A randomized controlled trial of a WeChat-based artificial intelligence agent for postoperative care in orthopedic patients

Effective postoperative management in orthopedic surgery is often hindered by challenges such as poor patient adherence to rehabilitation protocols, insufficient monitoring of wound healing, inadequate pain control, and limited access to timely psychological and functional support. To address these issues, we conducted a randomized controlled trial (registered in the Chinese Clinical Trial Registry, ChiCTR2500101273, April 23, 2025) that evaluated the use of a GPT-4-powered AI agent delivered via WeChat for postoperative care in 261 patients, with 140 assigned to the AI group and 121 to the doctor-led group. In the intervention arm, patients interacted with a GPT-4-based WeChat agent that delivered real-time, context-aware support, while the control arm received routine physician communication. The AI system responded far more rapidly (0.5 ± 0.6 vs. 358 ± 47.5 min, p < 0.05) and provided feedback of higher perceived quality, though with slightly reduced accuracy (93.9% vs. 98.1%, p < 0.05). At 1 and 3 months, the AI group achieved significantly better outcomes in knee function (IKDC), physical health (PCS), and overall satisfaction (all p < 0.05). By the 6-month follow-up, group differences were no longer significant (p > 0.05), suggesting equivalent long-term outcomes. Overall, GPT-4-enabled WeChat agent may provide short-term benefits in postoperative functional recovery and patient experience, whereas long-term outcomes remain comparable to doctor-led care. These findings support the potential value of LLM-based tools as a supplementary component of postoperative management.