A5085639088- Meta-analysis and systematic reviews
- COVID-19 Clinical Research Studies
- Sleep and related disorders
- Clinical practice guidelines implementation
- Artificial Intelligence in Healthcare and Education
- Pelvic and Acetabular Injuries
- Pelvic floor disorders treatments
- Long-Term Effects of COVID-19
- COVID-19 and healthcare impacts
- Respiratory viral infections research
- Pregnancy-related medical research
- SARS-CoV-2 and COVID-19 Research
- Sleep and Wakefulness Research
- Health Systems, Economic Evaluations, Quality of Life
- Obesity, Physical Activity, Diet
- Topic Modeling
- Consumer Attitudes and Food Labeling
- Pharmacological Effects of Natural Compounds
- Diabetes and associated disorders
- Plant-based Medicinal Research
- Infective Endocarditis Diagnosis and Management
- Acupuncture Treatment Research Studies
- Traditional Chinese Medicine Studies
- Andrographolide Research and Applications
- Complementary and Alternative Medicine Studies
Lanzhou University
2020-2025
Guangzhou Eighth People's Hospital
2024
Guangzhou Medical University
2024
Importance Large language models (LLMs) may facilitate the labor-intensive process of systematic reviews. However, exact methods and reliability remain uncertain. Objective To explore feasibility using LLMs to assess risk bias (ROB) in randomized clinical trials (RCTs). Design, Setting, Participants A survey study was conducted between August 10, 2023, October 30, 2023. Thirty RCTs were selected from published Main Outcomes Measures structured prompt developed guide ChatGPT (LLM 1) Claude 2)...
BackgroundThe goal of this systematic review was to examine the efficacy and safety proton-pump inhibitors for stress ulcer prophylaxis in critically ill patients.MethodsWe included randomized trials comparing versus placebo or no adults, performed meta-analyses, assessed certainty evidence using Grading Recommendations, Assessment, Development, Evaluations approach. To explore effect on mortality based disease severity, a subgroup analysis conducted combining within-trial data from two...
Large language models (LLMs) have the potential to enhance evidence synthesis efficiency and accuracy. This study assessed LLM-only LLM-assisted methods in data extraction risk of bias assessment for 107 trials on complementary medicine. Moonshot-v1-128k Claude-3.5-sonnet achieved high accuracy (≥95%), with performing better (≥97%). significantly reduced processing time (14.7 5.9 min vs. 86.9 10.4 conventional methods). These findings highlight LLMs' when integrated human expertise.
The advancement of large language models (LLMs) presents promising opportunities to enhance evidence synthesis efficiency, particularly in data extraction processes, yet existing prompts for remain limited, focusing primarily on commonly used items without accommodating diverse needs. This research letter developed structured LLMs and evaluated their feasibility extracting from randomized controlled trials (RCTs). Using Claude (Claude-2) as the platform, we designed comprehensive comprising...