Overview
Body
Appendicitis is the most common surgical emergency requiring operation in children, and accounts for a third of all pediatric hospital admissions for abdominal pain. Approximately 80,000 appendectomies are performed in the US annually, of which a third are for complicated appendicitis (appendicitis where the appendix is inflamed & damaged by gangrene, abscess, and/or perforation). Surgical Site Infection (SSI) is common among patients who undergo appendectomies for complicated appendicitis. Many parents and/or caregivers have few tools to detect the presence of infection with objective data. In most cases, they must rely on measures & assessment that can be inaccurate. (e.g. thermometers and appetite). The object of this study is to develop and externally validate a machine learning algorithm for postoperative infection. Additionally, a pre-post study will be conducted to determine the effect of near real-time availability of the infection alert from Fitbit on clinical decision-making, time to first contact with the healthcare system, and healthcare utilization.
Subject Population
Body
- Age 3-18 years old
- Be post-surgical laparoscopic appendectomy for complicated appendectomy
