ABSTRACT
PURPOSE: This study aimed to compare the performance of ChatGPT, a large language model (LLM), with human neurosurgical applicants in a neurosurgical national selection interview, to assess the potential of artificial intelligence (AI) and LLMs in healthcare and provide insights into their integration into the field. METHODS: In a prospective comparative study, a set of neurosurgical national selection-style interview questions were asked to eight human participants and ChatGPT in an online interview. All participants were doctors currently practicing in the UK who had applied for a neurosurgical National Training Number. Interviews were recorded, anonymised, and scored by three neurosurgical consultants with experience as interviewers for national selection. Answers provided by ChatGPT were used as a template for a virtual interview. Interview transcripts were subsequently scored by neurosurgical consultants using criteria utilised in real national selection interviews. Overall interview score and subdomain scores were compared between human participants and ChatGPT. RESULTS: For overall score, ChatGPT fell behind six human competitors and did not achieve a mean score higher than any individuals who achieved training positions. Several factors, including factual inaccuracies and deviations from expected structure and style may have contributed to ChatGPT's underperformance. CONCLUSIONS: LLMs such as ChatGPT have huge potential for integration in healthcare. However, this study emphasises the need for further development to address limitations and challenges. While LLMs have not surpassed human performance yet, collaboration between humans and AI systems holds promise for the future of healthcare.
ABSTRACT
Background: Persistent or worsening syringomyelia after foramen magnum decompression (FMD) for Chiari I malformation (CIM) can be challenging to manage. We present a previously unpublished surgical technique of FMD with concomitant cervical syringotomy in selected patients. Methods: A retrospective analysis of prospectively collected data was carried out. Patients who underwent FMD and expansion duraplasty (FMDD) with concomitant syringotomy were collected. Results: Three patients with CIM with high cervical syringomyelia who underwent FMDD with concurrent syringotomy were identified. All cases had an idiopathic CIM. Improvement in clinical symptoms was noticed in all patients. Early postoperative imaging (within 6 weeks-4 months) showed syrinx transverse diameter reduction in the range of 85-100%. There were no postoperative complications. Conclusion: FMDD with concurrent high cervical syringotomy through a standard approach in selected cases of CIM with high cervical syringes achieves clinical improvement without additional complications.
Subject(s)
Cardiopulmonary Resuscitation , Heart Arrest , Humans , Animals , Oxygen , Brain , Disease Models, AnimalABSTRACT
OBJECTIVE: Endoscopic strip craniectomy with postoperative molding helmet therapy (ESC-H) and spring-assisted cranioplasty (SAC) are commonly used minimally invasive techniques for correction of nonsyndromic sagittal craniosynostosis, but it is unclear which, if either, is superior. Therefore, the authors undertook a systematic review to compare ESC-H with SAC for the surgical management of nonsyndromic single-suture sagittal craniosynostosis. METHODS: Studies were identified through a systematic and comprehensive search of four databases (Embase, MEDLINE, and two databases in the Cochrane Library). Databases were searched from inception until February 19, 2021. Pediatric patients undergoing either ESC-H or SAC for the management of nonsyndromic single-suture sagittal craniosynostosis were included. Systematic reviews and meta-analyses, single-patient case reports, mixed cohorts of nonsyndromic and syndromic patients, mixed cohorts of different craniosynostosis types, and studies in which no outcomes of interest were reported were excluded. Outcomes of interest included reoperations, blood transfusion, complications, postoperative intensive care unit (ICU) admission, operative time, estimated blood loss, length of hospital stay, and cephalic index. Pooled summary cohort characteristics were calculated for each outcome of interest. Methodological quality was assessed using the Newcastle-Ottawa Scale. The study was reported in accordance with the 2020 PRISMA statement. RESULTS: Twenty-two studies were eligible for inclusion in the review, including 1094 patients, of whom 605 (55.3%) underwent ESC-H and 489 (44.7%) underwent SAC for nonsyndromic sagittal craniosynostosis. There was no difference between the pooled estimates of the ESC-H and SAC groups for operative time, length of stay, estimated blood loss, and cephalic index. There was no difference between the groups for reoperation rate and complication rate. However, ESC-H was associated with a higher blood transfusion rate and higher postoperative ICU admission. CONCLUSIONS: The available literature does not demonstrate superiority of either ESC-H or SAC, and outcomes are broadly similar for the treatment of nonsyndromic sagittal craniosynostosis. However, the evidence is limited by single-center retrospective studies with low methodological quality. There is a need for international multicenter randomized controlled trials comparing both techniques to gain definitive and generalizable data.
