Objective To explore the effectiveness of the generative large language model MedGo in nursing decision-making for elderly patients with multimorbidity.
Methods A quasi-randomized controlled trial study was conducted involving 6 junior nurses, 6 senior nurses and the MedGo model from January 1, 2025 to March 31, 2025 at the Emergency Internal Medicine Ward of Shanghai East Hospital Affiliated to Tongji University. Clinical data of 120 elderly patients with multimorbidity were analyzed to compare the performance of the three groups in four tasks (nursing diagnosis assessment, nursing intervention formulation, complication identification, and complication prevention) from three evaluation dimensions: decision-making time consumption, decision accuracy, and decision-making quality.
Results In terms of decision-making time, the senior nurse group completed all four tasks faster than the junior nurse group (P＜0.01), and the MedGo group completed all four tasks faster than the junior nurse group (P＜0.001) and the senior nurse group (P＜0.001). In terms of decision-making accuracy, senior nurse group scored higher than junior nurse group in all four tasks (P＜0.001), while the MedGo group outperformed the senior nurse group only in complication identification (P＜0.001). In terms of decision-making quality, the MedGo group scored higher than junior nurse group (P＜0.001) and senior nurse group (P＜0.001) in all four tasks.
Conclusions The MedGo model demonstrates advantages of high efficiency, accuracy, and quality in nursing decision-making for elderly patients with multimorbidity; senior nurses outperform junior nurses in decision-making, providing diverse references for clinical nursing decision-making.
DownLoad: