Machine Learning and DSP Algorithms for Screening of Possible Osteoporosis Using Electronic Stethoscopes

Scanlan, Jamie; Li, Francis F.; Umnova, Olga; Rakoczy, Gyorgy; Lövey, Nóra

doi:10.1145/3288200.3288215

Cited by 4 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A region of peaks is found at 75–110 Hz, followed by a cluster of much more damped peaks in the 200–250 Hz region. These regions are consistent with the literature [13,14,15,16,17,18,19,20,22,23], but there is not a clear change in the peak position to suggest a strong correlation. The decrease in t-score did not result in a reliable decrease in the resonant frequency.…”

Section: Methodssupporting

confidence: 91%

“…To ease the vibro-acoustic data acquisition in a primary care clinical setting, the use of reflex hammer as an electronic-stethoscope was first proposed by the authors [15]. To exploit the full bandwidth of the electronic stethoscope, the “extended range” filter mode is selected in the StethAssist software on exporting the audio files.…”

Section: Methodsmentioning

confidence: 99%

“…The lowest resonant frequency of tibia and other physiological information were mapped onto the fracture risk assessment tool (FRAX) algorithm to give a diagnosis of osteoporosis [14]. More recently, the authors proposed a machine learning method to differentiate vibro-acoustic signals and detect osteoporosis [15].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning

Scanlan

Umnova

et al. 2018

Bioengineering

Self Cite

View full text Add to dashboard Cite

Osteoporosis is an asymptomatic bone condition that affects a large proportion of the elderly population around the world, resulting in increased bone fragility and increased risk of fracture. Previous studies had shown that the vibroacoustic response of bone can indicate the quality of the bone condition. Therefore, the aim of the authors’ project is to develop a new method to exploit this phenomenon to improve detection of osteoporosis in individuals. In this paper a method is described that uses a reflex hammer to exert testing stimuli on a patient’s tibia and an electronic stethoscope to acquire the impulse responses. The signals are processed as mel frequency cepstrum coefficients and passed through an artificial neural network to determine the likelihood of osteoporosis from the tibia’s impulse responses. Following some discussions of the mechanism and procedure, this paper details the signal acquisition using the stethoscope and the subsequent signal processing and the statistical machine learning algorithm. Pilot testing with 12 patients achieved over 80% sensitivity with a false positive rate below 30% and accuracies in the region of 70%. An extended dataset of 110 patients achieved an error rate of 30% with some room for improvement in the algorithm. By using common clinical apparatus and strategic machine learning, this method might be suitable as a large population screening test for the early diagnosis of osteoporosis, thus avoiding secondary complications.

show abstract

Section: Methodssupporting

confidence: 91%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning

Scanlan

Umnova

et al. 2018

Bioengineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…A Fracture Risk Assessment Tool (FRAX) is meant for diagonalizing osteoporosis, using the lowest tibia resonant frequency and other physiological details (Tejaswini et al, 2016). Much research has been done to detect osteoporosis with machine learning methods that differentiate the various vibroacoustic signals (Scanlan et al, 2018). From the Euclidean distance minimization mechanism, a simple expert system is derived and is successfully applied in cases bearing faulty recognition (Montechiesi et al, 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

A proactive model to predict osteoporosis: An artificial immune system approach

Periasamy¹,

Periasamy²,

Sathiyamoorthi³

et al. 2021

Expert Systems

View full text Add to dashboard Cite

Osteoporosis disease is caused by hormonal changes, vitamin D, and calcium deficiency. With current technologies, the identification of osteoporosis requires many tests with the support of medications. Bone mineral density is a typical measure implemented using a DEXA scan which can be very costly. Such high technology equipment is usually not accessible for remote people, and thus a low-cost screening system is very appealing. This article proposes an osteoporosis prediction system that effectively determines its possibility of occurrence based on essential factors such as smoking habits and calcium level so that the people at high risk can be referred to access the DEXA scanner. Our proposed system is implemented by an improved version of the artificial immune system, enabling care providers to take precautionary measures at the right time to avoid the early development of osteoporosis. The experiments demonstrated a promising result of 94% prediction accuracy that proved its usefulness in identifying people with potential osteoporosis in the future.

show abstract

Current Imaging Techniques

Miedany

2022

New Horizons in Osteoporosis Management

View full text Add to dashboard Cite

Machine Learning and DSP Algorithms for Screening of Possible Osteoporosis Using Electronic Stethoscopes

Abstract: Ti t l e M a c hi n e le a r ni n g a n d D S P al g o rit h m s fo r s c r e e ni n g of p o s si bl e o s t e o p o r o si s u si n g el e c t r o nic s t e t h o s c o p e s

Cited by 4 publications

References 17 publications

Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning

Detection of Osteoporosis from Percussion Responses Using an Electronic Stethoscope and Machine Learning

A proactive model to predict osteoporosis: An artificial immune system approach

Current Imaging Techniques

Contact Info

Product

Resources

About