(1) Background: As the field of artificial intelligence (AI) evolves, tools like ChatGPT are increasingly integrated into various domains of medicine, including medical education and research. Given ...the critical nature of medicine, it is of paramount importance that AI tools offer a high degree of reliability in the information they provide. (2) Methods: A total of
= 450 medical examination questions were manually entered into ChatGPT thrice, each for ChatGPT 3.5 and ChatGPT 4. The responses were collected, and their accuracy and consistency were statistically analyzed throughout the series of entries. (3) Results: ChatGPT 4 displayed a statistically significantly improved accuracy with 85.7% compared to that of 57.7% of ChatGPT 3.5 (
< 0.001). Furthermore, ChatGPT 4 was more consistent, correctly answering 77.8% across all rounds, a significant increase from the 44.9% observed from ChatGPT 3.5 (
< 0.001). (4) Conclusions: The findings underscore the increased accuracy and dependability of ChatGPT 4 in the context of medical education and potential clinical decision making. Nonetheless, the research emphasizes the indispensable nature of human-delivered healthcare and the vital role of continuous assessment in leveraging AI in medicine.
The United States Medical Licensing Examination (USMLE) has been critical in medical education since 1992, testing various aspects of a medical student's knowledge and skills through different steps, ...based on their training level. Artificial intelligence (AI) tools, including chatbots like ChatGPT, are emerging technologies with potential applications in medicine. However, comprehensive studies analyzing ChatGPT's performance on USMLE Step 3 in large-scale scenarios and comparing different versions of ChatGPT are limited.
This paper aimed to analyze ChatGPT's performance on USMLE Step 3 practice test questions to better elucidate the strengths and weaknesses of AI use in medical education and deduce evidence-based strategies to counteract AI cheating.
A total of 2069 USMLE Step 3 practice questions were extracted from the AMBOSS study platform. After including 229 image-based questions, a total of 1840 text-based questions were further categorized and entered into ChatGPT 3.5, while a subset of 229 questions were entered into ChatGPT 4. Responses were recorded, and the accuracy of ChatGPT answers as well as its performance in different test question categories and for different difficulty levels were compared between both versions.
Overall, ChatGPT 4 demonstrated a statistically significant superior performance compared to ChatGPT 3.5, achieving an accuracy of 84.7% (194/229) and 56.9% (1047/1840), respectively. A noteworthy correlation was observed between the length of test questions and the performance of ChatGPT 3.5 (ρ=-0.069; P=.003), which was absent in ChatGPT 4 (P=.87). Additionally, the difficulty of test questions, as categorized by AMBOSS hammer ratings, showed a statistically significant correlation with performance for both ChatGPT versions, with ρ=-0.289 for ChatGPT 3.5 and ρ=-0.344 for ChatGPT 4. ChatGPT 4 surpassed ChatGPT 3.5 in all levels of test question difficulty, except for the 2 highest difficulty tiers (4 and 5 hammers), where statistical significance was not reached.
In this study, ChatGPT 4 demonstrated remarkable proficiency in taking the USMLE Step 3, with an accuracy rate of 84.7% (194/229), outshining ChatGPT 3.5 with an accuracy rate of 56.9% (1047/1840). Although ChatGPT 4 performed exceptionally, it encountered difficulties in questions requiring the application of theoretical concepts, particularly in cardiology and neurology. These insights are pivotal for the development of examination strategies that are resilient to AI and underline the promising role of AI in the realm of medical education and diagnostics.
Objective
To analyze the effect of contralateral knee pain on sensitivity of patient‐reported outcomes and objectively measured functional performance tests in subjects with knee osteoarthritis (OA).
...Methods
Subjects with discordant knee pain status (i.e., 1 knee being painful ≥4 on a numeric pain rating scale (NPRS), with the contralateral knee being pain free NPRS 0) were selected from the Osteoarthritis Initiative and matched to subjects with bilaterally pain‐free and painful knees by age, sex, body mass index, and radiographic knee OA. The Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) physical function score, the global Physical Activity Scale for the Elderly (PASE), and objective functional performance tests were cross‐sectionally compared in a matched case–control design.
Results
A total of 378 subjects with discordant knee pain status were matched to 359 controls with bilaterally pain‐free knees and to 323 controls with bilaterally painful knees. WOMAC scores in pain‐free knees of discordant knee pain cases significantly differed compared to scores of bilaterally pain‐free knees (P = 0.003). Likewise, scores in painful knees of discordant knee pain cases significantly differed compared to scores of bilaterally painful knees (P < 0.001). PASE levels between these groups were not significantly different (P > 0.68). Functional performance tests differed in subjects with discordant knee pain compared to subjects with bilaterally pain‐free knees and when compared to subjects with bilaterally painful knees, with the chair stand test showing the strongest effect size (standardized response mean 0.28 and 0.33, respectively).
Conclusion
The WOMAC physical function score, although knee specific, is impacted by the contralateral knee pain status. The repeated chair stand test appears to be the most sensitive assessment in differentiation between groups with different status of knee pain.
Objectives: To assess the effect of oxygen-ozone therapy guided by percutaneous Computed Tomography (CT) compared to corticosteroids in individuals experiencing lower back pain (LBP) not attributed ...to underlying bone-related issues. Methods: A total of 321 patients (192 males and 129 females, mean age: 51.5 ± 15.1 years) with LBP were assigned to three treatment groups: group A) oxygen-ozone only, group B) corticosteroids only, group C) oxygen-ozone and corticosteroids. Treatment was administered via CT-guided injections to the intervertebral disc (i.e., intradiscal location). Clinical improvement of pain and functionality was assessed via self-reported pain scales and magnetic resonance (MR) and CT imaging. Results: At all follow-up times, the mean score of the numeric rating scale and the total global pain scale (GPS) of study groups receiving oxygen-ozone (groups A and C) were statistically significantly lower than the study group receiving corticosteroids only (group B), with p < 0.001. There was a statistically significant difference between groups A and C at 30 days for the numeric rating scale. Conclusions: The percutaneous application of oxygen-ozone in patients with LBP due to degeneration of the lumbosacral spine showed long-lasting significant pain reduction of up to two years post-treatment when compared to corticosteroids alone. Combination therapy of oxygen-ozone and corticosteroids can be useful as corticosteroids showed statistically significant improvement in LBP earlier than the oxygen-ozone-only treatment.
Purpose
Morphological data pertaining to the pelvis and lower extremity muscles are increasingly being used in biomechanical modeling to compare healthy and pathological conditions. Very few data ...sets exist that encompass all of the muscles of the lower limb, allowing for comparisons between regions. The aims of this study were to (a) provide physiological cross-sectional area (PCSA) data for the pelvic, thigh, and leg muscles in young, healthy participants, using magnetic resonance imaging (MRI), and (b) to compare these data with summarized PCSAs obtained from the literature.
Materials and methods
Six young and healthy volunteers participated and were scanned using 3 T MRI. PCSAs were calculated from volumetric segmentations obtained bilaterally of 28 muscles/muscle groups of the pelvis, thigh, and leg. These data were compared to published, summarized PCSA data derived from cadaveric, computed tomography, MRI and ultrasound studies.
Results
The PCSA of the pelvis, thigh, and leg muscles tended to be 20–130% larger in males than in females, except for the gemelli which were 34% smaller in males, and semitendinosus and triceps surae which did not differ (<20% different). The dominant and the non-dominant sides showed similar and minutely different PCSA with less than 18% difference between sides. Comparison to other studies revealed wide ranges within, and large differences between, the cadaveric and imaging PCSA data. Comparison of the PCSA of this study and published literature revealed major differences in the iliopsoas, gluteus minimus, tensor fasciae latae, gemelli, obturator internus, biceps femoris, quadriceps femoris, and the deep leg flexor muscles.
Conclusions
These volume-derived PCSAs of the pelvic and lower limb muscles alongside the data synthesised from the literature may serve as a basis for comparative and biomechanical studies of the living and healthy young, and enable calculation of muscle forces. Comparison of the literature revealed large variations in PCSA from each of the different investigative modalities, hampering comparability between studies. Sample size, age, post-mortem changes of muscle tone, chemical fixation of cadaveric tissues, and the underlying physics of the imaging techniques may potentially influence PCSA calculations.
Hands‐on dissection‐based learning of anatomy offers an unique and valued experience for medical students. Too often however, the inexperienced student's focus is to avoid damage to unfamiliar ...structures instead of understanding spatial relationships between structures. This results in unfortunate surrender of a critical learning experience. Additionally, approaches to dissection and anatomic exposure share little alignment to clinical approaches, making it less powerful in clinical applicability. The goal of this viewpoint commentary is based on the experience of the two authors and aims to demonstrate opportunity to introduce clinical approaches for dissection while incorporating relevant anatomical concepts in medical school curriculum that aligns with authentic healthcare practice. Using the dissections of the superficial face as a relevant and current topic of clinical interest, we point out that applying the currently performed dissection approach (medial‐to‐lateral) falls short of providing sufficient knowledge and understanding of the layered arrangement of facial structures. The lateral‐to‐medial approach, as performed in surgical face lifting procedures would offer a better understanding of the layers of the face and especially the superficial musculoaponeurotic system (SMAS) accounting for the difficulties of facial dissections on embalmed cadavers. This commentary could offer a potential change in paradigm for students and course facilitators for how to maximize the knowledge transfer during facial dissections. It potentially opens a door to rethink dissection‐based learning of anatomy toward techniques and approaches that are aligned to surgical access pathways and thus considered more clinically relevant.
HLA-G is a non-classical MHC class Ib molecule predominantly expressed in cytotrophoblasts and under pathological conditions also in chronically inflamed and in malignant tissues. Recently an ...increased expression of HLA-G was found in ulcerative colitis (UC), but not in Crohn's disease (CD). The HLA-G gene is located in IBD3, a linkage region for inflammatory bowel disease (IBD). A 14-bp deletion polymorphism (Del+/Del−) within exon 8 of the HLA-G gene might influence transcription activity and is therefore of potential functional relevance. To investigate whether the 14-bp deletion polymorphism is associated with IBD, 371 patients with CD, 257 patients with UC and 739 controls were genotyped. The heterozygous genotype (P = 0.031) and the Del+ phenotype (P = 0.038) were significantly increased, whereas the homozygous Del− phenotype (P = 0.038) was significantly decreased in UC when compared with CD. Thus, the 14-bp deletion polymorphism within the HLA-G gene displayed significant differences between UC and CD. Moreover, a significant increase of the Del+ allele (P = 0.002) and the Del+/Del+ genotype (P = 0.013) and a consecutive decrease of the Del−/− genotype (P = 0.024) were observed in those CD cases positive for ileocecal resection. Thus, a potential effect of the HLA-G gene in IBD may affect both UC and CD. Other polymorphisms linked to the 14-bp deletion polymorphism might also contribute to immunopathogenesis. As there are several partly functional polymorphisms within the promoter region potentially influencing HLA-G expression, further studies in IBD are necessary in the context of differential expression of HLA-G between UC and CD.
PDF
