Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia: Results from a Prospective Exploratory Study

Catriona M. Steele (Corresponding Author), Rajat Mukherjee, Juha M. Kortelainen, Harri Pölönen, Michael Jedwab, Susan L. Brady, Kayla Brinkman Theimer, Susan Langmore, Luis F. Riquelme, Nancy B. Swigert, Philip M. Bath, Larry B. Goldstein, Richard L. Hughes, Dana Leifer, Kennedy R. Lees, Atte Meretoja, Natalia Muehlemann

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Oropharyngeal dysphagia is prevalent in several at-risk populations, including post-stroke patients, patients in intensive care and the elderly. Dysphagia contributes to longer hospital stays and poor outcomes, including pneumonia. Early identification of dysphagia is recommended as part of the evaluation of at-risk patients, but available bedside screening tools perform inconsistently. In this study, we developed algorithms to detect swallowing impairment using a novel accelerometer-based dysphagia detection system (DDS). A sample of 344 individuals was enrolled across seven sites in the United States. Dual-axis accelerometry signals were collected prospectively with simultaneous videofluoroscopy (VFSS) during swallows of liquid barium stimuli in thin, mildly, moderately and extremely thick consistencies. Signal processing classifiers were trained using linear discriminant analysis and 10,000 random training–test data splits. The primary objective was to develop an algorithm to detect impaired swallowing safety with thin liquids with an area under receiver operating characteristic curve (AUC) > 80% compared to the VFSS reference standard. Impaired swallowing safety was identified in 7.2% of the thin liquid boluses collected. At least one unsafe thin liquid bolus was found in 19.7% of participants, but participants did not exhibit impaired safety consistently. The DDS classifier algorithms identified participants with impaired thin liquid swallowing safety with a mean AUC of 81.5%, (sensitivity 90.4%, specificity 60.0%). Thicker consistencies were effective for reducing the frequency of penetration–aspiration. This DDS reached targeted performance goals in detecting impaired swallowing safety with thin liquids. Simultaneous measures by DDS and VFSS, as performed here, will be used for future validation studies.

LanguageEnglish
Pages1-10
JournalDysphagia
DOIs
Publication statusE-pub ahead of print - 5 Jan 2019
MoE publication typeNot Eligible

Fingerprint

Deglutition Disorders
Deglutition
Prospective Studies
Equipment and Supplies
Safety
Area Under Curve
Accelerometry
Swallows
Validation Studies
Discriminant Analysis
Barium
Critical Care
ROC Curve
Length of Stay
Pneumonia
Stroke
Sensitivity and Specificity

Keywords

  • Deglutition
  • Deglutition disorders
  • Devices
  • Dysphagia
  • Screening
  • Swallowing

Cite this

Steele, Catriona M. ; Mukherjee, Rajat ; Kortelainen, Juha M. ; Pölönen, Harri ; Jedwab, Michael ; Brady, Susan L. ; Theimer, Kayla Brinkman ; Langmore, Susan ; Riquelme, Luis F. ; Swigert, Nancy B. ; Bath, Philip M. ; Goldstein, Larry B. ; Hughes, Richard L. ; Leifer, Dana ; Lees, Kennedy R. ; Meretoja, Atte ; Muehlemann, Natalia. / Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia : Results from a Prospective Exploratory Study. In: Dysphagia. 2019 ; pp. 1-10.
@article{89811de113364adf8b6a487806306b21,
title = "Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia: Results from a Prospective Exploratory Study",
abstract = "Oropharyngeal dysphagia is prevalent in several at-risk populations, including post-stroke patients, patients in intensive care and the elderly. Dysphagia contributes to longer hospital stays and poor outcomes, including pneumonia. Early identification of dysphagia is recommended as part of the evaluation of at-risk patients, but available bedside screening tools perform inconsistently. In this study, we developed algorithms to detect swallowing impairment using a novel accelerometer-based dysphagia detection system (DDS). A sample of 344 individuals was enrolled across seven sites in the United States. Dual-axis accelerometry signals were collected prospectively with simultaneous videofluoroscopy (VFSS) during swallows of liquid barium stimuli in thin, mildly, moderately and extremely thick consistencies. Signal processing classifiers were trained using linear discriminant analysis and 10,000 random training–test data splits. The primary objective was to develop an algorithm to detect impaired swallowing safety with thin liquids with an area under receiver operating characteristic curve (AUC) > 80{\%} compared to the VFSS reference standard. Impaired swallowing safety was identified in 7.2{\%} of the thin liquid boluses collected. At least one unsafe thin liquid bolus was found in 19.7{\%} of participants, but participants did not exhibit impaired safety consistently. The DDS classifier algorithms identified participants with impaired thin liquid swallowing safety with a mean AUC of 81.5{\%}, (sensitivity 90.4{\%}, specificity 60.0{\%}). Thicker consistencies were effective for reducing the frequency of penetration–aspiration. This DDS reached targeted performance goals in detecting impaired swallowing safety with thin liquids. Simultaneous measures by DDS and VFSS, as performed here, will be used for future validation studies.",
keywords = "Deglutition, Deglutition disorders, Devices, Dysphagia, Screening, Swallowing",
author = "Steele, {Catriona M.} and Rajat Mukherjee and Kortelainen, {Juha M.} and Harri P{\"o}l{\"o}nen and Michael Jedwab and Brady, {Susan L.} and Theimer, {Kayla Brinkman} and Susan Langmore and Riquelme, {Luis F.} and Swigert, {Nancy B.} and Bath, {Philip M.} and Goldstein, {Larry B.} and Hughes, {Richard L.} and Dana Leifer and Lees, {Kennedy R.} and Atte Meretoja and Natalia Muehlemann",
year = "2019",
month = "1",
day = "5",
doi = "10.1007/s00455-018-09974-5",
language = "English",
pages = "1--10",
journal = "Dysphagia",
issn = "0179-051X",
publisher = "Springer",

}

Steele, CM, Mukherjee, R, Kortelainen, JM, Pölönen, H, Jedwab, M, Brady, SL, Theimer, KB, Langmore, S, Riquelme, LF, Swigert, NB, Bath, PM, Goldstein, LB, Hughes, RL, Leifer, D, Lees, KR, Meretoja, A & Muehlemann, N 2019, 'Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia: Results from a Prospective Exploratory Study', Dysphagia, pp. 1-10. https://doi.org/10.1007/s00455-018-09974-5

Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia : Results from a Prospective Exploratory Study. / Steele, Catriona M. (Corresponding Author); Mukherjee, Rajat; Kortelainen, Juha M.; Pölönen, Harri; Jedwab, Michael; Brady, Susan L.; Theimer, Kayla Brinkman; Langmore, Susan; Riquelme, Luis F.; Swigert, Nancy B.; Bath, Philip M.; Goldstein, Larry B.; Hughes, Richard L.; Leifer, Dana; Lees, Kennedy R.; Meretoja, Atte; Muehlemann, Natalia.

In: Dysphagia, 05.01.2019, p. 1-10.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Development of a Non-invasive Device for Swallow Screening in Patients at Risk of Oropharyngeal Dysphagia

T2 - Dysphagia

AU - Steele, Catriona M.

AU - Mukherjee, Rajat

AU - Kortelainen, Juha M.

AU - Pölönen, Harri

AU - Jedwab, Michael

AU - Brady, Susan L.

AU - Theimer, Kayla Brinkman

AU - Langmore, Susan

AU - Riquelme, Luis F.

AU - Swigert, Nancy B.

AU - Bath, Philip M.

AU - Goldstein, Larry B.

AU - Hughes, Richard L.

AU - Leifer, Dana

AU - Lees, Kennedy R.

AU - Meretoja, Atte

AU - Muehlemann, Natalia

PY - 2019/1/5

Y1 - 2019/1/5

N2 - Oropharyngeal dysphagia is prevalent in several at-risk populations, including post-stroke patients, patients in intensive care and the elderly. Dysphagia contributes to longer hospital stays and poor outcomes, including pneumonia. Early identification of dysphagia is recommended as part of the evaluation of at-risk patients, but available bedside screening tools perform inconsistently. In this study, we developed algorithms to detect swallowing impairment using a novel accelerometer-based dysphagia detection system (DDS). A sample of 344 individuals was enrolled across seven sites in the United States. Dual-axis accelerometry signals were collected prospectively with simultaneous videofluoroscopy (VFSS) during swallows of liquid barium stimuli in thin, mildly, moderately and extremely thick consistencies. Signal processing classifiers were trained using linear discriminant analysis and 10,000 random training–test data splits. The primary objective was to develop an algorithm to detect impaired swallowing safety with thin liquids with an area under receiver operating characteristic curve (AUC) > 80% compared to the VFSS reference standard. Impaired swallowing safety was identified in 7.2% of the thin liquid boluses collected. At least one unsafe thin liquid bolus was found in 19.7% of participants, but participants did not exhibit impaired safety consistently. The DDS classifier algorithms identified participants with impaired thin liquid swallowing safety with a mean AUC of 81.5%, (sensitivity 90.4%, specificity 60.0%). Thicker consistencies were effective for reducing the frequency of penetration–aspiration. This DDS reached targeted performance goals in detecting impaired swallowing safety with thin liquids. Simultaneous measures by DDS and VFSS, as performed here, will be used for future validation studies.

AB - Oropharyngeal dysphagia is prevalent in several at-risk populations, including post-stroke patients, patients in intensive care and the elderly. Dysphagia contributes to longer hospital stays and poor outcomes, including pneumonia. Early identification of dysphagia is recommended as part of the evaluation of at-risk patients, but available bedside screening tools perform inconsistently. In this study, we developed algorithms to detect swallowing impairment using a novel accelerometer-based dysphagia detection system (DDS). A sample of 344 individuals was enrolled across seven sites in the United States. Dual-axis accelerometry signals were collected prospectively with simultaneous videofluoroscopy (VFSS) during swallows of liquid barium stimuli in thin, mildly, moderately and extremely thick consistencies. Signal processing classifiers were trained using linear discriminant analysis and 10,000 random training–test data splits. The primary objective was to develop an algorithm to detect impaired swallowing safety with thin liquids with an area under receiver operating characteristic curve (AUC) > 80% compared to the VFSS reference standard. Impaired swallowing safety was identified in 7.2% of the thin liquid boluses collected. At least one unsafe thin liquid bolus was found in 19.7% of participants, but participants did not exhibit impaired safety consistently. The DDS classifier algorithms identified participants with impaired thin liquid swallowing safety with a mean AUC of 81.5%, (sensitivity 90.4%, specificity 60.0%). Thicker consistencies were effective for reducing the frequency of penetration–aspiration. This DDS reached targeted performance goals in detecting impaired swallowing safety with thin liquids. Simultaneous measures by DDS and VFSS, as performed here, will be used for future validation studies.

KW - Deglutition

KW - Deglutition disorders

KW - Devices

KW - Dysphagia

KW - Screening

KW - Swallowing

UR - http://www.scopus.com/inward/record.url?scp=85059561394&partnerID=8YFLogxK

U2 - 10.1007/s00455-018-09974-5

DO - 10.1007/s00455-018-09974-5

M3 - Article

SP - 1

EP - 10

JO - Dysphagia

JF - Dysphagia

SN - 0179-051X

ER -