Clustering neonatal and pediatric intensive care time series using k-means

Anis Abdollahi-Sissan; Camelia Oprea; Lena Olivier; Mark Schoberer; André Stollenwerk

doi:10.3205/25gmds207

April 1, 2026Open Access

Clustering neonatal and pediatric intensive care time series using k-means

View Full Paper

Ask AI

Bookmark

Share

Key Points

To explore how unsupervised clustering can effectively categorize time series data from NICU and PICU.
Utilized k-means clustering to analyze multivariate time series data.
Focused on continuous sensor recordings during neonatal and pediatric intensive care.
Emphasized the challenges of labeling large volumes of data.
Identified distinct clusters within the time series data.
Demonstrated that k-means can reduce the need for manual labeling.
Showed potential for improved data analysis in clinical settings.

Implication

Unsupervised clustering identifies patterns in time series data from neonatal and pediatric intensive care, suggesting a new analysis approach.

Abstract

Introduction: Continuous recordings of different sensors in clinical settings, such as neonatal and pediatric intensive care units (NICU/PICU), produce large volumes of unlabeled multivariate time series (MTS) data. Labeling data is time-intensive, requires trained staff, and is error-prone. Unsupervised [for full text, please go to the a.m. URL]

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Abdollahi-Sissan et al. (2026) studied this question.

synapsesocial.com/papers/69cf5e3d5a333a821460c642 https://doi.org/10.3205/25gmds207

View Full Paper

Ask AI

Bookmark

Share

Clustering neonatal and pediatric intensive care time series using k-means

Key Points

Implication

Abstract

Discussion

Cite This Study

Clustering neonatal and pediatric intensive care time series using k-means

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

Keep reading

More related papers