Comparison of ChatGPT-3.5, ChatGPT-4, and Orthopaedic Resident Performance on Orthopaedic Assessment Examinations.

INTRODUCTION: Artificial intelligence (AI) programs have the ability to answer complex queries including medical profession examination questions. The purpose of this study was to compare the performance of orthopaedic residents (ortho residents) against Chat Generative Pretrained Transformer (ChatGPT)-3.5 and GPT-4 on orthopaedic assessment examinations. A secondary objective was to perform a subgroup analysis comparing the performance of each group on questions that included image interpretation versus text-only questions. METHODS: The ResStudy orthopaedic examination question bank was used as the primary source of questions. One hundred eighty questions and answer choices from nine different orthopaedic subspecialties were directly input into ChatGPT-3.5 and then GPT-4. ChatGPT did not have consistently available image interpretation, so no images were directly provided to either AI format. Answers were recorded as correct versus incorrect by the chatbot, and resident performance was recorded based on user data provided by ResStudy. RESULTS: Overall, ChatGPT-3.5, GPT-4, and ortho residents scored 29.4%, 47.2%, and 74.2%, respectively. There was a difference among the three groups in testing success, with ortho residents scoring higher than ChatGPT-3.5 and GPT-4 ( P < 0.001 and P < 0.001). GPT-4 scored higher than ChatGPT-3.5 ( P = 0.002). A subgroup analysis was performed by dividing questions into question stems without images and question stems with images. ChatGPT-3.5 was more correct (37.8% vs. 22.4%, respectively, OR = 2.1, P = 0.033) and ChatGPT-4 was also more correct (61.0% vs. 35.7%, OR = 2.8, P < 0.001), when comparing text-only questions versus questions with images. Residents were 72.6% versus 75.5% correct with text-only questions versus questions with images, with no significant difference ( P = 0.302). CONCLUSION: Orthopaedic residents were able to answer more questions accurately than ChatGPT-3.5 and GPT-4 on orthopaedic assessment examinations. GPT-4 is superior to ChatGPT-3.5 for answering orthopaedic resident assessment examination questions. Both ChatGPT-3.5 and GPT-4 performed better on text-only questions than questions with images. It is unlikely that GPT-4 or ChatGPT-3.5 would pass the American Board of Orthopaedic Surgery written examination.

Cost and Complications of Percutaneous Fixation of Hand Fractures in a Procedure Room Versus the Operating Room.

BACKGROUND: The purpose of this study was to compare closed reduction and percutaneous pinning of metacarpal and phalanx fractures performed in the operating room (OR) versus the procedure room of the emergency department with primary outcomes being infection rate, radiographic union, and monetary cost. METHODS: From January 2006 to December 2010, all closed reduction and percutaneous pinnings of metacarpal and phalanx fractures (CPT codes: 26608; 26727) by a single board-certified hand surgeon (A.M.H.) were retrospectively reviewed. Patients were placed into 2 groups: Group 1 was patients treated in the OR, and group 2 was patients in an emergency department procedure room. Infection, malunion, and nonunion rates were compared using a chi-square test. Charges were compared using a t-test, and cost of supplies and labor was evaluated. RESULTS: A total of 189 patients met final inclusion criteria for this study: 130 in group 1 and 59 in group 2. There was no statistically significant difference in infection rates ( P = .13), nonunion ( P = .40), malunion rates ( P = .89), and hardware failure with revision ( P = .94) between the 2 groups. The procedure room patients had an average hospital charge of $1358.55 compared with $3691.85 for OR-treated patients (P = .001). The total cost of supplies and nonphysician labor was $432.31 per OR case and $179.59 per procedure room case. CONCLUSIONS: Metacarpal and phalanx fractures of the hand amendable to closed reduction and percutaneous pinning can be treated in the procedure room with no increase in risk of infection, malunion, or nonunion rates. In addition, these surgeries can be performed in a procedure room with lower cost and less charges to patients than in the operating room.

Dietary supplements.

The amount of published information on dietary supplements mushroomed in the 1990s. In fewer than 5 years, publications increased at least 100-fold in the medical literature alone. Dietary supplements are an uncharted territory that warrants complete and accurate exploration. One should not be surprised that disease and illness may respond to dietary supplements. Nutrition is the foundation to good health, and dietary supplements may prove to be some of the most powerful medicines ever discovered. An especially exciting discovery is that dietary supplements may enhance the effects of specific drugs. This discovery may lead to more effective and safer protocols for the treatment of cancer, heart and lung disease, and a host of chronic medical conditions. Information about dietary supplements is becoming more common in the popular medical literature and is creating increased curiosity and an increased awareness. The explosion of the dietary supplement market is compelling physicians to become aware of dietary supplements. Whether or not they are used in clinical practice is a decision for the individual physician. Given the increasing number of patients who are using dietary supplements, however, it is imperative that physicians have a good understanding of this topic. Considering the increasing complexity and magnitude of this topic, physician specialization may be essential. There are many good reference books, review articles, and internet sites on specific supplements that probably should be part of every physician's reference library. The accompanying box provides a brief list of such sources.