Evaluating performance of ChatGPT on MKSAP cardiology board review questions.

Chat Generative Pretrained Transformer (ChatGPT) is a natural language processing tool created by OpenAI. Much of the discussion regarding artificial intelligence (AI) in medicine is the ability of the language to enhance medical practice, improve efficiency and decrease errors. The objective of this study was to analyze the ability of ChatGPT to answer board-style cardiovascular medicine questions by using the Medical Knowledge Self-Assessment Program (MKSAP).The study evaluated the performance of ChatGPT (versions 3.5 and 4), alongside internal medicine residents and internal medicine and cardiology attendings, in answering 98 multiple-choice questions (MCQs) from the Cardiovascular Medicine Chapter of MKSAP. ChatGPT-4 demonstrated an accuracy of 74.5 %, comparable to internal medicine (IM) intern (63.3 %), senior resident (63.3 %), internal medicine attending physician (62.2 %), and ChatGPT-3.5 (64.3 %) but significantly lower than cardiology attending physician (85.7 %). Subcategory analysis revealed no statistical difference between ChatGPT and physicians, except in valvular heart disease where cardiology attending outperformed ChatGPT (p = 0.031) for version 3.5, and for heart failure (p = 0.046) where ChatGPT-4 outperformed senior resident. While ChatGPT shows promise in certain subcategories, in order to establish AI as a reliable educational tool for medical professionals, performance of ChatGPT will likely need to surpass the accuracy of instructors, ideally achieving the near-perfect score on posed questions.

Rhabdomyolysis Risk: The Dangers of Tribulus Terrestris, an Over-the-Counter Supplement.

BACKGROUND Over-the-counter (OTC) supplement use is a very common practice within the United States. Supplements are not tightly regulated by the Food and Drug Administration. There are many case reports involving OTC supplement adverse effects and medication interactions, but there remains minimal clinical research regarding these subjects. Rhabdomyolysis is one interaction and adverse effect frequently documented in case reports among a variety of OTC supplements, although, to date, there is no documentation of rhabdomyolysis occurring from an interaction between the supplement Tribulus terrestris and atorvastatin. CASE REPORT A 71-year-old man presented to the Emergency Department in rhabdomyolysis with a mild transaminitis after taking the over-the-counter supplement Tribulus terrestris while on long-term atorvastatin. His rhabdomyolysis peaked at day 4 after cessation of the Tribulus and atorvastatin and aggressive fluid resuscitation with a normal saline bolus at admission followed by a D5 sodium bicarbonate drip later transitioned to a normal saline drip with subsequent down-trending of the creatinine phosphokinase levels. CONCLUSIONS Tribulus terrestris is an herbal supplement used for erectile dysfunction and energy. Recent research suggests it to be a moderate CYP 3A4 inhibitor that plays a significant role in metabolism of statin and many other commonly prescribed medications. This may put patients at increased risk of developing serious adverse effects, including rhabdomyolysis and drug-induced liver injury. Screening patients for over-the-counter supplement use and educating them on the potential risks of their use is extremely important for inpatient and outpatient healthcare professionals to avoid dangerous medication interactions.

The dose-response characteristics of four NTCP models: using a novel CT-based radiomic method to quantify radiation-induced lung density changes.

Multiple competing normal tissue complication probability (NTCP) models have been proposed for predicting symptomatic radiation-induced lung injury in human. In this paper we tested the efficacy of four common NTCP models applied quantitatively to sub-clinical X-ray computed tomography (CT)-density changes in the lung following radiotherapy. Radiotherapy planning datasets and follow-up chest CTs were obtained in eight patients treated for targets within the lung or hilar region. Image pixel-wise radiation dose exposure versus change in observable CT Hounsfield units was recorded for early (2-5 months) and late (6-9 months) time-points. Four NTCP models, Lyman, Logistic, Weibull and Poisson, were fit to the population data. The quality of fits was assessed by five statistical criteria. All four models fit the data significantly (p < 0.05) well at early, late and cumulative time points. The Lyman model fitted best for early effects while the Weibull Model fitted best for late effects. No significant difference was found between the fits of the models and with respect to parameters D50 and γ50. The D50 estimates were more robust than γ50 to image registration error. For analyzing population-based sub-clinical CT pixel intensity-based dose response, all four models performed well.

A Prospective Outcomes Study of Proton Therapy for Chordomas and Chondrosarcomas of the Spine.

PURPOSE: To evaluate the effectiveness of definitive or adjuvant external beam proton therapy on survival in patients with chordomas and chondrosarcomas of the spine. METHODS AND MATERIALS: Between March 2007 and May 2013, 51 patients with a median age of 58 years (range, 22-83 years) with chordoma (n=34) or chondrosarcomas (n=17) of the sacrum (n=21), the cervical spine (n=20), and the thoracolumbar spine (n=10) were treated with external beam proton therapy to a median dose of 70.2 Gy(RBE) [range, 64.2-75.6 Gy(RBE)] at our institution. Distant metastases, overall survival, cause-specific survival, local control, and disease-free survival were calculated. RESULTS: The mean follow-up time was 3.7 years (range, 0.3-7.7 years). Across all time points, 25 patients experienced disease recurrence: 18 local recurrences, 6 local and distant recurrences, and 1 distant metastasis. The 4-year rates of overall survival and cause-specific survival were 72%; disease-free survival was 57%, local control was 58%, and freedom from distant metastases was 86%. The median time to local progression was 1.7 years (range, 0.2-6.0 years), and the median time to distant progression was 1.6 years (range, 0.2-6.0 years). The risk factors for local recurrence were age ≤58 years (62% vs 26%; P=.04) and recurrence after prior surgery (29% vs 81%; P=.01). Secondary cancers developed in 2 patients: B-cell lymphoma 5.5 years after treatment and bladder cancer 2 years after treatment. We observed the following toxicities: sacral soft tissue necrosis requiring surgery (n=2), T1 vertebral fracture requiring fusion surgery (n=1), chronic urinary tract infections (n=1), surgery for necrotic bone cyst (n=1), and grade 2 bilateral radiation nephritis (n=1). CONCLUSION: High-dose proton therapy controls more than half of spinal chordomas and chondrosarcomas and compares favorably with historic photon data. Local progression is the dominant mode of treatment failure and may be reduced by treating patients at the time of initial diagnosis. The impact of age is a novel finding of this study.