A comparative analysis of DBSCAN, K-means, and quadratic variation algorithms for automatic identification of swallows from swallowing accelerometry signals

BACKGROUND Cervical auscultation with high resolution sensors is currently under consideration as a method of automatically screening for specific swallowing abnormalities. To be clinically useful without human involvement, any devices based on cervical auscultation should be able to detect specified swallowing events in an automatic manner. METHODS In this paper, we comparatively analyze the density-based spatial clustering of applications with noise algorithm (DBSCAN), a k-means based algorithm, and an algorithm based on quadratic variation as methods of differentiating periods of swallowing activity from periods of time without swallows. These algorithms utilized swallowing vibration data exclusively and compared the results to a gold standard measure of swallowing duration. Data was collected from 23 subjects that were actively suffering from swallowing difficulties. RESULTS Comparing the performance of the DBSCAN algorithm with a proven segmentation algorithm that utilizes k-means clustering demonstrated that the DBSCAN algorithm had a higher sensitivity and correctly segmented more swallows. Comparing its performance with a threshold-based algorithm that utilized the quadratic variation of the signal showed that the DBSCAN algorithm offered no direct increase in performance. However, it offered several other benefits including a faster run time and more consistent performance between patients. All algorithms showed noticeable differentiation from the endpoints provided by a videofluoroscopy examination as well as reduced sensitivity. CONCLUSIONS In summary, we showed that the DBSCAN algorithm is a viable method for detecting the occurrence of a swallowing event using cervical auscultation signals, but significant work must be done to improve its performance before it can be implemented in an unsupervised manner.

[1]  Sheela Ramanna,et al.  Classification of Swallowing Sound Signals: A Rough Set Approach , 2004, Rough Sets and Current Trends in Computing.

[2]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[3]  Suzanne Kieffer,et al.  Feature extraction and selection for objective gait analysis and fall risk assessment by accelerometry , 2011, Biomedical engineering online.

[4]  Amitava Das,et al.  Hybrid fuzzy logic committee neural networks for recognition of swallow acceleration signals , 2001, Comput. Methods Programs Biomed..

[5]  Z. Moussavi,et al.  Swallowing Sound Characteristics in Healthy and Dysphagic Individuals , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  S. Leder,et al.  Fiberoptic endoscopic evaluation of swallowing. , 2008, Physical medicine and rehabilitation clinics of North America.

[7]  J. Stierwalt,et al.  An Acoustic Profile of Normal Swallowing , 2005, Dysphagia.

[8]  Tom Chau,et al.  Baseline Characteristics of Dual-Axis Cervical Accelerometry Signals , 2010, Annals of Biomedical Engineering.

[9]  J. Logemann,et al.  Evaluation and treatment of swallowing disorders , 1983 .

[10]  Catriona M. Steele,et al.  Oropharyngeal dysphagia assessment and treatment efficacy: setting the record straight (response to Campbell-Taylor). , 2009, Journal of the American Medical Directors Association.

[11]  Walter Huda,et al.  Radiation Exposure Time during MBSS: Influence of Swallowing Impairment Severity, Medical Diagnosis, Clinician Experience, and Standardized Protocol Use , 2013, Dysphagia.

[12]  C. Sapienza,et al.  Strength-Training Exercise in Dysphagia Rehabilitation: Principles, Procedures, and Directions for Future Research , 2007, Dysphagia.

[13]  Gregory Piatetsky-Shapiro,et al.  Advances in Knowledge Discovery and Data Mining , 2004, Lecture Notes in Computer Science.

[14]  Irena Orovic,et al.  Time-Frequency Analysis and Hermite Projection Method Applied to Swallowing Accelerometry Signals , 2010, EURASIP J. Adv. Signal Process..

[15]  Andréa P. da Silva,et al.  Comparison between videofluoroscopy and endoscopic evaluation of swallowing for the diagnosis of dysphagia in children , 2010, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[16]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[17]  Joshua M. Dudik,et al.  The effects of increased fluid viscosity on swallowing sounds in healthy adults , 2013, Biomedical engineering online.

[18]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[19]  M G Rugiu,et al.  Role of videofluoroscopy in evaluation of neurologic dysphagia. , 2007, Acta otorhinolaryngologica Italica : organo ufficiale della Societa italiana di otorinolaringologia e chirurgia cervico-facciale.

[20]  T Chau,et al.  Time and time–frequency characterization of dual-axis swallowing accelerometry signals , 2008, Physiological measurement.

[21]  Edward Sazonov,et al.  Abstract—the Detection of Swallowing Events by Acoustic , 2011 .

[22]  Tom Chau,et al.  Segmentation of Dual-Axis Swallowing Accelerometry Signals in Healthy Subjects With Analysis of Anthropometric Effects on Duration of Swallowing Activities , 2009, IEEE Transactions on Biomedical Engineering.

[23]  A. Nacci,et al.  Fiberoptic endoscopic evaluation of swallowing (FEES): proposal for informed consent. , 2008, Acta otorhinolaryngologica Italica : organo ufficiale della Societa italiana di otorinolaringologia e chirurgia cervico-facciale.

[24]  C. Steele,et al.  Variation in Temporal Measures of Swallowing: Sex and Volume Effects , 2013, Dysphagia.

[25]  Zahra Moussavi,et al.  Comparison of recurrence plot features of swallowing and breath sounds , 2008 .

[26]  Tom Chau,et al.  An Online Swallow Detection Algorithm Based on the Quadratic Variation of Dual-Axis Accelerometry , 2010, IEEE Transactions on Signal Processing.

[27]  B. Murdoch,et al.  Acoustic Signature of the Normal Swallow: Characterization by Age, Gender, and Bolus Volume , 2002, The Annals of otology, rhinology, and laryngology.

[28]  M. J. Katz,et al.  Fractals and the analysis of waveforms. , 1988, Computers in biology and medicine.

[29]  Michael R. Neuman,et al.  Limited receptive area neural classifier for recognition of swallowing sounds using short-time Fourier transform , 2007, 2007 International Joint Conference on Neural Networks.

[30]  A. Rademaker,et al.  Chin-down posture effect on aspiration in dysphagic patients. , 1993, Archives of physical medicine and rehabilitation.

[31]  D. Smithard,et al.  Complications and outcome after acute stroke. Does dysphagia matter? , 1996, Stroke.

[32]  A. Rademaker,et al.  Temporal and biomechanical characteristics of oropharyngeal swallow in younger and older men. , 2000, Journal of speech, language, and hearing research : JSLHR.

[33]  Andy Lücking,et al.  Reliability and Validity of Cervical Auscultation , 2007, Dysphagia.

[34]  M. Spieker,et al.  Evaluating dysphagia. , 2000, American family physician.

[35]  J. Parmanen.  Some Reasons to Revise the International Standard ISO 226:2003: Acoustics—Normal Equal-Loudness-Level Contours , 2012 .

[36]  Joshua M. Dudik,et al.  A comparative analysis of swallowing accelerometry and sounds during saliva swallows , 2015, Biomedical engineering online.

[37]  O. Makeyev,et al.  Limited receptive area neural classifier for recognition of swallowing sounds using continuous wavelet transform , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[38]  Kuldip K. Paliwal,et al.  Speech Coding and Synthesis , 1995 .

[39]  R. H. Mills,et al.  Using cervical auscultation in the clinical dysphagia examination in long-term care , 2004, Dysphagia.

[40]  Paula Leslie,et al.  Radiation Dose in Videofluoroscopic Swallow Studies , 2006, Dysphagia.

[41]  A. Rademaker,et al.  Changes in pharyngeal dimensions effected by chin tuck. , 1993, Archives of Physical Medicine and Rehabilitation.

[42]  J. Logemann,et al.  Manual for the videofluorographic study of swallowing , 1986 .

[43]  Tom Chau,et al.  Vocalization removal for improved automatic segmentation of dual-axis swallowing accelerometry signals. , 2010, Medical engineering & physics.

[44]  Bonnie Martin-Harris,et al.  Clinical Utility of the Modified Barium Swallow , 2000, Dysphagia.

[45]  Tom Chau,et al.  Automatic discrimination between safe and unsafe swallowing using a reputation-based classifier , 2011, Biomedical engineering online.

[46]  J. Christie,et al.  Express Your LOV: An Engineered Flavoprotein as a Reporter for Protein Expression and Purification , 2012, PloS one.

[47]  J. Rosenbek,et al.  Sensitivity and specificity of clinical/bedside examination signs for detecting aspiration in adults subsequent to stroke. , 2001, Journal of communication disorders.

[48]  P J Kahrilas,et al.  AGA technical review on management of oropharyngeal dysphagia. , 1999, Gastroenterology.

[49]  Martien Limburg,et al.  Bedside screening tests vs. videofluoroscopy or fibreoptic endoscopic evaluation of swallowing to detect dysphagia in patients with neurological disorders: systematic review. , 2009, Journal of advanced nursing.

[50]  Yong Man Ro,et al.  Mass type-specific sparse representation for mass classification in computer-aided detection on mammograms , 2013, Biomedical engineering online.

[51]  Tom Chau,et al.  A Method for Removal of Low Frequency Components Associated with Head Movements from Dual-Axis Swallowing Accelerometry Signals , 2012, PloS one.

[52]  J. Logemann,et al.  A Screening Procedure for Oropharyngeal Dysphagia , 1999, Dysphagia.

[53]  James Chang,et al.  Diagnostic Accuracy of Bedside Swallow Evaluation Versus Videofluoroscopy to Assess Dysphagia in Individuals With Tetraplegia , 2012, PM & R : the journal of injury, function, and rehabilitation.

[54]  C. Turkelson,et al.  Prevention of Pneumonia in Elderly Stroke Patients by Systematic Diagnosis and Treatment of Dysphagia: An Evidence-Based Comprehensive Analysis of the Literature , 2001, Dysphagia.

[55]  Paul Finn,et al.  Reliability and validity of cervical auscultation: A controlled comparison using videofluoroscopy , 2007, Dysphagia (New York. Print).

[56]  Susan E. Langmore,et al.  Endoscopic and Videofluoroscopic Evaluations of Swallowing and Aspiration , 1991, The Annals of otology, rhinology, and laryngology.

[57]  Zahra Moussavi,et al.  Classification of normal and dysphagic swallows by acoustical means , 2004, IEEE Transactions on Biomedical Engineering.

[58]  Susan E. Langmore,et al.  Fiberoptic endoscopic examination of swallowing safety: A new procedure , 2006, Dysphagia.

[59]  Michael R. Neuman,et al.  Recognition of Swallowing Sounds Using Time-Frequency Decomposition and Limited Receptive Area Neural Classifier , 2008, SGAI Conf..

[60]  Tom Chau,et al.  Swallow segmentation with artificial neural networks and multi-sensor fusion. , 2009, Medical engineering & physics.