Artificial intelligence (AI) based large language models (LLM) contain enormous potential in education and training. Recent publications demonstrated that they are able to outperform participants in written medical exams. We aimed to explore the accuracy of AI in the written part of the EANS board exam. Eighty-six representative single best answer (SBA) questions, included at least ten times in prior EANS board exams, were selected by the current EANS board exam committee. The questions’ content was classified as 75 text-based (TB) and 11 image-based (IB) and their structure as 50 interpretation-weighted, 30 theory-based and 6 true-or-false. Questions were tested with Chat GPT 3.5, Bing and Bard. The AI and participant results were statistically analyzed through ANOVA tests with Stata SE 15 (StataCorp, College Station, TX). P-values of <0.05 were considered as statistically significant. The Bard LLM achieved the highest accuracy with 62% correct questions overall and 69% excluding IB, outperforming human exam participants 59% (p = 0.67) and 59% (p = 0.42), respectively. All LLMs scored highest in theory-based questions, excluding IB questions (Chat-GPT: 79%; Bing: 83%; Bard: 86%) and significantly better than the human exam participants (60%; p = 0.03). AI could not answer any IB question correctly. AI passed the written EANS board exam based on representative SBA questions and achieved results close to or even better than the human exam participants. Our results raise several ethical and practical implications, which may impact the current concept for the written EANS board exam.

The use of robotics in spine surgery has gained popularity. This study aims to assess the current state of robotics and raise awareness of its educational implications. What are the current adoption trends and barriers to the implementation of robotic assistance in spine surgery? An online questionnaire comprising 27 questions was distributed to AO spine members between October 25th and November 13th, 2023, using the SurveyMonkey platform (https://www.surveymonkey.com; SurveyMonkey Inc., San Mateo, CA, USA). Statistical analyses (descriptive statistics, Pearson Chi-Square tests) and generation of all graphs were performed using SPSS Version 29.0.1.0 (IBM SPSS Statistic). We received 424 responses from AO Spine members (response rate = 9.9 %). The participants were mostly board-certified orthopedic surgeons (46 %, n = 195) and neurosurgeons (32%, n = 136). While 49% (n = 208) of the participants reported occasional or frequent use of navigation assistance, only 18 % (n = 70) indicated the use of robotic assistance for spinal instrumentation. A significant difference based on the country's median income status (p < 0.001) and the respondent's number of annual instrumentation procedures (p < 0.001) has been observed. While 11 % (n = 47) of all surgeons use a spinal robot frequently, 36 % (n = 153) of the participants stated they don't need a robot from a current perspective. Most participants (77%, n = 301) concluded that high acquisition costs are the primary barrier for the implementation of robotics. Although the hype for robotics in spine surgery increased recently, robotic systems remain non-standard equipment due to cost constraints and limited usability.

Three-dimensional exoscopes have been designed to overcome certain insufficiencies of operative microscopes. We aimed to explore the clinical use in various spinal surgeries. We performed surgery on patients with different spine entities in a neurosurgical department according to the current standard operating procedures over a 4-week period of time. The microsurgical part has been performed with Aesculap AEOS 3D microscope. Three neurosurgeons with different degree of surgical expertise completed a questionnaire with 43 items based on intraoperative handling and feasibility after the procedures. We collected and analyzed data from seventeen patients (35% male/65% female) with a median age of 70 years [CI 47–86] and median BMI of 25.8 kg/m² [range 21–33]. We included a variety of spinal pathologies (10 degenerative, 4 tumor and 3 infectious cases) with different level of complexity. Regarding setup conflicts we observed issues with adjustment of the monitor position or while using additional equipment (e.g. fluoroscopy in fusion surgery) (p = 0.007/p = 0.001). However image resolution and sharpness as well as 3D-depth perception were completely satisfactory for all surgeons in all procedures. The utilization of the exoscopic arm was easy for 76.5% of the surgeons, and all of them declared a significant improvement of the surgical corridor. The 3D-exoscope implementation appears to achieve very satisfactory results in spinal procedures especially with minimally invasive approaches.

Treatment of patients with failed back surgery syndrome (FBSS) with predominant low back pain (LBP) remains challenging. High-frequency spinal cord stimulation (HF10 SCS) is believed to achieve significant pain reduction. We aimed to evaluate the real-life efficacy of HF-10 SCS in a tertiary spine center. A prospective observational study of all patients with FBSS and predominant LBP who underwent HF-10 SCS surgery was performed between 2016 and 2018. Patients > 18 years with Visual Analogue Scale (VAS) scores of ≥ 5 for LBP and pain duration > 6 months under stable medication were implanted percutaneous under general anesthesia and a trial phase of 7–14 days was accomplished. Primary end point was a successful trial defined as ≥ 50% VAS score reduction for LBP. Thirty-four of 39 (85%) subjects had a successful trial. Fifty-three percent were female and the mean age was 69 years. Median follow-up lasted for 10 months. Devices were removed after a median of 10 months in 5 cases. Remaining 29 patients stated significant VAS score reduction for LBP from 8.1 to 2.9 and VAS for leg pain from 4.9 to 2.2. Twenty-four percent of all patients were able to discontinue their opioids. Eight of 9 patients (89%) with signs of adjacent disc disease and 7 of 10 (70%) patients with hardware failure were successfully implanted with significant VAS reduction for LBP. HF-10 SCS achieves significant pain reduction in most patients with FBSS and predominant LBP. It might be an efficient alternative to revision surgery.

Background: The integration of artificial intelligence (AI), particularly large language models (LLMs) like ChatGPT-4, is transforming healthcare. ChatGPT’s potential to assist in decision-making for complex cases, such as spinal metastasis treatment, is promising but widely untested. Especially in cancer patients who develop spinal metastases, precise and personalized treatment is essential. This study examines ChatGPT-4’s performance in treatment planning for spinal metastasis cases compared to experienced spine surgeons. Materials and Methods: Five spine metastasis cases were randomly selected from recent literature. Consequently, five spine surgeons and ChatGPT-4 were tasked with providing treatment recommendations for each case in a standardized manner. Responses were analyzed for frequency distribution, agreement, and subjective rater opinions. Results: ChatGPT’s treatment recommendations aligned with the majority of human raters in 73% of treatment choices, with moderate to substantial agreement on systemic therapy, pain management, and supportive care. However, ChatGPT’s recommendations tended towards generalized statements, with raters noting its generalized answers. Agreement among raters improved in sensitivity analyses excluding ChatGPT, particularly for controversial areas like surgical intervention and palliative care. Conclusions: ChatGPT shows potential in aligning with experienced surgeons on certain treatment aspects of spinal metastasis. However, its generalized approach highlights limitations, suggesting that training with specific clinical guidelines could potentially enhance its utility in complex case management. Further studies are necessary to refine AI applications in personalized healthcare decision-making.

Introduction Unilateral biportal endoscopy (UBE) is a minimally invasive surgical (MIS) technique utilized for lumbar decompression, which has recently gained popularity in Europe. We aimed to explore the value of sequential adaptive e-learning, followed by simulator-based hands-on training modules for UBE at the occasion of the 2024 EANS Young Neurosurgeons meeting. Materials and methods An adaptive e-learning was designed by learning engineers (Area 9 Lyceum), based on theoretical content provided by two endoscopic spine surgeons. A two-module simulator training, consisting of an insight-the-box model (basic tasks for eye-hand coordination), followed by a realistic lumbar spine model (execution of an endoscopic decompression) was developed. Course participants completed the e-learning before the hands-on training course. Course experience was evaluated through a standardized self-assessment questionnaire containing a 5-point Likert scale and a 10-point numeric rating scale. Results Eleven of eighteen (61%) participants with different levels of professional education (62.5% residents in 1^st -6^th year of training, 37.5% board-certified) completed both trainings. Thirteen participants (72%) had no prior experience with UBE. The perception of knowledge after the e-learning module increased from 2.5 (SD 2) to 6.5 (SD 1.8; p = 0.039). The usefulness, enjoyment, and efficiency of the courses averaged a score of 8.0 (SD 1.8). Regarding the hands-on training, participants estimated an average increase in their skills from 2.9 (SD 1.8) to 6.8 (SD 2, p = 0.028). The overall rating of the two-module course was 7.9 (SD 2.2). Discussion and conclusion Sequential e-learning and simulator training appear to be an effective educational adjunct to establish novel, MIS-techniques such as UBE.