Can ChatGPT outperform a neurosurgical trainee? A prospective comparative study.

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.

Systematic review and meta-analysis of predictive factors for spontaneous regression in lumbar disc herniation.

OBJECTIVE: Relatively little evidence exists on predictive factors for the spontaneous regression of lumbar disc herniation (LDH), although it is a well-documented phenomenon. Therefore, current care is not optimized to identify those who would benefit from early surgery versus those who could avoid surgical risks and pursue nonsurgical therapy. In this study, the authors aimed to analyze and summarize all literature to date on predictive factors for spontaneous LDH regression as well as suggest future research strategies to aid in the decision-making for this cohort. METHODS: A literature search was conducted of the Cochrane, Embase, and MEDLINE databases for articles that described LDH in terms of the North American Spine Society task force definitions: bulging, protruded, extruded, and sequestered disc morphologies. All articles described a nonsurgical primary symptomatic LDH cohort with at least two MR images to assess regression. Those with concomitant spinal disease were excluded. The primary outcome was to assess the probability of disc regression for each disc morphology, with a secondary analysis for any other predictive factors identified. The authors synthesized their results with the only previous review (examining articles published before March 2014) to comprehensively describe the literature. A qualitative analysis of the wider literature was also performed for those studies with differing definitions of LDH but meeting all remaining inclusion criteria. RESULTS: Sixteen articles describing 360 cases of LDH were identified. Participants tended to be younger and male and presented with radiculopathy and L4-5 or L5-S1 LDH. The mean time to follow-up imaging was 11.5 months. The probabilities of spontaneous regression with bulging, protruded, extruded, and sequestered discs were 13.3%, 52.5%, 70.4%, and 93.0%, respectively (χ2 = 126.01, p < 0.001). Extruded and sequestered discs were also significantly more likely to completely regress than smaller morphologies. Other predictors of regression were larger baseline herniation volume (1260.16 vs 1006.71 mm3, p < 0.002), transligamentous herniation (χ2 = 13.321, p < 0.001), and higher Komori types (χ2 = 14.5132, p < 0.001). The authors also found similar trends in qualitative data as well as confirmed that symptom improvement was associated with disc regression. CONCLUSIONS: This study shows further evidence of the influence of disc morphology on predicting LDH regression as well as provides the first meta-analysis of data indicating additional predictive factors. Further investigation of predictive factors for early (< 6 months) LDH regression is suggested to optimize clinical use.

Optimising trajectory planning for stereotactic brain tumour biopsy using artificial intelligence: a systematic review of the literature.

PURPOSE: Despite advances in technology, stereotactic brain tumour biopsy remains challenging due to the risk of injury to critical structures. Indeed, choosing the correct trajectory remains essential to patient safety. Artificial intelligence can be used to perform automated trajectory planning. We present a systematic review of automated trajectory planning algorithms for stereotactic brain tumour biopsies. METHODS: A PRISMA adherent systematic review was conducted. Databases were searched using keyword combinations of 'artificial intelligence', 'trajectory planning' and 'brain tumours'. Studies reporting applications of artificial intelligence (AI) to trajectory planning for brain tumour biopsy were included. RESULTS: All eight studies were in the earliest stage of the IDEAL-D development framework. Trajectory plans were compared through a variety of surrogate markers of safety, of which the minimum distance to blood vessels was the most common. Five studies compared manual to automated planning strategies and favoured automation in all cases. However, this comes with a significant risk of bias. CONCLUSIONS: This systematic review reveals the need for IDEAL-D Stage 1 research into automated trajectory planning for brain tumour biopsy. Future studies should establish the congruence between expected risk of algorithms and the ground truth through comparisons to real world outcomes.

Climate change in healthcare: Exploring the potential role of inhaler prescribing.

Climate change has been described as the biggest global health threat of the 21st century. As a result, governments around the world are committing to legislative change in order to reduce greenhouse gas emissions (GHGEs). The healthcare sector makes a significant contribution to GHGEs and in line with national legislation in the UK, the NHS has recently committed to achieving net zero emissions by 2050. The management of asthma and COPD largely depends on the prescribing of medications that are delivered through inhalers. In the UK, the use of pressurized metered dose inhalers (pMDIs), which rely on hydrofluorocarbon (HFC) propellants accounts for 3.5% of the NHS's total carbon footprint. In contrast, dry powder inhalers (DPIs) have a much lower carbon footprint due to the absence of a HFC propellant. Here we review evidence of the impact of inhaler choices across four domains: environmental impact, clinical effectiveness, cost effectiveness and patient preferences. We find that as well as a lower global-warming potential, DPIs have additional benefits over pMDIs in other domains and should be considered first line where clinically appropriate.