PerSleep: A Visual Analytics Approach for Performance Assessment of Sleep Staging Models

Humberto Garcia Caballero, Alberto Corvo, Fokke van Meulen, Pedro Fonseca, Sebastiaan Overeem, Jack J. van Wijk, Michel A. Westenberg

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

106 Downloads (Pure)

Abstract

Machine learning is becoming increasingly popular in the medical domain. In the near future, clinicians expect predictive models to support daily tasks such as diagnosis and prognostic analysis. For this reason, it is utterly important to evaluate and compare the performance of such models so that clinicians can safely rely on them. In this paper, we focus on sleep staging wherein machine learning models can be used to automate or support sleep scoring. Evaluation of these models is complex because sleep is a natural process, which varies among patients. For adoption in clinical routine, it is important to understand how the models perform for different groups of patients. Moreover, models can be trained to recognize different characteristics in the data, and model developers need to understand why and how performance of the different models varies. To address these challenges, we present a visual analytics approach to evaluate the performance of predictive models on sleep staging and to help experts better understand these models with respect to patient data (e.g., conditions, medication, etc.). We illustrate the effectiveness of our approach by comparing multiple models trained on real-world sleep staging data with experts.
Original languageEnglish
Title of host publicationEurographics Workshop on Visual Computing for Biology and Medicine (2021)
EditorsS. Oeltze-Jafra, N.N. Smit, B. Sommer
PublisherThe Eurographics Association
Pages123-133
Number of pages11
ISBN (Electronic)978-3-03868-140-3
DOIs
Publication statusPublished - 2021
Event2021 Eurographics Workshop on Visual Computing for Biology and Medicine, VCBM 2021 - Paris, France
Duration: 22 Sep 202124 Sep 2021
https://conferences.eg.org/vcbm2021/program/

Workshop

Workshop2021 Eurographics Workshop on Visual Computing for Biology and Medicine, VCBM 2021
Abbreviated titleVCBM 2021
Country/TerritoryFrance
CityParis
Period22/09/2124/09/21
Internet address

Fingerprint

Dive into the research topics of 'PerSleep: A Visual Analytics Approach for Performance Assessment of Sleep Staging Models'. Together they form a unique fingerprint.
  • VCBM 2021 Honorable Mention

    Garcia Caballero, Humberto (Recipient), Corvo, Alberto (Recipient), van Meulen, Fokke (Recipient), Fonseca, Pedro (Recipient), Overeem, Sebastiaan (Recipient), van Wijk, Jack J. (Recipient) & Westenberg, Michel A. (Recipient), 24 Sep 2021

    Prize: OtherCareer, activity or publication related prizes (lifetime, best paper, poster etc.)Scientific

    File

Cite this