Impact of large language model Dialogue System on Perioperative Anxiety and Depression in Patients Undergoing Total Knee Arthroplasty: A Randomized Controlled Trial (Preprint) DOI
Yixiang Zhang,

Chunlei Wu,

Tao Yang

и другие.

Опубликована: Апрель 6, 2025

BACKGROUND Total knee arthroplasty (TKA) is a widely performed procedure for osteoarthritis, yet patient satisfaction remains suboptimal, with preoperative anxiety and depression contributing to poor postoperative outcomes. Large-scale language models (LLMs), such as ChatGPT, have shown potential in healthcare applications but remain underexplored the context of TKA. This study evaluates impact an AI-driven dialogue system on perioperative TKA patients. OBJECTIVE aimed evaluate effect LLMs improving depression, well overall psychological well-being, patients undergoing The primary objective was assess system’s reducing levels before after surgery. Secondary objectives included evaluating satisfaction, feasibility scalability AI compared traditional methods, its broader clinical application surgical settings. METHODS We expect conduct parallel randomized controlled trial Tianjin Hospital. content needs gather 210 participants between ages 50-80 randomly divide them into two groups, namely, LLM intervention group or usual care group. ChatGPT 4.0 software used personalized education activity about 20-30 minutes every day, routine nursing control group, receiving standard education. test results were evaluated by hospital Depression Scale (HADS) at baseline, 48 hours, 24 hours surgery, 72 surgery determine whether artificial intelligence effective anti improve patients' mood health. RESULTS Statistical analyses showed that reduction significantly greater. found both groups experienced significant With guidance intelligence, these symptoms continued alleviate particularly (P<.001), while conventional slower decline. CONCLUSIONS Experimental data shows intelligent support driven can effectively reduce Compared measures, this method breaks through limitations high labor costs, economy, difficulties implementing plans, achieving efficient innovative breakthroughs. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR2500099927; https://www.chictr.org.cn/bin/project/edit?pid=256631ChatGPT；Total Knee Arthroplasty；Perioperative；Anxiety；Depression.

Язык: Английский

Impact of large language model Dialogue System on Perioperative Anxiety and Depression in Patients Undergoing Total Knee Arthroplasty: A Randomized Controlled Trial (Preprint) DOI
Yixiang Zhang,

Chunlei Wu,

Tao Yang

и другие.

Опубликована: Апрель 6, 2025

BACKGROUND Total knee arthroplasty (TKA) is a widely performed procedure for osteoarthritis, yet patient satisfaction remains suboptimal, with preoperative anxiety and depression contributing to poor postoperative outcomes. Large-scale language models (LLMs), such as ChatGPT, have shown potential in healthcare applications but remain underexplored the context of TKA. This study evaluates impact an AI-driven dialogue system on perioperative TKA patients. OBJECTIVE aimed evaluate effect LLMs improving depression, well overall psychological well-being, patients undergoing The primary objective was assess system’s reducing levels before after surgery. Secondary objectives included evaluating satisfaction, feasibility scalability AI compared traditional methods, its broader clinical application surgical settings. METHODS We expect conduct parallel randomized controlled trial Tianjin Hospital. content needs gather 210 participants between ages 50-80 randomly divide them into two groups, namely, LLM intervention group or usual care group. ChatGPT 4.0 software used personalized education activity about 20-30 minutes every day, routine nursing control group, receiving standard education. test results were evaluated by hospital Depression Scale (HADS) at baseline, 48 hours, 24 hours surgery, 72 surgery determine whether artificial intelligence effective anti improve patients' mood health. RESULTS Statistical analyses showed that reduction significantly greater. found both groups experienced significant With guidance intelligence, these symptoms continued alleviate particularly (P<.001), while conventional slower decline. CONCLUSIONS Experimental data shows intelligent support driven can effectively reduce Compared measures, this method breaks through limitations high labor costs, economy, difficulties implementing plans, achieving efficient innovative breakthroughs. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR2500099927; https://www.chictr.org.cn/bin/project/edit?pid=256631ChatGPT；Total Knee Arthroplasty；Perioperative；Anxiety；Depression.

Язык: Английский

Процитировано

0