Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Turubayev, Alisher, Shopova, Anna, Lange, Fabian, Kamalak, Mahmut, Mattes, Paul, Ayvasky, Victoria, Arnrich, Bert, Pfitzner, Bjarne, van de Water, Robin P.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.24217
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914118124961792
author Turubayev, Alisher
Shopova, Anna
Lange, Fabian
Kamalak, Mahmut
Mattes, Paul
Ayvasky, Victoria
Arnrich, Bert
Pfitzner, Bjarne
van de Water, Robin P.
author_facet Turubayev, Alisher
Shopova, Anna
Lange, Fabian
Kamalak, Mahmut
Mattes, Paul
Ayvasky, Victoria
Arnrich, Bert
Pfitzner, Bjarne
van de Water, Robin P.
contents As more Intensive Care Unit (ICU) data becomes available, the interest in developing clinical prediction models to improve healthcare protocols increases. However, the lack of data quality still hinders clinical prediction using Machine Learning (ML). Many vital sign measurements, such as heart rate, contain sizeable missing segments, leaving gaps in the data that could negatively impact prediction performance. Previous works have introduced numerous time-series imputation techniques. Nevertheless, more comprehensive work is needed to compare a representative set of methods for imputing ICU vital signs and determine the best practice. In reality, ad-hoc imputation techniques that could decrease prediction accuracy, like zero imputation, are still used. In this work, we compare established imputation techniques to guide researchers in improving the performance of clinical prediction models by selecting the most accurate imputation technique. We introduce an extensible and reusable benchmark with currently 15 imputation and 4 amputation methods, created for benchmarking on major ICU datasets. We hope to provide a comparative basis and facilitate further ML development to bring more models into clinical practice.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24217
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Closing Gaps: An Imputation Analysis of ICU Vital Signs
Turubayev, Alisher
Shopova, Anna
Lange, Fabian
Kamalak, Mahmut
Mattes, Paul
Ayvasky, Victoria
Arnrich, Bert
Pfitzner, Bjarne
van de Water, Robin P.
Machine Learning
Artificial Intelligence
As more Intensive Care Unit (ICU) data becomes available, the interest in developing clinical prediction models to improve healthcare protocols increases. However, the lack of data quality still hinders clinical prediction using Machine Learning (ML). Many vital sign measurements, such as heart rate, contain sizeable missing segments, leaving gaps in the data that could negatively impact prediction performance. Previous works have introduced numerous time-series imputation techniques. Nevertheless, more comprehensive work is needed to compare a representative set of methods for imputing ICU vital signs and determine the best practice. In reality, ad-hoc imputation techniques that could decrease prediction accuracy, like zero imputation, are still used. In this work, we compare established imputation techniques to guide researchers in improving the performance of clinical prediction models by selecting the most accurate imputation technique. We introduce an extensible and reusable benchmark with currently 15 imputation and 4 amputation methods, created for benchmarking on major ICU datasets. We hope to provide a comparative basis and facilitate further ML development to bring more models into clinical practice.
title Closing Gaps: An Imputation Analysis of ICU Vital Signs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.24217