A Novel Approach in Auscultation Technology - New Sensors and Algorithms

Grochala, Dominik; Kajor, Marcin; Kucharski, Dariusz; Iwaniec, Marek; Kańtoch, Eliasz

doi:10.1109/hsi.2018.8431339

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach also allows us to incorporate digital signal processing and implement dedicated algorithms supporting the detection of pathological syndromes and pattern recognition [16]. Therefore, seeking the patterns occurring in the signal, which correspond with real pathologies detected by a physician, is usually crucial in the development of algorithms facilitating an automated diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method of Temporomandibular Joint Hypermobility Diagnosis Based on Signal Analysis

Grochala

Kajor

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

Despite the temporomandibular joint (TMJ) being a well-known anatomical structure its diagnosis may become difficult because physiological sounds accompanying joint movement can falsely indicate pathological symptoms. One example of such a situation is temporomandibular joint hypermobility (TMJH), which still requires comprehensive study. The commonly used official research diagnostic criteria for temporomandibular disorders (RDC/TMD) does not support the recognition of TMJH. Therefore, in this paper the authors propose a novel diagnostic method of TMJH based on the digital time–frequency analysis of sounds generated by TMJ. Forty-seven volunteers were diagnosed using the RDC/TMD questionnaire and auscultated with the Littmann 3200 electronic stethoscope on both sides of the head simultaneously. Recorded TMJ sounds were transferred to the computer via Bluetooth® for numerical analysis. The representation of the signals in the time–frequency domain was computed with the use of the Python Numpy and Matplotlib libraries and short-time Fourier transform. The research reveals characteristic time–frequency features in acoustic signals which can be used to detect TMJH. It is also proved that TMJH is a rare disorder; however, its prevalence at the level of around 4% is still significant.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Method of Temporomandibular Joint Hypermobility Diagnosis Based on Signal Analysis

Grochala

Kajor

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…After each hidden layer, a hyperbolic activation function was used. The approach with neural network resulted in accuracy of 75% [4]. The obtained result seemed reliable however many matrix multiplications discouraged us from using MLP as our final classifier on embedded system.…”

Section: Fourier Transform On Whole Signalmentioning

confidence: 78%

“…While training the Random Forest algorithm we took advantage of scikitlearn framework [8]. The result was 71% accuracy using 5-fold cross validation technique [4]…”

Section: Fourier Transform On Whole Signalmentioning

confidence: 99%

See 1 more Smart Citation

Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

Kucharski¹,

Kajor²,

Grochala³

et al. 2019

Adv. Sci. Technol. Res. J.

Self Cite

View full text Add to dashboard Cite

The auscultation technique has been widely used in medicine as a screening examination for ages. Nowadays, advanced electronics and effective computational methods aim to support the healthcare sector by providing dedicated solutions which help physicians and support diagnostic process. In this paper, we propose a machine learning approach for the analysis of heart sounds. We used the spectral analysis of acoustic signal to calculate feature vectors and tested a set of machine learning approaches to provide the most effective detection of cardiac disorders. Finally, we achieved 91% of sensitivity and 99% of positive predictivity for a designed algorithm based on convolutional neural network.

show abstract

Selected Aspects of Interactive Feature Extraction

Grzegorowski¹

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Novel Approach in Auscultation Technology - New Sensors and Algorithms

Cited by 3 publications

References 7 publications

A Novel Method of Temporomandibular Joint Hypermobility Diagnosis Based on Signal Analysis

A Novel Method of Temporomandibular Joint Hypermobility Diagnosis Based on Signal Analysis

Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

Selected Aspects of Interactive Feature Extraction

Contact Info

Product

Resources

About