Heart sound and electrocardiogram recording devices for telemedicine environments

Automatic Evaluation of Heart Condition According to the Sounds Emitted and Implementing Six Classification Methods

The main cause of death in Mexico and the world is heart disease, and it will continue to lead the death rate in the next decade according to data from the World Health Organization (WHO) and the National Institute of Statistics and Geography (INEGI). Therefore, the objective of this work is to implement, compare and evaluate machine learning algorithms that are capable of classifying normal and abnormal heart sounds. Three different sounds were analyzed in this study; normal heart sounds, heart murmur sounds and extra systolic sounds, which were labeled as healthy sounds (normal sounds) and unhealthy sounds (murmur and extra systolic sounds). From these sounds, fifty-two features were calculated to create a numerical dataset; thirty-six statistical features, eight Linear Predictive Coding (LPC) coefficients and eight Cepstral Frequency-Mel Coefficients (MFCC). From this dataset two more were created; one normalized and one standardized. These datasets were analyzed with six classifiers: k-Nearest Neighbors, Naive Bayes, Decision Trees, Logistic Regression, Support Vector Machine and Artificial Neural Networks, all of them were evaluated with six metrics: accuracy, specificity, sensitivity, ROC curve, precision and F1-score, respectively. The performances of all the models were statistically significant, but the models that performed best for this problem were logistic regression for the standardized data set, with a specificity of 0.7500 and a ROC curve of 0.8405, logistic regression for the normalized data set, with a specificity of 0.7083 and a ROC curve of 0.8407, and Support Vector Machine with a lineal kernel for the non-normalized data; with a specificity of 0.6842 and a ROC curve of 0.7703. Both of these metrics are of utmost importance in evaluating the performance of computer-assisted diagnostic systems.

Desarrollo de una aplicación para configurar el teléfono inteligente como fonendoscopio para profesionales sanitarios con deficiencias auditivas

Introducción y objetivos. La hipoacusia supone un severo hándicap para cualquier profesional cuya actividad se base en el reconocimiento de sonidos. En el caso de profesionales sanitarios, la auscultación constituye una actividad rutinaria y el padecimiento de hipoacusia la limita en grado variable en función de la severidad de la misma. Aquellos profesionales sanitarios que por la severidad de su hipoacusia necesitan del uso de audífonos ven dificultadas las rutinas basadas en el uso del fonendoscopio. El objetivo del presente trabajo es describir el proceso llevado a cabo para desarrollar una aplicación para smartphones, que permita la reproducción en tiempo real, el registro y el análisis de sonidos para facilitar la labor de profesionales sanitarios con hipoacusia. Métodos. Hemos recogido somatosonidos cardiacos, pulmonares y abdominales de sujetos sanos y patológicos a fin de caracterizarles frecuencialmente. Posteriormente, la aplicación ha sido diseñada con el objetivo de facilitar la labor diagnóstica del profesional sanitario hipoacúsico, teniendo en cuenta la caracterización anterior para optimizar la escucha y el análisis de sonidos cardiacos, pulmonares y abdominales. Además, con el objetivo de maximizar el número de dispositivos compatibles, ha sido desarrollada para el sistema operativo Android, el más extendido del mercado. Resultados. Hemos desarrollado una App. para smartphones (a la que hemos llamado STETHOSCOPE) basados en Android que configura el teléfono como un fonendoscopio recogiendo el somatosonido a través de su micrófono (siendo posible utilizar exclusivamente el micrófono interno del smartphone o bien micrófonos externos de alta calidad a través de su conector JACK), procesando la señal hasta enviarla finalmente por Bluetooth a los audífonos del profesional hipoacúsico. Esta aplicación permite grabar y representar gráficamente sonidos cardiacos, pulmonares y abdominales en dispositivos Android y almacenarlos en formato WAV, según las recomendaciones del Instituto de Ingeniería Eléctrica y Electrónica (Institute of Electrical and Electronics Engineers, IEEE), utilizando una codificación FLOAT de 32 bits sin compresión posibilitando su archivo, comparación o compartición con otros profesionales. Conclusiones. En este estudio presentamos una aplicación destinada a utilizar el smartphone como fonendoscopio, haciendo llegar el sonido captado a la ayuda auditiva (por vía inalámbrica) del profesional sanitario hipoacúsico que lo precise.

Wearable, multimodal, vitals acquisition unit for intelligent field triage

In this Letter, the authors describe the characterisation design and development of the authors' wearable, multimodal vitals acquisition unit for intelligent field triage. The unit is able to record the standard electrocardiogram, blood oxygen and body temperature parameters and also has the unique capability to record up to eight custom designed acoustic streams for heart and lung sound auscultation. These acquisition channels are highly synchronised to fully maintain the time correlation of the signals. The unit is a key component enabling systematic and intelligent field triage to continuously acquire vital patient information. With the realised unit a novel data-set with highly synchronised vital signs was recorded. The new data-set may be used for algorithm design in vital sign analysis or decision making. The monitoring unit is the only known body worn system that records standard emergency parameters plus eight multi-channel auscultatory streams and stores the recordings and wirelessly transmits them to mobile response teams.

The impact of various backboard configurations on compression stiffness in a manikin study of CPR

When performing cardiopulmonary resuscitation (CPR) it is important that adequate back support is given to the patient in order to allow the medical practitioner to produce an appropriate technique during chest compression (CC). The current study investigates how backboard configuration (i.e., orientation and size) impact compression stiffness during CPR using a torso CPR training manikin. The effect of backboard size on CC performance during CPR was found to be significant with the 94.8% larger backboard producing an increase in compression stiffness of as much as 62.7% relative to the smaller backboard. The impact of backboard orientation was also found to be important with a longitudinal orientation producing an increase in compression stiffness of as much as 60.3% relative to a latitudinal orientation. Backboard configuration should be considered by clinicians when trying to achieve optimal CC performance during CPR in hospital settings.

Autonomous auscultation of the human heart employing a precordial electro-phonocardiogram and ensemble empirical mode decomposition

The research presented in this paper serves to provide a tool to autonomously screen for cardiovascular disease in the rural areas of Africa. With this tool, cardiovascular disease can potentially be detected in its initial stages, which is essential for effective treatment. The autonomous auscultation system proposed here utilizes recorded heart sounds and electrocardiogram signals to automatically distinguish between normal and abnormal heart conditions. Patients that are identified as abnormal by the system can then be referred to a specialist consultant, which will save a lot of unnecessary referrals. In this study, heart sound and electrocardiogram signals were recorded with the prototype precordial electro-phonocardiogram device, as part of a clinical study to screen patients for cardiovascular disease. These volunteers consisted of 28 patients with a diagnosed cardiovascular disease and, for control purposes, 34 persons diagnosed with healthy hearts. The proposed system employs wavelets to first denoise the recorded signals, which is then followed by segmentation of heart sounds. Frequency spectrum information was extracted as diagnostic features from the heart sounds by means of ensemble empirical mode decomposition and auto regressive modelling. The respective features were then classified with an ensemble artificial neural network. The performance of the autonomous auscultation system used in concert with the precordial electro-phonocardiogram prototype showed a sensitivity of 82% and a specificity of 88%. These results demonstrate the potential benefit of the precordial electro-phonocardiogram device and the developed autonomous auscultation software as a screening tool in a rural healthcare environment where large numbers of patients are often cared for by a small number of inexperienced medical personnel.