Clinical Research Directory

Expert-Validated ChatGPT Support for Arterial Blood Gas Interpretation

This randomized controlled study evaluated whether expert-validated ChatGPT support improved arterial blood gas (ABG) interpretation performance among early-career non-specialist physicians. Participants completed a baseline assessment consisting of 11 standardized clinical scenarios covering five domains of ABG interpretation. Eligible participants who entered the reassessment phase were randomly assigned to either an AI-supported group or a control group. One week after baseline assessment, participants completed a posttest using the same clinical scenarios. The AI-supported group received expert-validated ChatGPT responses before answering each case, whereas the control group completed the assessment without AI support. The primary outcome was posttest total ABG interpretation accuracy across 55 scored items, compared between groups after adjustment for baseline accuracy. Secondary outcomes included changes in total accuracy, domain-specific accuracy, case-level performance, and item-level accuracy.

Static Ultrasound Guidance for Radial Arterial Puncture

Radial arterial puncture is a commonly performed procedure in emergency departments for arterial blood gas analysis and invasive hemodynamic monitoring. The conventional palpation technique may be associated with prolonged procedure duration and multiple puncture attempts, particularly in patients with weak arterial pulsation or difficult vascular anatomy. Ultrasound guidance has been proposed as a method to improve procedural success. This randomized controlled trial aimed to compare the static ultrasound-guided technique with the conventional palpation technique for radial arterial puncture in adult emergency department patients. The primary outcome was puncture duration. Secondary outcomes included first-attempt success rate, total number of attempts, procedure-related complications, and patient pain scores.