• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.101-102
• /
• 2007

Heart diseases are critical and should be detected as soon as possible. A stethoscope is a simple device to find cardiac disorder but requires keen experiences in heart sounds. We evaluate a cardiac disorder classifier by using heart sounds recorded by a digital wireless stethoscope developed in this work. The classifier uses hidden Markov models with circular state transition to model the heart sounds. We train the classifier using two kinds of data: One recorded by using our stethoscope and the other sampled from a clean heart sound database. In classification experiments using 165 sound clips, the classifier shows the classification accuracy of 82% in classifying 6 cardiac disorder categories.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.237-243
• /
• 2014

환자의 흉부에서 들리는 심음은 아날로그청진기를 이용하여 들을 수 있었다. 그러나 심음은 듣는 의사에 따라 다르게 진단한다. 그러므로 오랜 경험과 노하우를 가진 의사들만이 주관적인 판단으로 환자의 이상 유 무를 판단할 수 있다. 본 논문에서는 심음의 심박수를 분석하여 환자의 상태를 진단 할 수 있는 무선디지털 청진 진단시스템에 대해 자세하게 서술한다. 그리고, 이 시스템을 통해 진단되는 심음에 대한 레벨교차율(LCR)과 질병의 관계를 보여준다. 또한, 심박수와 질병에 대해 새로운 개념의 진단시스템 환경을 제시하고 심박수의 레벨교차율은 질병에 따라 중요한 차이를 보여준다.

• Tuberculosis and Respiratory Diseases
• /
• 제86권4호
• /
• pp.251-263
• /
• 2023

The stethoscope has long been used for the examination of patients, but the importance of auscultation has declined due to its several limitations and the development of other diagnostic tools. However, auscultation is still recognized as a primary diagnostic device because it is non-invasive and provides valuable information in real-time. To supplement the limitations of existing stethoscopes, digital stethoscopes with machine learning (ML) algorithms have been developed. Thus, now we can record and share respiratory sounds and artificial intelligence (AI)-assisted auscultation using ML algorithms distinguishes the type of sounds. Recently, the demands for remote care and non-face-to-face treatment diseases requiring isolation such as coronavirus disease 2019 (COVID-19) infection increased. To address these problems, wireless and wearable stethoscopes are being developed with the advances in battery technology and integrated sensors. This review provides the history of the stethoscope and classification of respiratory sounds, describes ML algorithms, and introduces new auscultation methods based on AI-assisted analysis and wireless or wearable stethoscopes.

• 한국통신학회논문지
• /
• 제38B권9호
• /
• pp.722-727
• /
• 2013

동물 의료는 병의 정도나 치료의 필요성에 관계없이 보호자의 의향이 앞서는 어려운 의료행위이다. 특히, 동물치료 중 심장 질환은 필요한 치료법의 결정이나 치료 효과의 확인에 대해서 동물 환자로부터 직접적인 답을 얻기가 어렵다. 그래서 동물 환자의 경우, 심장질환은 증상의 악화로 급변하거나 돌연사 등의 응급사태를 예측하고 그것에 대처하는 것은 거의 불가능하다. 심장 및 몸 안의 질환을 확인하는 1차 진단 방법은 청진이다. CT나 X-ray, 초음파 등의 최첨단 영상장비들을 이용하여 정확하게 측정할 수 있지만 장비가 비싸고, 이를 활용할 수 있는 전문인력이 요구되는 등 경제성으로 인해 2차 진단장비로 활용되어질 뿐 1차 진단을 위한 가장 좋은 진단도구로 여전히 청진기가 이용되어지고 있다. 본 논문에서는 수의사가 귀에 대지 않고 청진음을 분석하고 무선으로 어디서나 진단 할 수 있는 무선디지털 진단시스템에 대해 자세하게 서술하고, 이 시스템을 통해 진단되는 청진음에 대한 레벨교차율(LCR)과 에너지레벨을 통해 질병의 관계에 대해 새로운 개념의 진단시스템 환경을 제시한다.

• 대한의용생체공학회:의공학회지
• /
• 제43권2호
• /
• pp.124-130
• /
• 2022

In this paper, we proposed a portable electronic cardiogram and stethoscope (ECGS) that can simultaneously perform the electrocardiogram (ECG) and auscultation tests to increase the reliability of diagnosis of heart disease. To measure the ECG and heart sound (HS) at the same time, three ECG electrodes and a microphone sensor were combined into a triangular shape with a width of 90 mm and a height of 97 mm that can be held in one hand. In order to prevent skin problems when they contact the patient's skin, a capacitive coupled electrode was selected as the ECG electrode and a silicone material was used in a chest piece with the microphone sensor. For the signals measured from the electrodes and the chest piece, filters were respectively configured to pass only the signals of 0.01-100 Hz and 20-250 Hz, which are frequency bands for ECG and HS. The filtered ECG and HS analog signals were converted into digital signals and transmitted to a PC using wireless communication for monitoring them. The HS could be auscultated simultaneously using an earphone. The monitored ECG had an SNR of about 34 dB and a P-QRS-T waveform is clearly visible. In addition, the HS had an SNR of about 28 dB and both S₁ and S₂ are clearly visible. It is expected that it can aid doctors' inexperience in analyzing the ECG and HS.

• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.