organizations in the BSSR were following: 1) stage of origin (1918-1922); 2) stage of formation (1921-1941, 1946-1952); 3) stage of development (1952). The main forensic medical experts, who made a significant contribution to the origin, formation and development of forensic medical examination in the territory of Belarus were V.F. Chervakov (1930-1939), S.A. Prilutskiy (1939-1941, 1946-1960), V.K. Steshits (1961-1977) and S.S. Maksimov (from 1977).

[Comparative analysis of the European and Russian models of medical examination (overview)].

Screening or its synonym medical check-up is the result of a health indicator, representing results of a medical examination and an effective tool of disease prevention. The concept of the term screening in European countries implies active detection of a disease or a premorbidity in people who are considered or consider themselves healthy. Medical check-up is a set of measures that includes preventive medical examination and additional methods of examinations conducted in order to assess the state of health and carried out in relation to certain groups of the population. The study and analysis of the international screening model and experience of its implementation, its role in the system of primary health care, including rehabilitation, is very important in terms of shaping public health at the international level. The article discusses regional trends in screening (medical check-up) and issues related to the conceptual and methodological aspects of medical check-up organization in the context of public health and prevention of risk factors. The data were searched in Scopus Web of Science, MedLine, the Cochrane Library, PubMed.

Assessing the Performance of ChatGPT in Medical Biochemistry Using Clinical Case Vignettes: Observational Study.

BACKGROUND: ChatGPT has gained global attention recently owing to its high performance in generating a wide range of information and retrieving any kind of data instantaneously. ChatGPT has also been tested for the United States Medical Licensing Examination (USMLE) and has successfully cleared it. Thus, its usability in medical education is now one of the key discussions worldwide. OBJECTIVE: The objective of this study is to evaluate the performance of ChatGPT in medical biochemistry using clinical case vignettes. METHODS: The performance of ChatGPT was evaluated in medical biochemistry using 10 clinical case vignettes. Clinical case vignettes were randomly selected and inputted in ChatGPT along with the response options. We tested the responses for each clinical case twice. The answers generated by ChatGPT were saved and checked using our reference material. RESULTS: ChatGPT generated correct answers for 4 questions on the first attempt. For the other cases, there were differences in responses generated by ChatGPT in the first and second attempts. In the second attempt, ChatGPT provided correct answers for 6 questions and incorrect answers for 4 questions out of the 10 cases that were used. But, to our surprise, for case 3, different answers were obtained with multiple attempts. We believe this to have happened owing to the complexity of the case, which involved addressing various critical medical aspects related to amino acid metabolism in a balanced approach. CONCLUSIONS: According to the findings of our study, ChatGPT may not be considered an accurate information provider for application in medical education to improve learning and assessment. However, our study was limited by a small sample size (10 clinical case vignettes) and the use of the publicly available version of ChatGPT (version 3.5). Although artificial intelligence (AI) has the capability to transform medical education, we emphasize the validation of such data produced by such AI systems for correctness and dependability before it could be implemented in practice.

ANALYSIS OF DEFECTS IN THE FORENSIC MEDICAL ASSESSMENT OF CHANGES DISCOVERED DURING THE EXAMINATION OF PERSONS WHO DIED FROM TRAUMATIC BRAIN INJURY.

OBJECTIVE: The aim: To identify the main groups of expert defects that arise during the forensic assessment of changes detected during the examination of persons who died from a traumatic brain injury (TBI). PATIENTS AND METHODS: Materials and methods: A total of 102 repeated commission forensic medical examinations with changed conclusions in corpses with TBI were analyzed. Data processing and analysis were conducted using statistical methods. RESULTS: Results: The examined forensic medical assessments of TBI with changed conclusions in corpses were categorized into the following groups: defects in estab¬lishing the diagnosis of TBI - 17.65±7.4%; defects in establishing the mechanism of TBI - 35.3±9.3%; defects in establishing the duration of TBI - 39.22±9.5%: sober - 20±12.4%; with alcohol intoxication - 80±12.4%. A combination of defects was found in 7.83±5.2% of cases. Defects that directly affected the experts' incorrect establishment of the diagnosis, mechanism, and duration of TBI were also identified. CONCLUSION: Conclusions: The largest number of changed conclusions during the forensic medical examination of corpses in cases of TBI was due to the wrongly established duration of the trauma, accounting for 39.2±9.5%, with the vast majority of cases (80±12.4%) observed against the background of alcohol intoxication. The mechanism of trauma accounted for 35.3±9.3% of the changed conclusions. The main defects were incomplete collection of material for histological examination (90.2±5.8%) and incorrect interpretation of the results of histological examination (76.48±8.2%), along with the violation of the method of sectional examination (68.6±9.0%). Different groups of expert defects predominated in the cases with an incorrectly established diagnosis of TBI, duration of trauma, and mechanism.

[Forensic medical examination of the age of living persons in Russia: problematic aspects and solutions]. / Sudebno-meditsinskaya ekspertiza po ustanovleniyu vozrasta zhivykh lits v Rossii: problemnye aspekty i puti resheniya.

The article presents the results of the study of quantitative indicators and analytical compilation of forensic medical expert practice data in terms of the age of living persons in Russia examination as a whole and in individual federal districts and subjects of Russia in the period from 2003 to 2021. It has been established that against the background of the rather low number of expert examinations, performed to determine the living persons age, there has been an increase in this indicator since 2018, mainly due to the Central Federal District. Regional differences in the studied indicators were identified. A systematic survey study of literature (electronic search of publications in PubMed, Science Direct Scopus and eLIBRARY databases) was conducted on the issue of forensic medical assessment of living persons' age, including the methodical support of this examination type, to form an idea of existing scientific clusters. Search modes allowed to form an array of 184 publications indexed in the database Scopus, PubMed, and 8 publications presented in Russian Science Citation Index. The study results were used as a predictor of the efficacy of the package of measures to modernize this type of expert study. The proposed set of measures to improve the scientific and methodical support of forensic medical examination for age establishment will optimize practical activities and increase the evidential efficacy of expert opinions.

[Expert characteristic of fatal outcomes related to operative interventions in aesthetic plastic surgery]. / Ekspertnaya kharakteristika letal'nykh iskhodov, svyazannykh s operativnymi vmeshatel'stvami v esteticheskoi plasticheskoi khirurgii.

THE AIM OF THE STUDY: Is to investigate fatal outcomes related to operative interventions in aesthetic plastic surgery for the period from 2010 to 2022 yrs., and to analyze the defects in health care delivery (DHCD), revealed during forensic medical examinations of fatal outcomes. The number of fatal outcomes equal 36, related to operative interventions in aesthetic plastic surgery, was analyzed. The data were collected from the expert's archival opinions (forensic medical examinations of corpse, commission forensic medical examinations based on materials of medical cases and expert opinions), and from judicial acts. The most frequent cause of death (19% of cases) was postoperative development of pulmonary artery thromboembolia, that requires further screening to assess the relationship between denoted reason and type of performed operative intervention as well as the use of anticoagulant therapy. In addition, 19% of the causes of death were related to the toxic lidocaine effects, that shows the necessity of strict control while using anaesthesia during operative interventions. During the forensic medical examination in 55.5% of cases were found the defects in health care delivery (DHCD), with an average of about two DHCD cases. Cause-effect relationship between identified drawbacks of health care delivery and fatal outcome was established in 18 (90%) of the 20 cases. Among them, the DHCD, which are extremely rare in other types of surgical specialty (health care delivery in an inappropriate place and by unqualified persons), were reliably determined in 30% of cases. The necessity of strict control by the relevant competent organizations in health care delivery for plastic surgery specialty, the need for a single system collection of information about fatal cases, associated with operative interventions in aesthetic plastic surgery, and the study of fatality structure and causes in this field were proved. The above mentioned will make it possible to develop unified approaches for the commission forensic medical examinations in this type of cases, and will also contribute to the fatal outcomes' prevention.

[Participation of aeromedicine specialists in complex forensic medical examination in aviation accidents]. / Uchastie spetsialistov v oblasti aviatsionnoi meditsiny pri provedenii kompleksnykh sudebno-meditsinskikh ekspertiz v sluchayakh aviatsionnykh katastrof.

The problem of flight safety and aviation injury were considered, data on aviation accidents in Civil aviation were shown, the main causes of aviation accidents were presented: technical failure, difficult meteorological conditions, deficiencies in flight organization and «human factor¼. The conditional classification of aviation injury was presented. Detection of primary injuries is especially important for aeromedicine (head impact on dashboard, bone fracture at the ankle, «loss of vital space¼, laceration between 1st and 2nd fingers from the control wheel), that determine the pattern of pilots' actions in an emergency situation. A three-link flight medical support system was remained to prevent flying under the influence of alcohol, drugs and psychoactive substances. The Department of Aerospace Medicine developed the algorithm of pilots' examination suspected of using toxic substances. The materials of pilot's psychological examination after an aviation accident in the state of posttraumatic stress disorder are presented.

[Justification of the need to introduce an additional criterion to the assessment of the nutrition status of military personnel].

Currently, in accordance with the regulations of the Government of the Russian Federation and the Ministry of Defense of the Russian Federation, the main indicator for assessing nutritional status is the body mass index, which does not take into account the component composition of the body. At the same time, it is necessary to assess in more detail the composition of the body of military personnel, that is, the ratio of its muscle and fat components. The purpose of the study is the scientific and methodological substantiation of the need to introduce an additional criterion for assessing the nutritional status of military personnel, that characterize body composition - the body fat percentage. Material and methods. The study involved 1.373 male military personnel aged 18 to 53 who underwent a medical examination. The following methods were used: anthropometry, bioimpedancemetry, caliperometry. Results. Various methods for determining the fat component of the body have been studied. The analysis of the data obtained showed that all methods for determining the body fat percentage have highly significant correlations among themselves and with bioimpedancemetry data. All coefficients had high reliability p<0.001 at r>0.7. When the values of the body mass index deviate from the normative ones, it is proposed to use the indicator of the body fat percentage to clarify the assessment of the nutritional status of male military personnel. Based on the data obtained, modern algorithms for assessing the nutritional status of military personnel have been developed for use in the practice of military health care at various levels of medical support for military personnel. Conclusion. As a result of a prospective study, the need to introduce an additional criterion for assessing the nutritional status of male military personnel was substantiated and proved, and calculation methods for assessing the fat component of the body, comparable with bioimpedancemetry data, were determined. Algorithms for determining the nutritional status of servicemen for different levels of medical support have been developed. In conditions where special devices for determining the fat component of the body are not included in the supply standards of the medical service, it is recommended to calculate the body fat percentage by girth methods using a centimeter tape.

Performance of ChatGPT on the Peruvian National Licensing Medical Examination: Cross-Sectional Study.

BACKGROUND: ChatGPT has shown impressive performance in national medical licensing examinations, such as the United States Medical Licensing Examination (USMLE), even passing it with expert-level performance. However, there is a lack of research on its performance in low-income countries' national licensing medical examinations. In Peru, where almost one out of three examinees fails the national licensing medical examination, ChatGPT has the potential to enhance medical education. OBJECTIVE: We aimed to assess the accuracy of ChatGPT using GPT-3.5 and GPT-4 on the Peruvian National Licensing Medical Examination (Examen Nacional de Medicina [ENAM]). Additionally, we sought to identify factors associated with incorrect answers provided by ChatGPT. METHODS: We used the ENAM 2022 data set, which consisted of 180 multiple-choice questions, to evaluate the performance of ChatGPT. Various prompts were used, and accuracy was evaluated. The performance of ChatGPT was compared to that of a sample of 1025 examinees. Factors such as question type, Peruvian-specific knowledge, discrimination, difficulty, quality of questions, and subject were analyzed to determine their influence on incorrect answers. Questions that received incorrect answers underwent a three-step process involving different prompts to explore the potential impact of adding roles and context on ChatGPT's accuracy. RESULTS: GPT-4 achieved an accuracy of 86% on the ENAM, followed by GPT-3.5 with 77%. The accuracy obtained by the 1025 examinees was 55%. There was a fair agreement (κ=0.38) between GPT-3.5 and GPT-4. Moderate-to-high-difficulty questions were associated with incorrect answers in the crude and adjusted model for GPT-3.5 (odds ratio [OR] 6.6, 95% CI 2.73-15.95) and GPT-4 (OR 33.23, 95% CI 4.3-257.12). After reinputting questions that received incorrect answers, GPT-3.5 went from 41 (100%) to 12 (29%) incorrect answers, and GPT-4 from 25 (100%) to 4 (16%). CONCLUSIONS: Our study found that ChatGPT (GPT-3.5 and GPT-4) can achieve expert-level performance on the ENAM, outperforming most of our examinees. We found fair agreement between both GPT-3.5 and GPT-4. Incorrect answers were associated with the difficulty of questions, which may resemble human performance. Furthermore, by reinputting questions that initially received incorrect answers with different prompts containing additional roles and context, ChatGPT achieved improved accuracy.

Success of ChatGPT, an AI language model, in taking the French language version of the European Board of Ophthalmology examination: A novel approach to medical knowledge assessment.

PURPOSE: The purpose of this study was to evaluate the performance of ChatGPT, a cutting-edge artificial intelligence (AI) language model developed by OpenAI, in successfully completing the French language version of the European Board of Ophthalmology (EBO) examination and to assess its potential role in medical education and knowledge assessment. METHODS: ChatGPT, based on the GPT-4 architecture, was exposed to a series of EBO examination questions in French, covering various aspects of ophthalmology. The AI's performance was evaluated by comparing its responses with the correct answers provided by ophthalmology experts. Additionally, the study assessed the time taken by ChatGPT to answer each question as a measure of efficiency. RESULTS: ChatGPT achieved a 91% success rate on the EBO examination, demonstrating a high level of competency in ophthalmology knowledge and application. The AI provided correct answers across all question categories, indicating a strong understanding of basic sciences, clinical knowledge, and clinical management. The AI model also answered the questions rapidly, taking only a fraction of the time needed by human test-takers. CONCLUSION: ChatGPT's performance on the French language version of the EBO examination demonstrates its potential to be a valuable tool in medical education and knowledge assessment. Further research is needed to explore optimal ways to implement AI language models in medical education and to address the associated ethical and practical concerns.