Clinical Research Directory
Browse clinical research sites, groups, and studies.
Neonatal AI-Based Early Warning System for Late-Onset Sepsis and Necrotizing Enterocolitis in the NICU: Assessment of Response and Effectiveness
Sponsor: University Hospital, Antwerp
Summary
This study aims to evaluate the Intellicens software, an artificial intelligence (AI)-based early warning system designed to help doctors and nurses detect serious complications in premature babies at an early stage. These complications include bloodstream infections (sepsis) and necrotizing enterocolitis (NEC), a serious condition affecting the intestines. The study will involve babies born before 32 weeks of pregnancy who are admitted to the Neonatal Intensive Care Unit (NICU). The Intellicens Neo model analyses routinely collected medical data, such as heart rate, to identify patterns that may indicate an increased risk of sepsis or NEC and generate an early warning for healthcare professionals. The treating doctor remains responsible for deciding whether further examinations or treatment are needed. The software has previously been tested using data from babies who had already been discharged from hospital, with promising results. This study will evaluate how well the software performs in real-life clinical practice during the hospital stay.
Official title: Neonatal AI-Based Early Warning System for Late-Onset Sepsis and Necrotizing Enterocolitis in the NICU: Assessment of Response and Effectiveness in a Post-Implementation Prospective Study With Pre-Implementation Historical Comparison
Key Details
Gender
All
Age Range
Any - Any
Study Type
INTERVENTIONAL
Enrollment
500
Start Date
2026-11-09
Completion Date
2028-03-31
Last Updated
2026-11-12
Healthy Volunteers
Yes
Interventions
Intellicens Neo software
Intellicens Neo is investigational medical device software designed to support early warning of late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in preterm infants admitted to the neonatal intensive care unit (NICU). The software calculates a NeoSep Index every 30 minutes and generates visual alerts when predefined alert criteria are met. The alerts are made visible to the clinical care team to support awareness of potential LOS or NEC. Clinical assessment and treatment decisions remain at the discretion of the treating clinicians. The intervention is evaluated in a prospective, multicenter, post-implementation clinical investigation, with outcomes compared with a pre-implementation historical dataset.
Locations (3)
Antwerp University Hospital
Edegem, Antwerp, Belgium
Amsterdam UMC
Amsterdam, Netherlands
Erasmus MC Rotterdam
Rotterdam, Netherlands