RESUMEN
BACKGROUND: The advent of Large Language Models (LLMs) like ChatGPT has introduced significant advancements in various surgical disciplines. These developments have led to an increased interest in the utilization of LLMs for Current Procedural Terminology (CPT) coding in surgery. With CPT coding being a complex and time-consuming process, often exacerbated by the scarcity of professional coders, there is a pressing need for innovative solutions to enhance coding efficiency and accuracy. METHODS: This observational study evaluated the effectiveness of 5 publicly available large language models-Perplexity.AI, Bard, BingAI, ChatGPT 3.5, and ChatGPT 4.0-in accurately identifying CPT codes for craniofacial procedures. A consistent query format was employed to test each model, ensuring the inclusion of detailed procedure components where necessary. The responses were classified as correct, partially correct, or incorrect based on their alignment with established CPT coding for the specified procedures. RESULTS: The results indicate that while there is no overall significant association between the type of AI model and the correctness of CPT code identification, there are notable differences in performance for simple and complex CPT codes among the models. Specifically, ChatGPT 4.0 showed higher accuracy for complex codes, whereas Perplexity.AI and Bard were more consistent with simple codes. DISCUSSION: The use of AI chatbots for CPT coding in craniofacial surgery presents a promising avenue for reducing the administrative burden and associated costs of manual coding. Despite the lower accuracy rates compared with specialized, trained algorithms, the accessibility and minimal training requirements of the AI chatbots make them attractive alternatives. The study also suggests that priming AI models with operative notes may enhance their accuracy, offering a resource-efficient strategy for improving CPT coding in clinical practice. CONCLUSIONS: This study highlights the feasibility and potential benefits of integrating LLMs into the CPT coding process for craniofacial surgery. The findings advocate for further refinement and training of AI models to improve their accuracy and practicality, suggesting a future where AI-assisted coding could become a standard component of surgical workflows, aligning with the ongoing digital transformation in health care.
RESUMEN
BACKGROUND: Melanotic neuroectodermal tumors of infancy are rare, benign neoplasms predominantly affecting the craniofacial region, and they are typically managed through resection with minimal need for reconstruction. However, in exceptional cases, larger or more complex tumors may necessitate open craniofacial approaches, with limited literature detailing the surgical strategies for these scenarios. The authors report a distinctive case of an aggressively expanding melanotic neuroectodermal tumor of infancy in a pediatric patient, describing their approach for the tumor's resection. METHODS: A 10-week-old male presented to the hospital with a reported 2 weeks of swelling of the left upper gum line noted by his mother and pediatrician. Preoperative biopsy revealed a soft, fluid-filled lesion, prompting surgical planning for complete excision. Intraoperative assessment with a nasal speculum by ENT, and utilization of a piezoelectric saw by plastic surgery facilitated precise tumor resection. The surgical technique required meticulous dissection, ensuring clear margins while preserving surrounding structures. RESULTS: The tumor, encompassing the alveolus and anterior maxilla, was completely excised with negative margins. Utilization of the piezoelectric saw facilitated safe bone cutting, preserving vital structures while ensuring comprehensive tumor removal. The patient tolerated the procedure well, with no immediate postoperative complications. CONCLUSIONS: Complete resection is essential in minimizing the risk of recurrence in MNTI. The utilization of piezoelectric surgery enhances precision and safety in tumor resection, preserving anatomic integrity and optimizing patient outcomes. This case underscores the importance of meticulous surgical techniques in managing craniofacial tumors, advocating for the adoption of advanced surgical tools to improve clinical outcomes.
RESUMEN
Dysphagia lusoria occurs due to compression of the esophagus as an aberrant right subclavian artery (ARSA) crosses the mediastinum. Surgical management includes open, hybrid, and endovascular techniques, with no consensus gold standard. There are few reports of robotic-assisted ARSA resection. We describe the innovative technique and outcomes for two patients who successfully underwent robotic-assisted transthoracic resection of an ARSA after right carotid-subclavian bypass for dysphagia lusoria. Both patients experienced improvement or resolution of their dysphagia and no major complications. In select patients with a noncalcified origin of the ARSA without aneurysmal degeneration, the robotic-assisted approach represents a viable option.
RESUMEN
This study introduces a novel application of the Osteochondral Autograft Transfer System (OATS) for autologous bone grafting during alveolar cleft repair. Approximately 75% of patients with cleft lip and palate have an alveolar cleft, which often necessitates secondary bone grafting from common donor sites such as the iliac crest. Traditional harvesting techniques, although effective, can be labor-intensive and increase the risk of donor site injury. Here the authors describe the use of OATS, which has primarily been used in orthopedic procedures like anterior cruciate ligament reconstruction, for the first time in alveolar cleft repair. It involves a minimally invasive, single-use transfer system for harvesting osteochondral autografts from the anterior iliac crest, and thereby reduces harvest time compared with traditional open approaches. The procedure is detailed from pre-operative evaluation through long-term follow-up and highlights the technique's benefits related to surgical time, ease of use, and maintenance of sizable autograft volumes. Similarly, the authors discuss other advantages of OATS, including its single-use and cordless nature, which is believed to contribute to a lower contamination risk and better intraoperative ergonomics.
RESUMEN
Background: Primary pancreatic signet ring cell carcinoma (PPSRCC) is a rare (<1%) poorly reported histopathological variant of pancreatic cancer with ill-defined treatment guidelines. Herein, we describe a case of nonmetastatic PPSRCC in a 45-year-old female. Presentation: A 45-year-old female presented with 3 weeks of abdominal pain radiating to her back. Other pertinent positives included a 20-pound (9.1-kilogram) weight loss and jaundice, with a known 30-pack-year smoking history. CT scan revealed a 4.6 × 3.6 cm hypoattenuating mass in the head of the pancreas (HOP) with dilatation of the common bile duct. Total bilirubin at presentation was elevated, and a biliary stent was placed endoscopically. Subsequent endoscopic ultrasonography revealed a periampullary ulcerated mass involving the HOP and second portion of the duodenum, with pathology revealing poorly differentiated adenocarcinoma with mucinous background and focal signet ring cells. A classic pancreatoduodenectomy (Whipple procedure) was performed. Final pathology revealed a poorly differentiated (G3) pT3/pN2/pM0 PPSRCC with 11 of 16 positive specimen lymph nodes. The tumor had evidence of both KRAS and TP53 mutations and expressed an MUC1+/MUC2-/MUC5AC+ immunophenotype. Medical oncology recommended a 6-month course of adjuvant modified-dose FOLFIRINOX therapy. Conclusion: This report highlights the need for further research into the pathogenesis of gastrointestinal signet ring cell carcinoma to identify and study therapeutic targets that can eventually be translated to PPSRCC treatment. Given the paucity of PPSRCC, adjuvant therapy candidates follow the current literature on more common pancreatic cancer subtypes to guide treatment.