An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight
An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight
Introduction: polysomnographic recordings are essential for diagnosing many sleep disorders, yet their detailed analysis presents considerable challenges. With the rise of machine learning methodologies, researchers have created various algorithms to automatically score and extract clinically relevant features from polysomnography, but less research has been devoted to how exactly the algorithms should be incorporated into the workflow of sleep technologists. This paper presents a sophisticated data collection platform developed under the Sleep Revolution project, to harness polysomnographic data from multiple European centers.
Methods: a tripartite platform is presented: a user-friendly web platform for uploading three-night polysomnographic recordings, a dedicated splitter that segments these into individual one-night recordings, and an advanced processor that enhances the one-night polysomnography with contemporary automatic scoring algorithms. The platform is evaluated using real-life data and human scorers, whereby scoring time, accuracy, and trust are quantified. Additionally, the scorers were interviewed about their trust in the platform, along with the impact of its integration into their workflow.
Results: we found that incorporating AI into the workflow of sleep technologists both decreased the time to score by up to 65 min and increased the agreement between technologists by as much as 0.17 κ.
Discussion: we conclude that while the inclusion of AI into the workflow of sleep technologists can have a positive impact in terms of speed and agreement, there is a need for trust in the algorithms.
Holm, Benedikt
d9ae89eb-36f6-4355-bdf0-90507762c9c5
Jouan, Gabriel
41a11a8b-6b6f-45e9-a34c-e653458ab262
Hardarson, Emil
bbdcb067-9e1b-4995-9340-cab3e48b981e
Sigurðardottir, Sigríður
e427c52c-5692-4bc7-911a-19d715fee5ec
Hoelke, Kenan
8bfe17e9-7a4a-406b-82ef-0d188f14fc5e
Murphy, Conor
a3c8a71b-f59f-4286-9610-782609818f68
Arnardóttir, Erna Sif
9bfbbe32-8214-47a9-86ba-43be85458830
Óskarsdóttir, María
d159ed8f-9dd3-4ff3-8b00-d43579ab71be
Islind, Anna Sigríður
207957b5-9bcb-4b25-8f06-016561470dd9
13 May 2024
Holm, Benedikt
d9ae89eb-36f6-4355-bdf0-90507762c9c5
Jouan, Gabriel
41a11a8b-6b6f-45e9-a34c-e653458ab262
Hardarson, Emil
bbdcb067-9e1b-4995-9340-cab3e48b981e
Sigurðardottir, Sigríður
e427c52c-5692-4bc7-911a-19d715fee5ec
Hoelke, Kenan
8bfe17e9-7a4a-406b-82ef-0d188f14fc5e
Murphy, Conor
a3c8a71b-f59f-4286-9610-782609818f68
Arnardóttir, Erna Sif
9bfbbe32-8214-47a9-86ba-43be85458830
Óskarsdóttir, María
d159ed8f-9dd3-4ff3-8b00-d43579ab71be
Islind, Anna Sigríður
207957b5-9bcb-4b25-8f06-016561470dd9
Holm, Benedikt, Jouan, Gabriel, Hardarson, Emil, Sigurðardottir, Sigríður, Hoelke, Kenan, Murphy, Conor, Arnardóttir, Erna Sif, Óskarsdóttir, María and Islind, Anna Sigríður
(2024)
An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight.
Frontiers in Neuroinformatics, 18, [1379932].
(doi:10.3389/fninf.2024.1379932).
Abstract
Introduction: polysomnographic recordings are essential for diagnosing many sleep disorders, yet their detailed analysis presents considerable challenges. With the rise of machine learning methodologies, researchers have created various algorithms to automatically score and extract clinically relevant features from polysomnography, but less research has been devoted to how exactly the algorithms should be incorporated into the workflow of sleep technologists. This paper presents a sophisticated data collection platform developed under the Sleep Revolution project, to harness polysomnographic data from multiple European centers.
Methods: a tripartite platform is presented: a user-friendly web platform for uploading three-night polysomnographic recordings, a dedicated splitter that segments these into individual one-night recordings, and an advanced processor that enhances the one-night polysomnography with contemporary automatic scoring algorithms. The platform is evaluated using real-life data and human scorers, whereby scoring time, accuracy, and trust are quantified. Additionally, the scorers were interviewed about their trust in the platform, along with the impact of its integration into their workflow.
Results: we found that incorporating AI into the workflow of sleep technologists both decreased the time to score by up to 65 min and increased the agreement between technologists by as much as 0.17 κ.
Discussion: we conclude that while the inclusion of AI into the workflow of sleep technologists can have a positive impact in terms of speed and agreement, there is a need for trust in the algorithms.
Text
fninf-18-1379932
- Version of Record
More information
Accepted/In Press date: 29 April 2024
Published date: 13 May 2024
Identifiers
Local EPrints ID: 504339
URI: http://eprints.soton.ac.uk/id/eprint/504339
ISSN: 1662-5196
PURE UUID: a1f8ac66-1f84-4f95-a507-08a80f695ae4
Catalogue record
Date deposited: 04 Sep 2025 16:56
Last modified: 16 Sep 2025 02:31
Export record
Altmetrics
Contributors
Author:
Benedikt Holm
Author:
Gabriel Jouan
Author:
Emil Hardarson
Author:
Sigríður Sigurðardottir
Author:
Kenan Hoelke
Author:
Conor Murphy
Author:
Erna Sif Arnardóttir
Author:
María Óskarsdóttir
Author:
Anna Sigríður Islind
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics