A Comparative Analysis of ChatGPT and Medical Faculty Graduates in Medical Specialization Exams: Uncovering the Potential of Artificial Intelligence in Medical Education.

Background This study aims to evaluate the performance of ChatGPT in the medical specialization exam (MSE) that medical graduates take when choosing their postgraduate specialization and to reveal how artificial intelligence-supported education can increase the quality and academic success of medical education. The research aims to explore the potential applications and advantages of artificial intelligence in medical education and examine ways in which this technology can contribute to student learning and exam preparation. Methodology A total of 240 MSE questions were posed to ChatGPT, 120 of which were basic medical sciences questions and 120 were clinical medical sciences questions. A total of 18,481 people participated in the exam. The performance of medical school graduates was compared with ChatGPT-3.5 in terms of answering these questions correctly. The average score for ChatGPT-3.5 was calculated by averaging the minimum and maximum scores. Calculations were done using the R.4.0.2 environment. Results The general average score of graduates was a minimum of 7.51 in basic sciences and a maximum of 81.46, while in clinical sciences, the average was a minimum of 12.51 and a maximum of 80.78. ChatGPT, on the other hand, had an average of at least 60.00 in basic sciences and a maximum of 72.00, with an average of at least 66.25 and a maximum of 77.00 in clinical sciences. The rate of correct answers in basic medical sciences for graduates was 43.03%, while for ChatGPT was 60.00%. In clinical medical sciences, the rate of correct answers for graduates was 53.29%, while for ChatGPT was 64.16%. ChatGPT performed best with a 91.66% correct answer rate in Obstetrics and Gynecology and an 86.36% correct answer rate in Medical Microbiology. The least successful area for ChatGPT was Anatomy, with a 28.00% correct answer rate, a subfield of basic medical sciences. Graduates outperformed ChatGPT in the Anatomy and Physiology subfields. Significant differences were found in all comparisons between ChatGPT and graduates. Conclusions This study shows that artificial intelligence models such as ChatGPT can provide significant advantages to graduates, as they score higher than medical school graduates. In terms of these benefits, recommended applications include interactive support, private lessons, learning material production, personalized learning plans, self-assessment, motivation boosting, and 24/7 access, among a variety of benefits. As a result, artificial intelligence-supported education can play an important role in improving the quality of medical education and increasing student success.

A comprehensive investigation of biochemical status in patients with telogen effluvium: Analysis of Hb, ferritin, vitamin B12, vitamin D, thyroid function tests, zinc, copper, biotin, and selenium levels.

AIM: The etiology of telogen effluvium (TE) includes situations that may cause physiological stress, surgical trauma, inflammatory, infectious, iatrogenic causes, medications and nutritional deficiencies. TE has been associated with iron deficiency, vitamin B12 deficiency and thyroid diseases. In recent years, the use of over-the-counter food supplements containing vitamins and minerals such as biotin, vitamin D, zinc (Zn), copper (Cu) and selenium (Se) has been increasing in TE patients. The aim of this study is to investigate whether there are differences in nutritional status, vitamin and mineral levels by comparing individuals with TE and a control group. MATERIALS AND METHODS: This case-control study included 90 female patients diagnosed with chronic telogen effluvium (CTE), and 90 female controls volunteered to participate in the study who consulted for reasons other than TE. Both groups aged 18 and over and applied to dermatology polyclinic between 01.09.2022 and 01.09.2023. A detailed anamnesis was taken from all patients, a hair pull test was performed, and TE was diagnosed after a dermoscopic examination was performed on all areas of the scalp. Then, serum vitamin D, Zn, Cu, Se levels and biotin levels in serum and urine were measured. Hemoglobin (Hb), ferritin, vitamin B12 and thyroid function tests were retrospectively scanned from the hospital database. RESULTS: It was determined that Zn levels were significantly lower in CTE patients than in controls. Se levels were found to be significantly higher in patients than in controls. There was no difference in Hb, ferritin, vitamin B12, thyroid function tests, vitamin D, Cu levels, serum and urine biotin levels between the two groups. Zn, Cu/Zn and Se levels were found to have statistically significant diagnostic performance in predicting the diagnosis of CTE. Cu/Zn ratio and Se value were found to be significant predictors of CTE. CONCLUSION: This study shows us that nutritional deficiencies are not as common as thought in patients diagnosed with TE. Other causes that may cause TE should be investigated by a detailed anamnesis and a good physical examination. After all, tests for suspected conditions should be performed and individualized treatment options should be created for each patient.

Retrospective analysis of serologic test requests in the diagnosis of viral hepatitis: Inappropriate test requests and cost.

The rational laboratory use and implementation of test ordering procedures aim to reduce unnecessary test requests. This study aimed to determine the financial burden caused by inappropriate serological test requests for viral hepatitis and to investigate physicians' reasons for making unnecessary test requests. We performed a retrospective evaluation of inappropriate requests for hepatitis serology testing and the financial burden they caused at a tertiary care hospital over a 1-year period. The study found 2183 (3.84%) inappropriate test requests, costing $3309.00. Of these, 357 were same-day repeat requests and 1826 were requests not following diagnostic algorithms. In the logistic regression analysis of the factors affecting unnecessary test requests, a statistically significant difference was found between whether the unit was internal or surgical, whether the request came from inpatient services or outpatient clinics, and the professional titles (P < .05). Both types of inappropriate requests were more common among male physicians (P < .05). The highest rates of inappropriate test requesting were in physical therapy and rehabilitation, pediatrics, and adult emergency units. To identify the reasons behind unnecessary test requests, 135 physicians from 23 different departments participated in the survey. The main reasons for requesting tests were identified as protecting against malpractice and fears of misdiagnosis or overlooking a diagnosis. It has been observed that physicians often order tests routinely, without being fully familiar with standard test ordering procedures based on diagnostic algorithms, and lacking knowledge about rational laboratory use. The cost of tests is mostly unknown to clinicians. The study concludes that there are laboratory tests that incur much higher costs. When this assessment is applied to the entire laboratory, it becomes clear how significant a financial burden, unnecessary workload, and loss of time this situation can cause. Identifying the presence of unnecessary test requests is the first step in preventing them. Appropriate measures include highlighting these issues, providing necessary information, and offering in-service training.

Analysis of the effect of hashimoto's thyroiditis and insulin resistance on ovarian volume in patients with polycystic ovary syndrome.

OBJECTIVE: In this study, patients were divided into two groups. Patients with polycystic ovary syndrome (PCOS) and patients with polycystic ovary syndrome + Hashimoto's Thyroid (PCOS + HT). The effect of insulin resistance on ovarian volume in patients divided into two groups and the change in ovarian volume with the addition of HT to PCOS will be investigated. MATERIAL AND METHODS: 46 PCOS patients and 46 PCOS patients diagnosed with HT were included in this study. A detailed medical history was taken from all participants. Polycystic ovary image was evaluated as below or above 10 ml and antral follicles were counted by transvaginal ultrasound. Insulin resistance of the patients was evaluated according to the fasting insulin (HOMA) index. RESULTS: Insulin resistance was found to be associated with fasting insulin, HOMA index, body mass index and right ovarian volume in patients diagnosed with PCOS. Among the patients diagnosed with PCOS + HT, insulin resistance was found to be significantly correlated with fasting insulin, HOMA index, (BMI), (SHBG) and left ovarian volume. An increase in right ovarian volume was found in 37.5% of patients with PCOS without insulin resistance and in 76.3% of patients with insulin resistance. An increase in left ovarian volume was found in 35.7% of patients without insulin resistance diagnosed with PCOS + HT and in 68.8% of patients with insulin resistance. CONCLUSIONS: This study shows that ovarian volume should be evaluated in every PCOS patient in order to predict insulin resistance, which causes long-term metabolic diseases, and that all PCOS patients with increased ovarian volume should be investigated for insulin resistance. In addition, it has been observed that insulin resistance affects left ovarian volume in patients with PCOS + HT, whereas insulin resistance affects the volume of the right ovary more in patients with PCOS. At least one ovary has been found to be affected by long-term metabolic diseases. While there was a greater increase in ovarian volume with the addition of insulin resistance, no significant change was observed in the number of patients with increased ovarian volume (PCOS-58, PCOS + HT-57) with the addition of HT finding.