Using the Fitbit for Early Detection of Infection and Reduction of Healthcare Utilization After Discharge in Pediatric Surgical Patients

What this Trial Is About

This research aims to analyze data from the Fitbit wearable device to predict infections after surgery in children with complicated appendicitis. The study focuses on how this prediction affects clinical decision-making, time to first contact with healthcare, and postoperative healthcare use. The study involves children aged 3 to 18 who have undergone laparoscopic appendectomy for complicated appendicitis, with the goal of improving early infection detection and patient care. Participants will wear Fitbit devices that collect heart rate, physical activity, and sleep data in near-real time. Machine learning methods will be applied to this data to develop and validate an algorithm that detects postoperative infection. The study has two main parts: first, developing and validating the infection prediction algorithm using Fitbit data; second, assessing how access to real-time infection alerts influences clinicians’ decisions and healthcare use. This includes daily reports and alerts sent to surgeons for patients in the implementation phase. Throughout the study, Fitbit data and daily symptom diaries will be collected for 30 days from enrollment to monitor recovery. Researchers will analyze changes in physical activity, heart rate, sleep patterns, symptom reports, healthcare visits, and clinician decision-making. The study includes surveys and qualitative assessments to understand the impact of Fitbit data on care. Participants are monitored for postoperative infection and healthcare utilization during this period, supporting early detection and improved management.

Early Detection of Infection Using the Fitbit in Pediatric Surgical Patients