Leveraging Large Language Models (LLM) for the Plastic Surgery Resident Training: Do They Have a Role?

Introduction Large language models (LLMs) are designed for recognizing, summarizing, translating, predicting, and generating text-based content from knowledge gained from extensive data sets. ChatGPT4 (Generative Pre-trained Transformer 4) (OpenAI, San Francisco, California, United States) is a transformer-based LLM model pretrained on public data as well as data obtained from third-party sources using deep learning techniques of fine tuning and reinforcement learning from human feedback to predict the next text. We wanted to explore the role of LLM as a teaching assistant (TA) in plastic surgery. Material and Methods TA roles were first identified in available literature, and based on the roles, a list of suitable tasks was created where LLM could be used to perform the task. Prompts designed to be fed in to the LLM (specifically ChatGPT) to generate appropriate output, were then created and fed to the ChatGPT model. The outputs generated were scored by evaluators and compared for interobserver agreement. Results A final set of eight TA roles were identified where a LLM could be utilized to generate content. These contents were scored for usefulness and accuracy. These were scored independently by the eight study authors in a scoring sheet created for the study. Interobserver agreements for content accuracy, usefulness, and clarity were 100% for content generated for the following: interactive case studies (generation), simulation of preoperative consultations, and generation of ethical considerations. Discussion LLMs in general and ChatGPT (on which this study is based) in specific, can generate answers to questions and prompts based on huge amount of text fed into the model for training the underlying language model. The answers generated have been found to be accurate, readable, and even indistinguishable from human-generated text. This capability of automated content synthesis can be exploited to generate summaries to text, answer short and long answers, and generate case scenarios. We could identify a few such scenarios where the LLM could in general be utilized to play the role of a TA and aid plastic surgery residents in particular. In addition, these models could also be used by students to obtain feedback and gain reflection which itself stimulates critical thinking. Conclusion Incorporating LLMs into the educational arsenal of plastic surgery residency programs can provide a dynamic, interactive, and individualized learning experience for residents and prove to be worthy TAs of future.

Facilitating Safe Discharge Through Predicting Disease Progression in Moderate Coronavirus Disease 2019 (COVID-19): A Prospective Cohort Study to Develop and Validate a Clinical Prediction Model in Resource-Limited Settings.

BACKGROUND: In locations where few people have received coronavirus disease 2019 (COVID-19) vaccines, health systems remain vulnerable to surges in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections. Tools to identify patients suitable for community-based management are urgently needed. METHODS: We prospectively recruited adults presenting to 2 hospitals in India with moderate symptoms of laboratory-confirmed COVID-19 to develop and validate a clinical prediction model to rule out progression to supplemental oxygen requirement. The primary outcome was defined as any of the following: SpO2 < 94%; respiratory rate > 30 BPM; SpO2/FiO2 < 400; or death. We specified a priori that each model would contain three clinical parameters (age, sex, and SpO2) and 1 of 7 shortlisted biochemical biomarkers measurable using commercially available rapid tests (C-reactive protein [CRP], D-dimer, interleukin 6 [IL-6], neutrophil-to-lymphocyte ratio [NLR], procalcitonin [PCT], soluble triggering receptor expressed on myeloid cell-1 [sTREM-1], or soluble urokinase plasminogen activator receptor [suPAR]), to ensure the models would be suitable for resource-limited settings. We evaluated discrimination, calibration, and clinical utility of the models in a held-out temporal external validation cohort. RESULTS: In total, 426 participants were recruited, of whom 89 (21.0%) met the primary outcome; 257 participants comprised the development cohort, and 166 comprised the validation cohort. The 3 models containing NLR, suPAR, or IL-6 demonstrated promising discrimination (c-statistics: 0.72-0.74) and calibration (calibration slopes: 1.01-1.05) in the validation cohort and provided greater utility than a model containing the clinical parameters alone. CONCLUSIONS: We present 3 clinical prediction models that could help clinicians identify patients with moderate COVID-19 suitable for community-based management. The models are readily implementable and of particular relevance for locations with limited resources.

Faculty Perception of Scenario-Based MCQs, SAQs, and MEQs in Medical Education at an Apex Institute.

Purpose: This study explores the current knowledge and overall awareness of the faculty at an Apex institute about the use and difficulties of scenario-based multiple-choice questions (SB-MCQs), short-answer questions (SB-SAQs), and modified essay questions (SB-MEQs) in the assessment of the undergraduate and postgraduate students. Objectives: To assess faculty perception of awareness and use of SB-MCQs, SB-SAQs, and SB-MEQs and to understand the challenges encountered while designing scenario-based questions (SBQs) and the ways to overcome them. Study Procedure: The tool used for data collection was a Google form questionnaire designed with a total of 16 questions-12 Likert-scale format items and four open-ended questions. The quantitative data collected as a response to close-ended questions was analyzed by descriptive statistics and percentage values. For qualitative data, thematic analysis was done for open-ended questions. Conclusion: The study showed that the faculty has the motivation and agreeability to switch over from traditional questions to scenario-based questions but constant training in the form of regular faculty development programs and workshops is required for its effective implementation. On the administrative level, challenges like lack of sufficient faculty and proper inter-departmental integration for designing scenarios must be addressed. Supplementary Information: The online version contains supplementary material available at 10.1007/s40670-024-02052-6.

Early Reconstruction with Locoregional-Free Flaps in Post-COVID-19 Rhino-orbital-cerebral Mucormycosis Craniofacial Deformities: A Single-Center Clinical Experience from India.

Aim of the Study Mucormycosis is a rare invasive and fatal fungal infection and its resurgence in coronavirus disease 2019 (COVID-19) patients has been a matter of grave concern. It is essentially a medical disease, but surgical debridement of necrotic tissues is of paramount importance leading to severe craniofacial deformities. In this case series, we present our experience with the feasibility of early reconstruction after surgical debridement. Case Series As a Dedicated COVID Center (DCH), the institute received the largest population of COVID-19 mucormycosis patients from the entire eastern region of the country between May 2021 and August 2021. More than 5,000 COVID-19 were admitted out of which 218 patients were diagnosed with mucormycosis. Nine patients, seven males and two females, with a mean age of 39 years with craniofacial mucormycosis underwent debridement and early reconstructions (2-4 weeks from first debridement and start of antifungal therapy) with free and pedicled flaps. All flaps survived and showed no evidence of recurrence. The average time of the early reconstruction after surgical debridement was 1.7 weeks once the course of systemic amphotericin B was received. Conclusion After aggressive surgical resection and a short course of antifungal therapy, early reconstruction can be done safely based on clinical criteria, as long as there is no evidence of hyphae invasion on wound edges in the intraoperative pathology examination.

Post-Traumatic Radial Artery Pseudoaneurysm at the Wrist Level: A Case Report.

A pseudoaneurysm is a collection of blood outside the arterial lumen but remains in continuity with the lumen and lined by fibrous tissue. Radial artery pseudoaneurysm is a rare entity mostly occurring due to iatrogenic reasons. Traumatic causes are rare. In this case report, we report a post-traumatic left radial artery pseudoaneurysm at the wrist level in a 20-year-old male patient. The patient was treated with end-to-end repair of excised pseudoaneurysm with a vein graft taken from the radial artery vena comitantes through the same incision.

Approach to management of nerve gaps in peripheral nerve injuries.

Peripheral nerve injuries (PNI) are a major clinical problem. In general, PNI results from motor vehicle accidents, lacerations with sharp objects, penetrating trauma (gunshot wounds) and stretching or crushing trauma and fractures. They can result in significant morbidity, including motor and/or sensory loss, which can affect significantly the life of the patient. Currently, the standard surgical technique for complete nerve transection is end-to-end neurorrhaphy. Unfortunately, there is segmental loss of the nerve trunk in some cases where nerve mobilization may permit end-to-end neurorrhaphy if the gap is less than 1 cm. When the nerve gap exceeds 1 cm, autologous nerve grafting is the gold standard of treatment. But in light of limited availability and concerned donor site morbidity, other techniques have been used: vascularized nerve grafts, cellular and acellular allografts, nerve conduits, nerve transfers and end-to-side neurorrhaphy. This review intends to present an overview of the literature on the applications of these techniques in repair of peripheral nerve injuries. This article also focuses on preoperative assessment, surgical timing, available options and future perspectives.