Enhancing Tonsillectomy Recovery with AI: A Comparative Study on Postoperative Care Outcomes.

UNLABELLED: Introduction: Tonsillectomy is commonly associated with significant postoperative challenges such as pain management, complication monitoring, and patient recovery. Traditional care methods, while effective, often do not adequately address these issues, particularly in personalized care and remote monitoring. This study assesses the impact of Artificial Intelligence (AI)-assisted postoperative care on recovery outcomes in tonsillectomy patients compared to conventional care methods. Methods: Conducted at a tertiary care hospital's Otolaryngology Department from January to December 2023, this observational cohort study involved 100 elective tonsillectomy patients. Participants were divided into two cohorts: one receiving traditional care and the other AI-assisted care, which utilized machine learning for pain management, continuous symptom monitoring through wearable devices, and virtual assistance. Results: AI-assisted care significantly improved early postoperative pain management, reducing pain scores to 5.2 ± 1.1 from 6.5 ± 1.2 in traditional care (p = 0.01). Dehydration rates decreased from 6 to 1% (p = 0.05), and the average hospital stay was reduced to 2.8 ± 1.1 days from 3.5 ± 1.2 days. While no significant differences were found in readmission rates for haemorrhage and infection, patient satisfaction notably increased, with pain management improving to 4.4 ± 0.7 and overall satisfaction to 4.1 ± 0.6 (p = 0.03). Conclusion: AI-assisted care offers significant advantages over traditional methods in managing tonsillectomy recovery, optimizing surgical outcomes, and enhancing patient satisfaction. This study supports further exploration into AI's long-term outcomes and its application across various surgical fields.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s12070-024-05103-x.