Antimicrobial prophylaxis in noninstrumented spine surgery: a prospective study to determine efficacy and drawbacks

Performance of a Large Language Model in the Generation of Clinical Guidelines for Antibiotic Prophylaxis in Spine Surgery

OBJECTIVE

Large language models, such as chat generative pre-trained transformer (ChatGPT), have great potential for streamlining medical processes and assisting physicians in clinical decision-making. This study aimed to assess the potential of ChatGPT's 2 models (GPT-3.5 and GPT-4.0) to support clinical decision-making by comparing its responses for antibiotic prophylaxis in spine surgery to accepted clinical guidelines.

METHODS

ChatGPT models were prompted with questions from the North American Spine Society (NASS) Evidence-based Clinical Guidelines for Multidisciplinary Spine Care for Antibiotic Prophylaxis in Spine Surgery (2013). Its responses were then compared and assessed for accuracy.

RESULTS

Of the 16 NASS guideline questions concerning antibiotic prophylaxis, 10 responses (62.5%) were accurate in ChatGPT's GPT-3.5 model and 13 (81%) were accurate in GPT-4.0. Twenty-five percent of GPT-3.5 answers were deemed as overly confident while 62.5% of GPT-4.0 answers directly used the NASS guideline as evidence for its response.

CONCLUSION

ChatGPT demonstrated an impressive ability to accurately answer clinical questions. GPT-3.5 model's performance was limited by its tendency to give overly confident responses and its inability to identify the most significant elements in its responses. GPT-4.0 model's responses had higher accuracy and cited the NASS guideline as direct evidence many times. While GPT-4.0 is still far from perfect, it has shown an exceptional ability to extract the most relevant research available compared to GPT-3.5. Thus, while ChatGPT has shown far-reaching potential, scrutiny should still be exercised regarding its clinical use at this time.

Is the routine use of systemic antibiotics after spine surgery warranted? A systematic review and meta-analysis

PURPOSE

To determine whether the published literature supports the current practice of utilizing antibiotics postoperatively in spine surgery.

METHODS

A systematic review from PubMed and Cochrane Central Register of Controlled trials databases was performed. Search terms used: "Antibiotic Prophylaxis"[Mesh], antibiotic*, antibacterial*, "Spine"[Mesh], "Surgical Procedures, Operative"[Mesh]. Only comparative, clinical studies were included. Those studies with surgical site infection (SSI) criteria that were not similar to the CDC definition were excluded. A meta-analysis for overall SSI was performed. A subgroup analysis was also performed to analyze the outcomes specifically on instrumented groups of patients. A random-effects model was used to calculate risk ratios (RR). Forest plots were used to display RR and 95% confidence intervals (CI).

RESULTS

Thirteen studies were included (four Randomized-Controlled Trials, three prospective cohorts, and six retrospective). Three different perioperative strategies were used in the selected studies: Group 1: preoperative antibiotic administration (PreopAbx) versus PreopAbx and any type of postoperative antibiotic administration (Pre + postopAbx) (n = 6 studies; 7849 patients); Group 2: Pre + postopAbx ≤ 24 h versus Pre + postopAbx > 24 h (n = 6; 1982); and Group 3: Pre + postopAbx ≤ 48 h versus. Pre + postopAbx ≤ 72 h (n = 1; 502). The meta-analysis performed on Groups 1 and 2 did not show significant effects (RR = 1.27, 95% CI = 0.77, 2.09, and RR = 0.97, 95% CI = 0.64, 1.46, respectively).

CONCLUSION

A meta-analysis and comprehensive review of the literature show that the routine use of postoperative antibiotics in spine surgery may not be effective in preventing surgical site infections.