Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

Kucharski, Dariusz; Kajor, Marcin; Grochala, Dominik; Iwaniec, Joanna

doi:10.12913/22998624/108447

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The signal analysis proposed in this paper takes advantage of spectrogram which allows to visually evaluate the acoustic syndromes of TMJH, which is more objective and evident. Moreover, such a representation of sound constitutes 2D signal feature vector which can be fed into a convolutional neural net classifier capable of supporting automatic diagnosis [18].…”

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

“…This application combines Active Sonar with Passive Acoustic Analysis 119 . In Reference 120, the spectral analysis of acoustic signals was used to measure feature vectors and was validated using a series of machine learning methods to provide the most efficient identification of cardiac valve defects based on heart sounds, and this study proved that the CNN model is an effective method for increasing efficiency. A new method of automated sound processing based on neural networks has been introduced in a framework that captures respiratory sounds using an electronic stethoscope.…”

Section: Acoustic Aimentioning

confidence: 92%

Securing AI‐based healthcare systems using blockchain technology: A state‐of‐the‐art systematic literature review and future research directions

Shinde,

Patil,

Kotecha

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Healthcare institutions are progressively integrating artificial intelligence (AI) into their operations. The extraordinary potential of AI is restricted by insufficient medical data for AI model training and adversarial attacks wherein attackers perturb the dataset by adding some noise to it, which leads to the malfunctioning of the AI models, and a lack of trust caused by the opaque operational approach it employs. This Systematic Literature Review (SLR) is a state‐of‐the‐art survey of the research on blockchain technology for securing AI‐integrated healthcare applications. The most relevant articles from the Scopus and Web of Science (WoS) databases were identified using the PRISMA model. Most of the existing literature is about protecting the healthcare data used by AI‐based healthcare systems using blockchain technology, but the modality of data (text, images, audio, and sound) was not specifically mentioned. Information on protecting the training phase and model deployment for AI‐based healthcare systems considering the variations in feature extraction based on the modality of data was also not clearly specified. Hence, the three subfields of AI, namely, natural language processing (NLP), computer vision, and acoustic AI are further studied to identify security loopholes in its implementation pipeline. The three phases, namely the dataset, the training phase, and the trained models need to be protected from adversaries to avoid malfunctioning of the deployed AI models. The nature of the data processed by NLP, computer vision, and acoustic AI, underlying deep neural network (DNN) architectures, the complexity of attacks, and the perceivability of attacks by humans are analyzed to identify the need for security. A blockchain solution for AI‐based healthcare systems is synthesized based on the findings that have demonstrated the distinctive technological features of blockchains. It offers a solution for the privacy and security issues encountered by NLP, computer vision, and acoustic AI to boost the widespread adoption of AI applications in healthcare.

show abstract

Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

Cited by 2 publications

References 6 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

Securing AI‐based healthcare systems using blockchain technology: A state‐of‐the‐art systematic literature review and future research directions

Contact Info

Product

Resources

About