Show simple item record

Medical Intervention Recognition in the PICU

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorSiebes, Arno
dc.contributor.authorTran, Zang
dc.date.accessioned2024-10-18T00:02:24Z
dc.date.available2024-10-18T00:02:24Z
dc.date.issued2024
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/47988
dc.description.sponsorshipUtrecht University
dc.language.isoEN
dc.subjectThis study focuses on monitoring vital signs in pediatric intensive care using data science techniques. By applying Mini Batch K-means clustering and Random Forest validation to multivariate time series data, we identified significant health events in cardiac infants. The “Difference Baseline Cubed (10m - 5m)” method achieved an accuracy of 0.966. These findings highlight the potential of clustering techniques to improve patient care and enable real-time event detection in critical care settings
dc.titleMedical Intervention Recognition in the PICU
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.courseuuApplied Data Science
dc.thesis.id40345


Files in this item

Thumbnail
Name:
ADS_thesis_final.pdf
Size:
1.479Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record