Article Notes
Why care about LLM's?
Large language models (LLMs) have revolutionised natural language processing, and so inevitably have found their way into healthcare. Their use in decision support and diagnosis has however shown mixed results, even as models and integrations quickly improve.
Despite short-comings, LLMs cannot be ignored by doctors – growing health cost-demand-challenges will continue to push LLM-based tools into clinical practice, even before robust clinical validation. We also know that diagnostic errors are common and costly, both in economic and patient safety terms, increasing the allure of medical LLMs.
What did this study do?
This single-blinded randomised controlled trial included 50 physicians (26 attendings, 24 residents) from family medicine, internal medicine, and emergency medicine. Participants were randomised to either use ChatGPT-4 plus conventional resources or conventional resources only, to complete up to six clinical diagnostic cases within 60 minutes.
Diagnostic performance was measured using validated standardised scoring of three elements: accuracy of generated differential diagnoses, ability to identify supporting and contradicting clinical findings, and the appropriateness of proposed next diagnostic steps.
(Interesting aside: the six selected vignettes were from a 1994 pool of 105 never-published real patient cases originally used in a landmark study on diagnostic systems, guaranteed to be outside the LLM's training data, as these cases have been kept private to preserve their future testing validity.)
And they found?
The LLM alone performed significantly better than either physician group, scoring 16 percentage points higher than the control group (95% CI, 2-30 %-points). Yet physicians with access to the LLM effectively showed no improvement compared to the conventional-resources-alone group (76% vs 74% median diagnostic score, p=.60). Time spent per case was no different between groups.
"Access alone to LLMs will not improve overall physician diagnostic reasoning in practice. These findings are particularly relevant now that many health systems offer [HIPAA]–compliant chatbots ... often with no to minimal training..."
Bottom-line
This study highlights the "implementation gap" between AI capability and clinical utility: even if reliably and consistently accurate (a big 'if'), the mere availability of AI tools will not automatically translate into improved clinical reasoning. Successful integration will require deliberate consideration of how to optimise human-AI collaboration in medical practice.
Daniel Jolley
This study from Liu et al. investigated whether using laryngeal mask airways (LMAs) might reduce atelectasis formation compared to endotracheal tubes (ETTs) during general anaesthesia (sufentanil/propofol/rocuronium → propofol/remifentanil TIVA; VCV: TV 6-8 mL/kg, PEEP 5 cmH2O, I:E 1:1.5, RR 12-20 & FiO2 40%.).
In their single-centre, double-blind randomised controlled trial of 180 patients undergoing non-laparoscopic surgery, they used lung ultrasound scoring to assess atelectasis at various timepoints.
The results were interesting: the LMA group showed significantly lower lung ultrasound scores at all timepoints, better oxygenation, and fewer postoperative pulmonary complications. The authors attribute this to several factors, including faster airway insertion (41 vs 95 seconds of apnoea), reduced airway irritation, and lower requirements for anaesthetic depth and muscle relaxation.
While these findings are limited to relatively healthy patients having shorter procedures, they suggest that when appropriate, using an LMA rather than ETT may help reduce atelectasis formation. However, as the authors acknowledge, these results may not apply to longer procedures, laparoscopic surgery, or higher-risk patients, and the risk-benefit balance of an unprotected airway versus an ETT must always be considered.
Daniel Jolley
This narrative review by Ford et al. examines how anaesthetic technique impacts the success of catheter ablation for atrial fibrillation (AF). With AF being the most common cardiac arrhythmia and ablation procedures increasingly common, understanding optimal anaesthetic approaches is crucial for improving patient outcomes.
The authors compare three key approaches: general anaesthesia (GA) versus conscious sedation, high-frequency jet ventilation (HFJV), and high-frequency low tidal volume ventilation (HFLTV).
The evidence strongly favours GA over conscious sedation, with one study showing significantly better arrhythmia-free rates at 17 months (88% vs 69%). Both HFJV and HFLTV show promise in improving catheter stability and procedural outcomes through reduced respiratory variability, though HFJV faces practical challenges including cost and training requirements.
While the review acknowledges the need for randomised controlled trials comparing different ventilation strategies, it makes a compelling argument for anaesthetic techniques that minimise ventilation variability. HFLTV might offer a practical middle ground, potentially providing similar benefits to HFJV without the associated costs and training demands.
Daniel Jolley
A comprehensive meta-analysis from Da Silveira examines whether minimally invasive abdominal surgery can be effectively managed without intraoperative opioids. Da Silveira and colleagues analysed 26 randomised controlled trials involving 2,025 patients, comparing traditional opioid-based anaesthesia with opioid-free techniques using alternatives like dexmedetomidine, ketamine, and lidocaine.
The results are compelling: opioid-free anaesthesia reduced postoperative nausea and vomiting by 45% (from 24% to 13%) without compromising pain control or increasing recovery time.
Notably, concerns about bradycardia with dexmedetomidine proved unfounded, with no significant difference in rates between the groups. The study also found slightly lower immediate postoperative pain scores and reduced opioid requirements in the first two hours after surgery.
While these findings strongly support opioid-free techniques for laparoscopic surgery, the authors note important caveats. The included trials used varying combinations of agents, making it difficult to recommend a standardised approach. Successfully implementing opioid-free anaesthesia requires expertise with multiple alternative agents and techniques - but the benefits, particularly in reducing post-operative nausea and vomiting, may be worth the learning curve.
Daniel Jolley