Background: Inadequately controlled postoperative pain continues to pose a significant clinical challenge in pediatric patients undergoing thoracic surgery. Objective: This randomized controlled study aimed to investigate the effectiveness of SMS-based educational support for postoperative pain management on patients’ pain experience. Methods: A total of 100 pediatric patients undergoing thoracic surgery were enrolled between December 2, 2023, and January 28, 2025. Patients in the intervention group (group 1) received structured postoperative pain management education via SMS text messages, whereas those in the control group (group 2) received standard oral education. Pain intensity and pain-related interference were assessed using the Brief Pain Inventory, and self-efficacy was measured using the Pain Self-Efficacy Scale. Results: The number of patients with moderate-to-severe average pain was significantly lower in group 1 than in group 2 (n=19, 18% vs n=19, 38%; =.04), and group 1 had significantly higher patient self-efficacy scores (mean 29.3, SD 7.5 vs mean 25.2, SD 8.7=.01). Least pain scores were lower in group 1 compared with group 2 across all 3 consecutive postoperative days (PODs): POD1 (mean 2.8, SD 0.8 vs mean 3.3, SD 0.7; <.001), POD2 (mean 2.2, SD 0.8 vs mean 2.7, SD 0.5<.001), and POD3 (mean 1.7, SD 0.7 vs mean2.2, SD 0.4; <.001). Similarly, average pain intensity was lower in group 1 compared with group 2 across all 3 consecutive PODs: POD1 (mean 3.7, SD 0.9 vs mean 4.7, SD 0.6; <.001); POD2 (mean 3.3, SD 0.8 vs mean 3.6, SD 0.5; =.01); and POD3 (mean 2.5, SD 0.8 vs mean 3.1, SD 0.5; <.001). General activity was significantly less affected in group 1 on POD 1 (mean 4.3, SD 1.0 vs mean 5.0, SD 1.5; =.004) and POD 2 (mean 3.1, SD 0.7 vs mean 3.7, SD 1.3; =.009). Conclusions: The use of an SMS-based educational intervention significantly improved the postoperative pain experience of pediatric patients undergoing thoracic surgery. Further research is needed to clarify its impact on clinical outcomes and to better understand the mechanisms underlying improved pain management. Trial Registration: Chinese Clinical Trial Registry ChiCTR2300076554; https://www.chictr.org.cn/showprojEN.html?proj=203355
Depression subtype classification from social media posts: few-shot prompting vs. fine-tuning of large language models
BackgroundSocial media provides timely proxy signals of mental health, but reliable tweet-level classification of depression subtypes remains challenging due to short, noisy text, overlapping symptomatology,