Introduction: Clinical documentation is a critical aspect of health care that enables healthcare providers to communicate effectively with each other and maintain accurate patient care records. Artificial intelligence tools, such as chatbots and virtual assistants, have the potential to assist healthcare providers in clinical documentation. ChatGPT is an artificial intelligence conversational model that generates human-like responses to text-based prompts. In this study, we sought to investigate ChatGPT's ability to assist with writing a history of present illness based on standardized patient histories. Methods: A blinded, randomized controlled study was conducted to compare the use of typing, dictation, and ChatGPT as tools to document history of present illness (HPI) of standardized patient histories. Eleven study participants, consisting of medical students, orthopaedic surgery residents, and attending surgeons, completed three HPIs using a different documentation technique for each one. Participants were randomized into cohorts based on the type of documentation technique. Participants were asked to interview standardized patients and document the patient's history of present illness using their assigned method. Results: ChatGPT was found to be intermediate for speed; dictation was fastest, but produced markedly longer and higher quality patient histories based on Physician Documentation Quality Instrument score compared with dictation and typing. However, ChatGPT included erroneous information in 36% of the documents. Poor agreement existed on the quality of patient histories between reviewers. Discussion: Our study suggests that ChatGPT has the potential to improve clinical documentation by producing more comprehensive and organized HPIs. ChatGPT can generate longer and more detailed documentation compared with typing or dictation documentation methods. However, additional studies are needed to investigate and address concerns regarding privacy, bias, and accuracy of information.

Proximal humerus fractures are the third most common fracture type in adults, with their incidence increasing over time. There are varied approaches to both the classification and treatment of proximal humerus fractures. Optimal treatments for this fracture type are still widely open to debate. This review summarizes the current and historical treatment modalities for proximal humerus fractures. In this paper, we provide updates on the advances and trends in the epidemiology, classification, and operative and nonoperative treatments of proximal humerus fractures.

Purpose: To investigate the injury rate in National Football League (NFL) athletes during the first 4 weeks of the 2020 NFL season. Methods: This study was a retrospective review of all NFL players who were placed on the injury report during the preseason and the first 4 weeks of the regular season from the 2016‐2017 through the 2020‐2021 NFL regular seasons. Players’ dates of injury were cross‐referenced with an absence of statistics from the respective games for which they were ruled out so as to ensure accuracy. Injury rates were calculated per 1,000 athletic exposures. Relative risk with 95% confidence intervals compared injury rates between the 2 cohorts. Results: Over the course of the study period of 4 NFL seasons, 3,025 injuries were reported. Of the 3,025 injuries reported, 582 (19%) occurred during weeks 1‐4 of the 2020‐2021 regular season, whereas 1,292 (53%) occurred during preseason weeks 1‐4, and 1,151 (38%) occurred during regular‐season weeks 1‐4 of NFL seasons 2016‐2017, 2018‐2019, and 2019‐2020. There was a significant increase in the injury rate during weeks 1‐4 of the 2020‐2021 regular season for all comparisons with the injury rate both during the preseasons and the regular seasons of 3 recent past NFL seasons. Conclusions: The rate of injury in NFL players during weeks 1‐4 of the 2020‐2021 regular seasons was significantly higher than during 3 recent past NFL preseasons and regular seasons. Level of Evidence: Level IV, diagnostic case series.

The integration of artificial intelligence technologies, such as large language models (LLMs), in health care holds potential for improved efficiency and decision support. However, ethical concerns must be addressed before widespread adoption. This article focuses on the ethical principles surrounding the use of Generative Pretrained Transformer-4 and its conversational model, ChatGPT, in healthcare settings. One concern is potential inaccuracies in generated content. LLMs can produce believable yet incorrect information, risking errors in medical records. Opacity of training data exacerbates this, hindering accuracy assessment. To mitigate, LLMs should train on precise, validated medical data sets. Model bias is another critical concern because LLMs may perpetuate biases from their training, leading to medically inaccurate and discriminatory responses. Sampling, programming, and compliance biases contribute necessitating careful consideration to avoid perpetuating harmful stereotypes. Privacy is paramount in health care, using public LLMs raises risks. Strict data-sharing agreements and Health Insurance Portability and Accountability Act (HIPAA)-compliant training protocols are necessary to protect patient privacy. Although artificial intelligence technologies offer promising opportunities in health care, careful consideration of ethical principles is crucial. Addressing concerns of inaccuracy, bias, and privacy will ensure responsible and patient-centered implementation, benefiting both healthcare professionals and patients.

Purpose: To provide an overview of the injuries suffered by Women’s National Basketball Association (WNBA) athletes and to analyze the demographic data, injury rates, and games missed as a result of individual injuries. Methods: Using publicly available data on WNBA player’s injury history, we generated a database cataloguing the quantity, location, frequency, and longitudinal impact of injuries sustained during the WNBA regular season from 2015 to 2019. We analyzed the data using SPSS‐25 data manipulation software to assess the number of injuries per athletic exposure. Results: Lower‐extremity injuries (n = 143, 73%) were the most common injury by body area and resulted in the greatest number of games missed (n = 1189, 88%). Lateral ankle sprains were the most frequent injury (n = 39, 20%), with a rate of 1.19 injuries per 1000 athletic exposures. Torn anterior cruciate ligaments (n = 18, 9.2%) were the most devastating, resulting in the greatest number of games missed (n=376, 28%). Conclusions: Our findings corroborate previous notions that lower‐extremity injuries are the greatest source of injury in this population. Ankle injuries were the most frequent injury reported by pathology, while knee injuries carried the most long‐term impact on games missed due to injury. Level of Evidence: IV, Epidemiological study