Using an Automated Speech Recognition Approach to Differentiate Between Normal and Aspirating Swallowing Sounds Recorded from Digital Cervical Auscultation in Children

Use of machine learning to accurately detect aspirating swallowing sounds in children is an evolving field. Previously reported classifiers for the detection of aspirating swallowing sounds in children have reported sensitivities between 79 and 89%. This study aimed to investigate the accuracy of using an automatic speaker recognition approach to differentiate between normal and aspirating swallowing sounds recorded from digital cervical auscultation in children. We analysed 106 normal swallows from 23 healthy children (median 13 months; 52.1% male) and 18 aspirating swallows from 18 children (median 10.5 months; 61.1% male) who underwent concurrent videofluoroscopic swallow studies with digital cervical auscultation. All swallowing sounds were on thin fluids. A support vector machine classifier with a polynomial kernel was trained on feature vectors that comprised the mean and standard deviation of spectral subband centroids extracted from each swallowing sound in the training set. The trained support vector machine was then used to classify swallowing sounds in the test set. We found high accuracy in the differentiation of aspirating and normal swallowing sounds with 98% overall accuracy. Sensitivity for the detection of aspiration and normal swallowing sounds were 89% and 100%, respectively. There were consistent differences in time, power spectral density and spectral subband centroid features between aspirating and normal swallowing sounds in children. This study provides preliminary research evidence that aspirating and normal swallowing sounds in children can be differentiated accurately using machine learning techniques.

Risk Feeding: An Australian Pediatric Palliative Care Perspective

Purpose

This article explores the challenges of risk feeding from an Australian Paediatric Palliative Care perspective. There is currently limited evidence to guide risk feeding in pediatric clinical practice. Therefore, this article uses evidence from the adult palliative and end-of-life care context (extrapolating to pediatric application), in addition to the authors' clinical experience in supporting children and their families with risk feeding. Recommendations for the clinical management of pediatric risk feeding are discussed, including the suggested focus for families and the interprofessional team along the different phases of the palliative care continuum.

Conclusion

There is currently limited information to guide decision making regarding risk feeding in pediatrics. Overall, in the absence of evidence-based practice guidelines, it is the authors' recommendation that a risk feeding plan is developed in consultation and collaboration with the family, treating physician, and interprofessional team. Further research is required to support guidance for clinicians working in this area.

Prediction of aspiration in dysphagia using logistic regression: oral intake and self-evaluation

OBJECTIVES

Oropharyngeal dysphagia (OD) has a major influence on health in general and health-related quality of life (HR-QoL) in particular. The gold standard assessments for OD, especially for aspiration in OD, are fiberoptic endoscopic evaluation of swallowing (FEES) and videofluoroscopy (VFSS), but not all patients have access to such procedures. Therefore, the current study built a prediction model to forecast aspiration in patients with OD on the basis of common self-evaluation questionnaires and oral intake status.

METHODS

A consecutive series of 111 patients with confirmed diagnosis of OD was measured according to a standardised protocol using the following tools: the Swallowing Quality of Life Questionnaire (SWAL-QOL), the Dysphagia Handicap Index (DHI), two self-report visual analogue scales which measure the Severity and the Impairment of the swallowing problem on everyday social life as experienced by the patient, the Eating Assessment Tool 10 (EAT-10), the Functional Oral Intake Scale (FOIS) and subsequently FEES (the gold standard). Penalised logistic regression was carried out to predict aspiration. The performance of the resulting models was evaluated by constructing receiver operating characteristics (ROC) curves and computing areas under the curve (AUC).

RESULTS

The final model showed an AUC of 0.92, indicating excellent performance.

CONCLUSION

This study shows that it may be possible to accurately predict aspiration in oropharyngeal dysphagia by a non-invasive and non-instrumental assessment protocol including oral intake status and self-report questionnaires on functional health status and HR-QoL.

Current approaches to instrumental assessment of swallowing in children

PURPOSE OF THE REVIEW

This article reviews recent developments in the instrumental assessment of swallowing in children with a specific focus on research published between January 2017 and June 2018.

RECENT FINDINGS

Instrumental swallowing assessments reported in the time period included: videofluoroscopic study of swallowing, digital cervical auscultation, dynamic ultrasound, high-resolution impedance manometry, nasal airflow thermistry and respiratory inductance plethysmography. Several studies were found exploring tools to objectively quantify videofluoroscopic study of swallowing data; swallowing from the mouth through to stomach was addressed including approaches to analysing mastication as well as evaluating oesophageal motility disorders.

SUMMARY

Even though a vast range of instrumentation were studied, lack of clarity on clinical feasibility and objective measures that facilitate medical decision-making in practice mean further research is required to provide guidance on implementation. Promising novel approaches to aid the quantification of swallowing physiology from the mouth, pharynx and through to the oesophagus are emerging.

Diagnostic validity of methods for assessment of swallowing sounds: a systematic review

Introduction

Objective

Methods

Results

Conclusion

Acoustic and Perceptual Profiles of Swallowing Sounds in Children: Normative Data for 4-36 Months from a Cross-Sectional Study Cohort

Limited data on cervical auscultation (CA) sounds during the transitional feeding period of 4-36 months in healthy children exist. This study examined the acoustic and perceptual parameters of swallowing sounds in children aged 4-36 months over a range of food and fluid consistencies. Using CA, swallowing sounds were recorded from a microphone as children ate or drank. Acoustic parameters of duration, peak frequency and peak intensity were determined. Perceptual parameters of swallowing/breath sounds heard pre-, during and post-swallow were rated ('present', 'absent', 'cannot be determined') for each texture. 74 children (35 males; mean age = 17.1 months [SD 10.0]) demonstrated mean swallow durations of <1 s. Increasing age correlated to reduced peak frequency on puree (r = -0.48, 95 % CI -0.66, -0.24). Age correlated to peak amplitude when swallowing puree (r = 0.27, 95 % CI 0.02, 0.49), chewable solids (r = 0.31, 95 % CI 0.02, 0.56) and thin fluids (r = 0.48, 95 % CI 0.27, 0.64). The bolus transit sound was present in all swallows. A majority of children had normal breathing sounds and coordinated swallows. A swallow duration of <1 s and the presence of a quick bolus transit sound with normal breathing sounds were found in healthy children. The normative data reported in this study provide a platform for future comparison to abnormal swallowing sounds in children.