Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Classification of orthostatic intolerance through data analytics

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Harvard

Gilmore, S, Hart, J, Geddes, J, Olsen, CH, Mehlsen, J, Gremaud, P & Olufsen, MS 2021, 'Classification of orthostatic intolerance through data analytics', Medical & Biological Engineering & Computing, bind 59, nr. 3, s. 621-632. https://doi.org/10.1007/s11517-021-02314-0

APA

CBE

MLA

Vancouver

Author

Gilmore, Steven ; Hart, Joseph ; Geddes, Justen ; Olsen, Christian H ; Mehlsen, Jesper ; Gremaud, Pierre ; Olufsen, Mette S. / Classification of orthostatic intolerance through data analytics. I: Medical & Biological Engineering & Computing. 2021 ; Bind 59, Nr. 3. s. 621-632.

Bibtex

@article{e891ad749421423fa12557aa5b5d6583,
title = "Classification of orthostatic intolerance through data analytics",
abstract = "Imbalance in the autonomic nervous system can lead to orthostatic intolerance manifested by dizziness, lightheadedness, and a sudden loss of consciousness (syncope); these are common conditions, but they are challenging to diagnose correctly. Uncertainties about the triggering mechanisms and the underlying pathophysiology have led to variations in their classification. This study uses machine learning to categorize patients with orthostatic intolerance. We use random forest classification trees to identify a small number of markers in blood pressure, and heart rate time-series data measured during head-up tilt to (a) distinguish patients with a single pathology and (b) examine data from patients with a mixed pathophysiology. Next, we use Kmeans to cluster the markers representing the time-series data. We apply the proposed method analyzing clinical data from 186 subjects identified as control or suffering from one of four conditions: postural orthostatic tachycardia (POTS), cardioinhibition, vasodepression, and mixed cardioinhibition and vasodepression. Classification results confirm the use of supervised machine learning. We were able to categorize more than 95% of patients with a single condition and were able to subgroup all patients with mixed cardioinhibitory and vasodepressor syncope. Clustering results confirm the disease groups and identify two distinct subgroups within the control and mixed groups. The proposed study demonstrates how to use machine learning to discover structure in blood pressure and heart rate time-series data. The methodology is used in classification of patients with orthostatic intolerance. Diagnosing orthostatic intolerance is challenging, and full characterization of the pathophysiological mechanisms remains a topic of ongoing research. This study provides a step toward leveraging machine learning to assist clinicians and researchers in addressing these challenges. Graphical abstract Machine learning tools utilized to analyze heart rate (HR) and blood pressure (BP) time-series data from syncope and control patients. Results show that machine learning can provide accurate classification of disease groups for 98% of patients and we identified two subgroups within the control patients differentiated by their BP response.",
keywords = "Classification, Clustering, Machine learning, Orthostatic intolerance, Syncope",
author = "Steven Gilmore and Joseph Hart and Justen Geddes and Olsen, {Christian H} and Jesper Mehlsen and Pierre Gremaud and Olufsen, {Mette S}",
year = "2021",
month = mar,
doi = "10.1007/s11517-021-02314-0",
language = "English",
volume = "59",
pages = "621--632",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer",
number = "3",

}

RIS

TY - JOUR

T1 - Classification of orthostatic intolerance through data analytics

AU - Gilmore, Steven

AU - Hart, Joseph

AU - Geddes, Justen

AU - Olsen, Christian H

AU - Mehlsen, Jesper

AU - Gremaud, Pierre

AU - Olufsen, Mette S

PY - 2021/3

Y1 - 2021/3

N2 - Imbalance in the autonomic nervous system can lead to orthostatic intolerance manifested by dizziness, lightheadedness, and a sudden loss of consciousness (syncope); these are common conditions, but they are challenging to diagnose correctly. Uncertainties about the triggering mechanisms and the underlying pathophysiology have led to variations in their classification. This study uses machine learning to categorize patients with orthostatic intolerance. We use random forest classification trees to identify a small number of markers in blood pressure, and heart rate time-series data measured during head-up tilt to (a) distinguish patients with a single pathology and (b) examine data from patients with a mixed pathophysiology. Next, we use Kmeans to cluster the markers representing the time-series data. We apply the proposed method analyzing clinical data from 186 subjects identified as control or suffering from one of four conditions: postural orthostatic tachycardia (POTS), cardioinhibition, vasodepression, and mixed cardioinhibition and vasodepression. Classification results confirm the use of supervised machine learning. We were able to categorize more than 95% of patients with a single condition and were able to subgroup all patients with mixed cardioinhibitory and vasodepressor syncope. Clustering results confirm the disease groups and identify two distinct subgroups within the control and mixed groups. The proposed study demonstrates how to use machine learning to discover structure in blood pressure and heart rate time-series data. The methodology is used in classification of patients with orthostatic intolerance. Diagnosing orthostatic intolerance is challenging, and full characterization of the pathophysiological mechanisms remains a topic of ongoing research. This study provides a step toward leveraging machine learning to assist clinicians and researchers in addressing these challenges. Graphical abstract Machine learning tools utilized to analyze heart rate (HR) and blood pressure (BP) time-series data from syncope and control patients. Results show that machine learning can provide accurate classification of disease groups for 98% of patients and we identified two subgroups within the control patients differentiated by their BP response.

AB - Imbalance in the autonomic nervous system can lead to orthostatic intolerance manifested by dizziness, lightheadedness, and a sudden loss of consciousness (syncope); these are common conditions, but they are challenging to diagnose correctly. Uncertainties about the triggering mechanisms and the underlying pathophysiology have led to variations in their classification. This study uses machine learning to categorize patients with orthostatic intolerance. We use random forest classification trees to identify a small number of markers in blood pressure, and heart rate time-series data measured during head-up tilt to (a) distinguish patients with a single pathology and (b) examine data from patients with a mixed pathophysiology. Next, we use Kmeans to cluster the markers representing the time-series data. We apply the proposed method analyzing clinical data from 186 subjects identified as control or suffering from one of four conditions: postural orthostatic tachycardia (POTS), cardioinhibition, vasodepression, and mixed cardioinhibition and vasodepression. Classification results confirm the use of supervised machine learning. We were able to categorize more than 95% of patients with a single condition and were able to subgroup all patients with mixed cardioinhibitory and vasodepressor syncope. Clustering results confirm the disease groups and identify two distinct subgroups within the control and mixed groups. The proposed study demonstrates how to use machine learning to discover structure in blood pressure and heart rate time-series data. The methodology is used in classification of patients with orthostatic intolerance. Diagnosing orthostatic intolerance is challenging, and full characterization of the pathophysiological mechanisms remains a topic of ongoing research. This study provides a step toward leveraging machine learning to assist clinicians and researchers in addressing these challenges. Graphical abstract Machine learning tools utilized to analyze heart rate (HR) and blood pressure (BP) time-series data from syncope and control patients. Results show that machine learning can provide accurate classification of disease groups for 98% of patients and we identified two subgroups within the control patients differentiated by their BP response.

KW - Classification

KW - Clustering

KW - Machine learning

KW - Orthostatic intolerance

KW - Syncope

U2 - 10.1007/s11517-021-02314-0

DO - 10.1007/s11517-021-02314-0

M3 - Journal article

C2 - 33582941

VL - 59

SP - 621

EP - 632

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 3

ER -

ID: 62386634