A radial basis classifier for the automatic detection of aspiration in children with dysphagia

Computer-aided screening of aspiration risks in dysphagia with wearable technology: a Systematic Review and meta-analysis on test accuracy

Aspiration caused by dysphagia is a prevalent problem that causes serious health consequences and even death. Traditional diagnostic instruments could induce pain, discomfort, nausea, and radiation exposure. The emergence of wearable technology with computer-aided screening might facilitate continuous or frequent assessments to prompt early and effective management. The objectives of this review are to summarize these systems to identify aspiration risks in dysphagic individuals and inquire about their accuracy. Two authors independently searched electronic databases, including CINAHL, Embase, IEEE Xplore^® Digital Library, PubMed, Scopus, and Web of Science (PROSPERO reference number: CRD42023408960). The risk of bias and applicability were assessed using QUADAS-2. Nine (n = 9) articles applied accelerometers and/or acoustic devices to identify aspiration risks in patients with neurodegenerative problems (e.g., dementia, Alzheimer's disease), neurogenic problems (e.g., stroke, brain injury), in addition to some children with congenital abnormalities, using videofluoroscopic swallowing study (VFSS) or fiberoptic endoscopic evaluation of swallowing (FEES) as the reference standard. All studies employed a traditional machine learning approach with a feature extraction process. Support vector machine (SVM) was the most famous machine learning model used. A meta-analysis was conducted to evaluate the classification accuracy and identify risky swallows. Nevertheless, we decided not to conclude the meta-analysis findings (pooled diagnostic odds ratio: 21.5, 95% CI, 2.7-173.6) because studies had unique methodological characteristics and major differences in the set of parameters/thresholds, in addition to the substantial heterogeneity and variations, with sensitivity levels ranging from 21.7% to 90.0% between studies. Small sample sizes could be a critical problem in existing studies (median = 34.5, range 18-449), especially for machine learning models. Only two out of the nine studies had an optimized model with sensitivity over 90%. There is a need to enlarge the sample size for better generalizability and optimize signal processing, segmentation, feature extraction, classifiers, and their combinations to improve the assessment performance. Systematic Review Registration: (https://www.crd.york.ac.uk/prospero/), identifier (CRD42023408960).

Autonomous Swallow Segment Extraction Using Deep Learning in Neck-Sensor Vibratory Signals From Patients With Dysphagia

Dysphagia occurs secondary to a variety of underlying etiologies and can contribute to increased risk of adverse events such as aspiration pneumonia and premature mortality. Dysphagia is primarily diagnosed and characterized by instrumental swallowing exams such as videofluoroscopic swallowing studies. videofluoroscopic swallowing studies involve the inspection of a series of radiographic images for signs of swallowing dysfunction. Though effective, videofluoroscopic swallowing studies are only available in certain clinical settings and are not always desirable or feasible for certain patients. Because of the limitations of current instrumental swallow exams, research studies have explored the use of acceleration signals collected from neck sensors and demonstrated their potential in providing comparable radiation-free diagnostic value as videofluoroscopic swallowing studies. In this study, we used a hybrid deep convolutional recurrent neural network that can perform multi-level feature extraction (localized and across time) to annotate swallow segments automatically via multi-channel swallowing acceleration signals. In total, we used signals and videofluoroscopic swallowing study images of 3144 swallows from 248 patients with suspected dysphagia. Compared to other deep network variants, our network was superior at detecting swallow segments with an average area under the receiver operating characteristic curve value of 0.82 (95% confidence interval: 0.807-0.841), and was in agreement with up to 90% of the gold standard-labeled segments.

AI-Based Detection of Aspiration for Video-Endoscopy with Visual Aids in Meaningful Frames to Interpret the Model Outcome

Disorders of swallowing often lead to pneumonia when material enters the airways (aspiration). Flexible Endoscopic Evaluation of Swallowing (FEES) plays a key role in the diagnostics of aspiration but is prone to human errors. An AI-based tool could facilitate this process. Recent non-endoscopic/non-radiologic attempts to detect aspiration using machine-learning approaches have led to unsatisfying accuracy and show black-box characteristics. Hence, for clinical users it is difficult to trust in these model decisions. Our aim is to introduce an explainable artificial intelligence (XAI) approach to detect aspiration in FEES. Our approach is to teach the AI about the relevant anatomical structures, such as the vocal cords and the glottis, based on 92 annotated FEES videos. Simultaneously, it is trained to detect boluses that pass the glottis and become aspirated. During testing, the AI successfully recognized the glottis and the vocal cords but could not yet achieve satisfying aspiration detection quality. While detection performance must be optimized, our architecture results in a final model that explains its assessment by locating meaningful frames with relevant aspiration events and by highlighting suspected boluses. In contrast to comparable AI tools, our framework is verifiable and interpretable and, therefore, accountable for clinical users.

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.

Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings

High resolution cervical auscultation is a very promising noninvasive method for dysphagia screening and aspiration detection, as it does not involve the use of harmful ionizing radiation approaches. Automatic extraction of swallowing events in cervical auscultation is a key step for swallowing analysis to be clinically effective. Using time-varying spectral estimation of swallowing signals and deep feed forward neural networks, we propose an automatic segmentation algorithm for swallowing accelerometry and sounds that works directly on the raw swallowing signals in an online fashion. The algorithm was validated qualitatively and quantitatively using the swallowing data collected from 248 patients, yielding over 3000 swallows manually labeled by experienced speech language pathologists. With a detection accuracy that exceeded 95%, the algorithm has shown superior performance in comparison to the existing algorithms and demonstrated its generalizability when tested over 76 completely unseen swallows from a different population. The proposed method is not only of great importance to any subsequent swallowing signal analysis steps, but also provides an evidence that such signals can capture the physiological signature of the swallowing process.

The Association of High Resolution Cervical Auscultation Signal Features With Hyoid Bone Displacement During Swallowing

Recent publications have suggested that high-resolution cervical auscultation (HRCA) signals may provide an alternative non-invasive option for swallowing assessment. However, the relationship between hyoid bone displacement, a key component to safe swallowing, and HRCA signals is not thoroughly understood. Therefore, in this work we investigated the hypothesis that a strong relationship exists between hyoid displacement and HRCA signals. Videofuoroscopy data was collected for 129 swallows, simultaneously with vibratory/acoustic signals. Horizontal, vertical and hypotenuse displacements of the hyoid bone were measured through manual expert analysis of videofluoroscopy images. Our results showed that the vertical displacement of both the anterior and posterior landmarks of the hyoid bone was strongly associated with the Lempel-Ziv complexity of superior-inferior and anterior-posterior vibrations from HRCA signals. Horizontal and hypotenuse displacements of the posterior aspect of the hyoid bone were strongly associated with the standard deviation of swallowing sounds. Medial-Lateral vibrations and patient characteristics such as age, sex, and history of stroke were not significantly associated with the hyoid bone displacement. The results imply that some vibratory/acoustic features extracted from HRCA recordings can provide information about the magnitude and direction of hyoid bone displacement. These results provide additional support for using HRCA as a non-invasive tool to assess physiological aspects of swallowing such as the hyoid bone displacement.

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

Introduction

Objective

Methods

Results

Conclusion

Deep Learning for Classification of Normal Swallows in Adults

Cervical auscultation is a method for assessing swallowing performance. However, its ability to serve as a classification tool for a practical clinical assessment method is not fully understood. In this study, we utilized neural network classification methods in the form of Deep Belief networks in order to classify swallows. We specifically utilized swallows that did not result in clinically significant aspiration and classified them on whether they originated from healthy subjects or unhealthy patients. Dual-axis swallowing vibrations from 1946 discrete swallows were recorded from 55 healthy and 53 unhealthy subjects. The Fourier transforms of both signals were used as inputs to the networks of various sizes. We found that single and multi-layer Deep Belief networks perform nearly identically when analyzing only a single vibration signal. However, multi-layered Deep Belief networks demonstrated approximately a 5% to 10% greater accuracy and sensitivity when both signals were analyzed concurrently, indicating that higher-order relationships between these vibrations are important for classification and assessment.

A hybrid classifier based on nonlinear-PCA and deep belief networks with applications in dysphagia diagnosis

Traditional dysphagia prescreening diagnostic methods require doctors specialists to give patients a total score based on a water swallow test scale. This method is limited by the high dimensionality of the diagnostic elements in the water swallow test scale with heavy workload (Towards each patient, the scale requires the doctors give score for 18 diagnostic elements respectively) as well as the difficulties of extracting and using the diagnostic scale data's non-linear features and hidden expertise information (Even with the scale scores, specific diagnostic conclusions are still given by expert doctors under the expertise). In this paper, a hybrid classifier model based on Nonlinear-Principal Component Analysis (NPCA) and Deep Belief Networks (DBN) is proposed in order to effectively extract the diagnostic scale data's nonlinear features and hidden information and to provide the key scale elements' locating methods towards the diagnostic results (The key scale elements that affect different diagnostic conclusions are given to improve the efficiency and pertinence of diagnosis and reduce the workload of diagnosis). We demonstrate the effectiveness of the proposed method using the frame of 'information entropy theory'. Real dysphagia diagnosis examples from the China-Japanese Friendship Hospital are used to demonstrate applications of the proposed methods. The examples show satisfactory results compared to the traditional classifier.

A statistical analysis of cervical auscultation signals from adults with unsafe airway protection

Background

Aspiration, where food or liquid is allowed to enter the larynx during a swallow, is recognized as the most clinically salient feature of oropharyngeal dysphagia. This event can lead to short-term harm via airway obstruction or more long-term effects such as pneumonia. In order to non-invasively identify this event using high resolution cervical auscultation there is a need to characterize cervical auscultation signals from subjects with dysphagia who aspirate.

Methods

In this study, we collected swallowing sound and vibration data from 76 adults (50 men, 26 women, mean age 62) who underwent a routine videofluoroscopy swallowing examination. The analysis was limited to swallows of liquid with either thin (<5 cps) or viscous (≈300 cps) consistency and was divided into those with deep laryngeal penetration or aspiration (unsafe airway protection), and those with either shallow or no laryngeal penetration (safe airway protection), using a standardized scale. After calculating a selection of time, frequency, and time-frequency features for each swallow, the safe and unsafe categories were compared using Wilcoxon rank-sum statistical tests.

Results

Our analysis found that few of our chosen features varied in magnitude between safe and unsafe swallows with thin swallows demonstrating no statistical variation. We also supported our past findings with regard to the effects of sex and the presence or absence of stroke on cervical ausculation signals, but noticed certain discrepancies with regards to bolus viscosity.

Conclusions

Overall, our results support the necessity of using multiple statistical features concurrently to identify laryngeal penetration of swallowed boluses in future work with high resolution cervical auscultation.

Oropharyngeal dysphagia: manifestations and diagnosis

Swallowing disorders (dysphagia) have been recognized by the WHO as a medical disability associated with increased morbidity, mortality and costs of care. With increasing survival rates and ageing of the population, swallowing disorders and their role in causing pulmonary and nutritional pathologies are becoming exceedingly important. Over the past two decades, the study of oropharyngeal dysphagia has been approached from various disciplines with considerable progress in understanding its pathophysiology. This Review describes the most frequent manifestations of oropharyngeal dysphagia and the clinical as well as instrumental techniques that are available to diagnose patients with dysphagia. However, the clinical value of these diagnostic tests and their sensitivity to predict outcomes is limited. Despite considerable clinical research efforts, conventional diagnostic methods for oropharyngeal dysphagia have limited proven accuracy in predicting aspiration and respiratory disease. We contend that incorporation of measurable objective assessments into clinical diagnosis is needed and might be key in developing novel therapeutic strategies.

Dysphagia Screening: Contributions of Cervical Auscultation Signals and Modern Signal-Processing Techniques

Cervical auscultation is the recording of sounds and vibrations caused by the human body from the throat during swallowing. While traditionally done by a trained clinician with a stethoscope, much work has been put towards developing more sensitive and clinically useful methods to characterize the data obtained with this technique. The eventual goal of the field is to improve the effectiveness of screening algorithms designed to predict the risk that swallowing disorders pose to individual patients' health and safety. This paper provides an overview of these signal processing techniques and summarizes recent advances made with digital transducers in hopes of organizing the highly varied research on cervical auscultation. It investigates where on the body these transducers are placed in order to record a signal as well as the collection of analog and digital filtering techniques used to further improve the signal quality. It also presents the wide array of methods and features used to characterize these signals, ranging from simply counting the number of swallows that occur over a period of time to calculating various descriptive features in the time, frequency, and phase space domains. Finally, this paper presents the algorithms that have been used to classify this data into 'normal' and 'abnormal' categories. Both linear as well as non-linear techniques are presented in this regard.

Physiological acoustic sensing based on accelerometers: a survey for mobile healthcare

This paper reviews the applications of accelerometers on the detection of physiological acoustic signals such as heart sounds, respiratory sounds, and gastrointestinal sounds. These acoustic signals contain a rich reservoir of vital physiological and pathological information. Accelerometer-based systems enable continuous, mobile, low-cost, and unobtrusive monitoring of physiological acoustic signals and thus can play significant roles in the emerging mobile healthcare. In this review, we first briefly explain the operation principle of accelerometers and specifications that are important for mobile healthcare. Applications of accelerometer-based monitoring systems are then presented. Next, we review a variety of accelerometers which have been reported in literatures for physiological acoustic sensing, including both commercial products and research prototypes. Finally, we discuss some challenges and our vision for future development.

Baseline characteristics of cervical auscultation signals during various head maneuvers

Cervical auscultation (CA) is an emerging method of assessing swallowing disorders that is both non-invasive and inexpensive. This technique utilizes microphones to detect acoustic sounds produced by swallowing activity and characterize its behavior. Though some properties of swallowing sounds are known, there is still a need for a complete understanding of the baseline characteristics of cervical auscultation signals as well as how they change due to the patient's head motion, age, and sex. In order to examine these parameters, data was collected from 56 healthy adult participants that performed six different head movement tasks without swallowing. After preprocessing the signal, features were extracted. Dependent variables were time domain, frequency domain and time-frequency domain features. Statistical tests showed that only the skewness and peak frequency were not statistically different for all tasks. The peak frequency results indicate that head movement does not significantly affect the microphone signal, and that it is unnecessary to filter out the lowest frequency components. No sex differences were observed in the extracted features, but several features exhibited age dependence.

Characteristics of the swallowing sounds recorded in the ear, nose and on trachea

The various malfunctions and difficulties of the swallowing mechanism necessitate various diagnostic techniques to address those problems. Swallowing sounds recorded from the trachea have been suggested as a noninvasive method of swallowing assessment. However, acquiring signals from the trachea can be difficult for those with loose skin. The objective of this pilot study was to explore the viability of using the ear and nose as alternative recording locations for recording swallowing sounds. We recorded the swallowing and breathing sounds of five healthy young individuals from the ear, nose and trachea, simultaneously. We computed time-frequency features and compared them for the different locations of recording. The features included the peak and the maximum frequencies of the power spectrum density, average power at different frequency bands and the wavelet coefficients. The average power calculated over the 4 octave bands between 150 and 2,400 Hz showed a consistent trend with less than 20 dB difference for the breath sounds of all the recording locations. Thus, analyzing breath sounds recorded from the ear and nose for the purpose of aspiration detection would give similar results to those from tracheal recordings; thus, ear and nose recording may be a viable alternative when tracheal recording is not possible.

Quantitative classification of pediatric swallowing through accelerometry

BACKGROUND

Dysphagia or swallowing disorder negatively impacts a child's health and development. The gold standard of dysphagia detection is videofluoroscopy which exposes the child to ionizing radiation, and requires specialized clinical expertise and expensive institutionally-based equipment, precluding day-to-day and repeated assessment of fluctuating swallowing function. Swallowing accelerometry is the non-invasive measurement of cervical vibrations during swallowing and may provide a portable and cost-effective bedside alternative. In particular, dual-axis swallowing accelerometry has demonstrated screening potential in older persons with neurogenic dysphagia, but the technique has not been evaluated in the pediatric population.

METHODS

In this study, dual-axis accelerometric signals were collected simultaneous to videofluoroscopic records from 29 pediatric participants (age 6.8 ± 4.8 years; 20 males) previously diagnosed with neurogenic dysphagia. Participants swallowed 3-5 sips of barium-coated boluses of different consistencies (normally, from thick puree to thin liquid) by spoon or bottle. Videofluoroscopic records were reviewed retrospectively by a clinical expert to extract swallow timings and ratings. The dual-axis acceleration signals corresponding to each identified swallow were pre-processed, segmented and trimmed prior to feature extraction from time, frequency, time-frequency and information theoretic domains. Feature space dimensionality was reduced via principal components.

RESULTS

Using 8-fold cross-validation, 16-17 dimensions and a support vector machine classifier with an RBF kernel, an adjusted accuracy of 89.6% ± 0.9 was achieved for the discrimination between swallows with and with out airway entry.

CONCLUSIONS

Our results suggest that dual-axis accelerometry has merit in the non-invasive detection of unsafe swallows in children and deserves further consideration as a pediatric medical device.

A method for removal of low frequency components associated with head movements from dual-axis swallowing accelerometry signals

Head movements can greatly affect swallowing accelerometry signals. In this paper, we implement a spline-based approach to remove low frequency components associated with these motions. Our approach was tested using both synthetic and real data. Synthetic signals were used to perform a comparative analysis of the spline-based approach with other similar techniques. Real data, obtained data from 408 healthy participants during various swallowing tasks, was used to analyze the processing accuracy with and without the spline-based head motions removal scheme. Specifically, we analyzed the segmentation accuracy and the effects of the scheme on statistical properties of these signals, as measured by the scaling analysis. The results of the numerical analysis showed that the spline-based technique achieves a superior performance in comparison to other existing techniques. Additionally, when applied to real data, we improved the accuracy of the segmentation process by achieving a 27% drop in the number of false negatives and a 30% drop in the number of false positives. Furthermore, the anthropometric trends in the statistical properties of these signals remained unaltered as shown by the scaling analysis, but the strength of statistical persistence was significantly reduced. These results clearly indicate that any future medical devices based on swallowing accelerometry signals should remove head motions from these signals in order to increase segmentation accuracy.

Perfil de pacientes com paralisia cerebral em uso de gastrostomia e efeito nos cuidadores

OBJETIVO: caracterizar o perfil de pacientes com paralisia cerebral em uso de gastrostomia e verificar o efeito que tal procedimento ocasiona nos cuidadores. MÉTODO: foi realizado estudo transversal de caráter qualitativo e quantitativo. A pesquisa foi feita com pacientes do Hospital da Criança Santo Antônio - Complexo Hospitalar Santa Casa que tivessem diagnóstico médico de Paralisia Cerebral (PC) em uso de gastrostomia. Foi aplicado um questionário aos cuidadores contendo questões quantitativas, qualitativas e dados sobre a caracterização da amostra. RESULTADOS: houve predominância de renda mensal de até dois salários mínimos, e uma configuração familiar caracterizada pelo pai trabalhar e a mãe não atuar no mercado de trabalho. Dentre os motivos para a indicação do procedimento, a dificuldade de deglutição esteve presente entre todos os sujeitos, seguido das pneumonias de repetição e baixo peso. Observa-se um grande número de pacientes que fizeram uso de sonda antes da gastrostomia, com tempo de permanência acima de um mês. Destacam-se os principais benefícios observados com a colocação da gastrostomia: ganho de peso, diminuição dos problemas respiratórios e redução de internações. A partir dos relatos dos cuidadores percebe-se a ocorrência de sentimentos como de medo do desconhecido, resistência e aceitação, dificuldades e benefícios. CONCLUSÃO: observa-se que problemas de alimentação são frequentemente encontrados como indicação para colocação de gastrostomia em crianças com PC. Os cuidadores sentem medo quanto à impossibilidade de alimentar a criança pela via oral. Porém, após a cirurgia, grande parte deles relatou benefícios, como por exemplo, ganho de peso e redução das internações.

ASSESSMENT AND CLASSIFICATION OF MECHANICAL STRENGTH COMPONENTS OF HUMAN FEMUR TRABECULAR BONE USING DIGITAL IMAGE PROCESSING AND NEURAL NETWORKS

In this work, the assessment of the mechanical strength of human femur trabecular bone and its classification into normal or abnormal are carried out using digital image processing and neural networks. The mechanical strength components of femur trabeculae, such as primary compressive (PC), primary tensile (PT), secondary tensile (ST), and Ward's triangle (WT), are delineated by the semiautomatic image processing procedure from the planar radiographic images (N = 90) of subjects that are acquired under controlled clinical settings. Parameters such as apparent mineralization and total area of the individual mechanical strength components are calculated for normal and abnormal samples. The data are trained with neural networks and validated. The classifications are carried out using feed-forward neural networks trained with the standard backpropagation algorithm. The abnormal and normal outputs are validated by sensitivity and specificity measurements. The observation shows that the investigation of bone mechanical strength at the various strength components is useful in classifying normal and abnormal human femur trabeculae from conventional radiographs. Furthermore, the results confirm the effectiveness of the neural network–based classification of femur trabeculae into normal and abnormal conditions. The sensitivity and specificity are found to be 100% and 80%, respectively. In this paper, the methodology, data collection procedures, and neural network–based analysis and results are discussed in detail.

Automatic discrimination between safe and unsafe swallowing using a reputation-based classifier

Background

Swallowing accelerometry has been suggested as a potential non-invasive tool for bedside dysphagia screening. Various vibratory signal features and complementary measurement modalities have been put forth in the literature for the potential discrimination between safe and unsafe swallowing. To date, automatic classification of swallowing accelerometry has exclusively involved a single-axis of vibration although a second axis is known to contain additional information about the nature of the swallow. Furthermore, the only published attempt at automatic classification in adult patients has been based on a small sample of swallowing vibrations.

Methods

In this paper, a large corpus of dual-axis accelerometric signals were collected from 30 older adults (aged 65.47 ± 13.4 years, 15 male) referred to videofluoroscopic examination on the suspicion of dysphagia. We invoked a reputation-based classifier combination to automatically categorize the dual-axis accelerometric signals into safe and unsafe swallows, as labeled via videofluoroscopic review. From these participants, a total of 224 swallowing samples were obtained, 164 of which were labeled as unsafe swallows (swallows where the bolus entered the airway) and 60 as safe swallows. Three separate support vector machine (SVM) classifiers and eight different features were selected for classification.

Results

With selected time, frequency and information theoretic features, the reputation-based algorithm distinguished between safe and unsafe swallowing with promising accuracy (80.48 ± 5.0%), high sensitivity (97.1 ± 2%) and modest specificity (64 ± 8.8%). Interpretation of the most discriminatory features revealed that in general, unsafe swallows had lower mean vibration amplitude and faster autocorrelation decay, suggestive of decreased hyoid excursion and compromised coordination, respectively. Further, owing to its performance-based weighting of component classifiers, the static reputation-based algorithm outperformed the democratic majority voting algorithm on this clinical data set.

Conclusion

Given its computational efficiency and high sensitivity, reputation-based classification of dual-axis accelerometry ought to be considered in future developments of a point-of-care swallow assessment where clinical informatics are desired.

Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals

BACKGROUND

Dysphagia assessment involves diagnosis of individual swallows in terms of the depth of airway invasion and degree of bolus clearance. The videofluoroscopic swallowing study is the current gold standard for dysphagia assessment but is time-consuming and costly. An ideal alternative would be an automated abnormal swallow detection methodology based on non-invasive signals.

OBJECTIVE

Building upon promising results from single-axis cervical accelerometry, the objective of this study was to investigate the combination of dual-axis accelerometry and nasal airflow for classification of healthy and abnormal swallows in a patient population with dysphagia.

METHODS

Signals were acquired from 24 adult patients with dysphagia (17.8±8.8 swallows per patient). The abnormality of each swallow was quantified using 4-point videofluoroscopic rating scales for its depth of airway invasion, bolus clearance from the valleculae, and bolus clearance from the pyriform sinuses. For each scale, we endeavored to automatically discriminate between the 2 extreme ratings, yielding 3 separate binary classification problems. Various time, frequency, and time-frequency domain features were extracted. A genetic algorithm was deployed for feature selection. Smoothed bootstrapping was utilized to balance the two classes and provide sufficient training data for a multidimensional feature space.

RESULTS

A Euclidean linear discriminant classifier resulted in a mean adjusted accuracy of 74.7% for the depth of airway invasion rating, whereas Mahalanobis linear discriminant classifiers yielded mean adjusted accuracies of 83.7% and 84.2% for bolus clearance from the valleculae and pyriform sinuses, respectively. The bolus clearance from the valleculae problem required the lowest feature space dimensionality. Wavelet features were found to be most discriminatory.

CONCLUSIONS

This exploratory study confirms that dual-axis accelerometry and nasal airflow signals can be used to discriminate healthy and abnormal swallows from patients with dysphagia. The fact that features from all signal channels contributed discriminatory information suggests that multi-sensor fusion is promising in abnormal swallow detection.

Effects of liquid stimuli on dual-axis swallowing accelerometry signals in a healthy population

Background

Dual-axis swallowing accelerometry has recently been proposed as a tool for non-invasive analysis of swallowing function. Although swallowing is known to be physiologically modifiable by the type of food or liquid (i.e., stimuli), the effects of stimuli on dual-axis accelerometry signals have never been thoroughly investigated. Thus, the objective of this study was to investigate stimulus effects on dual-axis accelerometry signal characteristics. Signals were acquired from 17 healthy participants while swallowing 4 different stimuli: water, nectar-thick and honey-thick apple juices, and a thin-liquid barium suspension. Two swallowing tasks were examined: discrete and sequential. A variety of features were extracted in the time and time-frequency domains after swallow segmentation and pre-processing. A separate Friedman test was conducted for each feature and for each swallowing task.

Results

Significant main stimulus effects were found on 6 out of 30 features for the discrete task and on 5 out of 30 features for the sequential task. Analysis of the features with significant stimulus effects suggested that the changes in the signals revealed slower and more pronounced swallowing patterns with increasing bolus viscosity.

Conclusions

We conclude that stimulus type does affect specific characteristics of dual-axis swallowing accelerometry signals, suggesting that associated clinical screening protocols may need to be stimulus specific.

Prediction of forced expiratory volume in pulmonary function test using radial basis neural networks and k-means clustering

In this work, prediction of forced expiratory volume in pulmonary function test, carried out using spirometry and neural networks is presented. The pulmonary function data were recorded from volunteers using commercial available flow volume spirometer in standard acquisition protocol. The Radial Basis Function neural networks were used to predict forced expiratory volume in 1 s (FEV1) from the recorded flow volume curves. The optimal centres of the hidden layer of radial basis function were determined by k-means clustering algorithm. The performance of the neural network model was evaluated by computing their prediction error statistics of average value, standard deviation, root mean square and their correlation with the true data for normal, restrictive and obstructive cases. Results show that the adopted neural networks are capable of predicting FEV1 in both normal and abnormal cases. Prediction accuracy was more in obstructive abnormality when compared to restrictive cases. It appears that this method of assessment is useful in diagnosing the pulmonary abnormalities with incomplete data and data with poor recording.

Swallow segmentation with artificial neural networks and multi-sensor fusion

Swallow segmentation is a critical precursory step to the analysis of swallowing signal characteristics. In an effort to automatically segment swallows, we investigated artificial neural networks (ANN) with information from cervical dual-axis accelerometry, submental MMG, and nasal airflow. Our objectives were (1) to investigate the relationship between segmentation performance and the number of signal sources and (2) to identify the signals or signal combinations most useful for swallow segmentation. Signals were acquired from 17 healthy adults in both discrete and continuous swallowing tasks using five stimuli. Training and test feature vectors were constructed with variances from single or multiple signals, estimated within 200 ms moving windows with 50% overlap. Corresponding binary target labels (swallow or non-swallow) were derived by manual segmentation. A separate 3-layer ANN was trained for each participant-signal combination, and all possible signal combinations were investigated. As more signal sources were included, segmentation performance improved in terms of sensitivity, specificity, accuracy, and adjusted accuracy. The combination of all four signal sources achieved the highest mean accuracy and adjusted accuracy of 88.5% and 89.6%, respectively. A-P accelerometry proved to be the most discriminatory source, while the inclusion of MMG or nasal airflow resulted in the least performance improvement. These findings suggest that an ANN, multi-sensor fusion approach to segmentation is worthy of further investigation in swallowing studies.

Assessment and classification of normal and restrictive respiratory conditions through pulmonary function test and neural network

In this work, an attempt to classify respiratory abnormality using a pulmonary function test and neural networks is reported. The flow - volume curves generated by spirometric pulmonary function tests were recorded from subjects under study. The pressure and resistance parameters were derived using theoretical approximation of the activation function representing the pressure - volume relationship of the lung. The pressure - time and resistance - expiration volume curves were obtained during maximum expiration. The derived values together with spirometric data were used for classification of normal and restrictive abnormality using feed forward network. Results demonstrate the ability of the proposed method in identifying and classifying pulmonary function data into normal and restrictive cases. The validity of the results was confirmed by measuring accuracy (92%), sensitivity (92.3%), specificity (91.6%) and adjusted accuracy (91.95%). As spirometric evaluation of human respiratory functions are essential components in primary care settings, the study carried out seems to be clinically relevant.

Time and time-frequency characterization of dual-axis swallowing accelerometry signals

Single-axis swallowing accelerometry has shown potential as a non-invasive clinical swallowing assessment tool. Previous swallowing accelerometry research has focused exclusively on the anterior-posterior vibration detected on the surface of the neck. However, hyolaryngeal motion during pharyngeal swallowing occurs in both the anterior-posterior and superior-inferior directions, suggesting that dual-axis accelerometry may be worthy of investigation. With this motivation, the present paper provides a characterization of dual-axis swallowing accelerometry signals from healthy adults in the time and time-frequency domains. Time-domain analysis revealed that signals in the two axes exhibited different probability density functions, and minimal cross-correlation and mutual information. Time-frequency analysis highlighted inter-axis dissimilarities in the scalograms, pseudo-spectra and temporal evolution of low- and high-frequency content. Therefore, it was concluded that the two axes contain different information about swallowing and that the superior-inferior axis should be further investigated in future swallowing accelerometry studies.

Assessment and classification of mechanical strength components of human femur trabecular bone using texture analysis and neural network

In this work the mechanical strength components of human femur trabecular bone are analyzed and classified using planar radiographic images and neural network. The mechanical strength regions such as Primary Compressive, Primary Tensile, Secondary Tensile and Ward Triangle in femur trabecular bone images (N = 100) are delineated by semi-automatic image processing procedure. First and higher order texture parameters and parameters such as apparent mineralization and total area associated with the strength regions are derived for normal and abnormal images. The statistically derived significant parameters corresponding to the primary strength regions are fed to the neural network for training and validation. The classifications are carried out using feed forward network that is trained with standard back propagation algorithm. Results demonstrate that the apparent mineralization of normal samples is always high as (71%) compared to abnormal samples (64%). Entropy shows a high value (7.3) for normal samples and variation between the mean intensity and apparent mineralization for the primary strength zone is statistically significant (p < 0.0005). The classified outputs are validated by sensitivity and specificity measurements and are found to be 66.66% and 80% respectively. Further it appears that it is possible to differentiate normal and abnormal samples from the conventional radiographic images. As trabecular architecture in the human femur is an important factor contributing to bone strength, the procedure adopted here could be a useful supplement to the clinical observations for bone loss and fracture risk.

Synergistic control of forearm based on accelerometer data and artificial neural networks

In the present study, we modeled a reaching task as a two-link mechanism. The upper arm and forearm motion trajectories during vertical arm movements were estimated from the measured angular accelerations with dual-axis accelerometers. A data set of reaching synergies from able-bodied individuals was used to train a radial basis function artificial neural network with upper arm/forearm tangential angular accelerations. The trained radial basis function artificial neural network for the specific movements predicted forearm motion from new upper arm trajectories with high correlation (mean, 0.9149-0.941). For all other movements, prediction was low (range, 0.0316-0.8302). Results suggest that the proposed algorithm is successful in generalization over similar motions and subjects. Such networks may be used as a high-level controller that could predict forearm kinematics from voluntary movements of the upper arm. This methodology is suitable for restoring the upper limb functions of individuals with motor disabilities of the forearm, but not of the upper arm. The developed control paradigm is applicable to upper-limb orthotic systems employing functional electrical stimulation. The proposed approach is of great significance particularly for humans with spinal cord injuries in a free-living environment. The implication of a measurement system with dual-axis accelerometers, developed for this study, is further seen in the evaluation of movement during the course of rehabilitation. For this purpose, training-related changes in synergies apparent from movement kinematics during rehabilitation would characterize the extent and the course of recovery. As such, a simple system using this methodology is of particular importance for stroke patients. The results underlie the important issue of upper-limb coordination.

Assessment of Swallowing Sounds by Digital Cervical Auscultation in Children

Objectives:

There is a lack of studies regarding swallowing sounds in children 3 to 11 years of age. This study aimed to assess swallowing sounds by digital cervical auscultation in children of this age group without symptoms of oropharyngeal dysphagia.

Methods:

Digital cervical auscultation was performed in 118 subjects by use of a piezoelectric microphone. The children swallowed 5 mL of liquid and yogurt. The components of perceptual acoustic analysis were discrete initial signal (DIS), main signal of swallowing sound (MS), discrete final signal (DFS), and expiratory return (ER). Duration in seconds was the objective parameter of the swallowing sound signal analyzed.

Results:

Fifty-six boys and 62 girls were evaluated at a mean (±SD) age of 6.9 ± 2.03 years. A complete DIS-MS-DFS-ER swallowing sequence was found in 60% of the children. There was no significant difference in swallowing sound duration between both food consistencies (p = .189) or between genders either for liquid (p = .327) or yogurt (p = .792). There was no correlation between age and duration of the swallowing sound for liquid or yogurt.

Conclusions:

We concluded that digital cervical auscultation was able to provide objective information about the swallowing process that could contribute to methodological standardization in children.