Project: Visualization to detect early deterioration of neonatal patients
Description
A Neonatal Intensive Care Unit (NICU) is a hospital department for neonates who need intensive care after birth. These neonates are monitored closely to check their vital signs (like ECG, blood pressure, oxygen saturation levels in the blood), as life-threatening complications can occur. These complications can have various causes. Each time a potentially critical situation occurs an alarm sounds. The more vital signs are measured, the more alarms can occur.
Premature infants are cared for in a neonatal intensive care unit, where they are continuously monitored to check their health status and development. To detect critical events, predefined boundaries to the monitored signals are defined and if they are crossed, an alarm is generated. However, though data is continuously available, it is not used prospectively to predict upcoming critical events or diseases. Furthermore, the data can also provide better understanding on the conditions that generate the upcoming events.
This project will be focused on developing a visual analytics solution that allows data exploration and aids in formulating hypothesis on the data by finding patterns, trends and detecting anomalies. The main goal is to provide better understanding on the data to support development of accurate and explainable models for early detection of neonatal deterioration.
Details
- Student
-
KTKy-Anh Tran
- Supervisor
-
Anna Vilanova
- Secondary supervisor
-
CPCarola van Pul (MMC)
- External location
- Máxima Medisch Centrum
- Link
- Thesis