Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures
(1) Background: Non-invasive uroflowmetry is used in clinical practice for diagnosing lower urinary tract symptoms (LUTS) and the health status of a patient. To establish a smart system for measuring the flowrate during urination without any temporospatial constraints for patients with a urinary dis...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/16/5328 |
_version_ | 1797522080638435328 |
---|---|
author | Jie Jin Youngbeen Chung Wanseung Kim Yonggi Heo Jinyong Jeon Jeongkyu Hoh Junhong Park Jungki Jo |
author_facet | Jie Jin Youngbeen Chung Wanseung Kim Yonggi Heo Jinyong Jeon Jeongkyu Hoh Junhong Park Jungki Jo |
author_sort | Jie Jin |
collection | DOAJ |
description | (1) Background: Non-invasive uroflowmetry is used in clinical practice for diagnosing lower urinary tract symptoms (LUTS) and the health status of a patient. To establish a smart system for measuring the flowrate during urination without any temporospatial constraints for patients with a urinary disorder, the acoustic signatures from the uroflow of patients being treated for LUTS at a tertiary hospital were utilized. (2) Methods: Uroflowmetry data were collected for construction and verification of a long short-term memory (LSTM) deep-learning algorithm. The initial sample size comprised 34 patients; 27 patients were included in the final analysis. Uroflow sounds generated from flow impacts on a structure were analyzed by loudness and roughness parameters. (3) Results: A similar signal pattern to the clinical urological measurements was observed and applied for health diagnosis. (4) Conclusions: Consistent flowrate values were obtained by applying the uroflow sound samples from the randomly selected patients to the constructed model for validation. The flowrate predicted using the acoustic signature accurately demonstrated actual physical characteristics. This could be used for developing a new smart flowmetry device applicable in everyday life with minimal constraints from settings and enable remote diagnosis of urinary system diseases by objective continuous measurements of bladder emptying function. |
first_indexed | 2024-03-10T08:24:26Z |
format | Article |
id | doaj.art-6b5270c8bb33474a89a5c10408c0edff |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T08:24:26Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-6b5270c8bb33474a89a5c10408c0edff2023-11-22T09:37:50ZengMDPI AGSensors1424-82202021-08-012116532810.3390/s21165328Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic SignaturesJie Jin0Youngbeen Chung1Wanseung Kim2Yonggi Heo3Jinyong Jeon4Jeongkyu Hoh5Junhong Park6Jungki Jo7School of Electromechanical and Automotive Engineering, Yantai University, 30 Qingquan Road, Laishan District, Yantai 264005, ChinaDepartment of Mechanical Engineering, Hanyang University, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Mechanical Engineering, Hanyang University, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Medical and Digital Engineering, Hanyang University, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Architectural Engineering, Hanyang University, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Obstetrics and Gynecology, Hanyang University Seoul Hospital, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Mechanical Engineering, Hanyang University, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, KoreaDepartment of Urology, Hanyang University Seoul Hospital, Wangsimni-ro 222, Seongdong-Gu, Seoul 04763, Korea(1) Background: Non-invasive uroflowmetry is used in clinical practice for diagnosing lower urinary tract symptoms (LUTS) and the health status of a patient. To establish a smart system for measuring the flowrate during urination without any temporospatial constraints for patients with a urinary disorder, the acoustic signatures from the uroflow of patients being treated for LUTS at a tertiary hospital were utilized. (2) Methods: Uroflowmetry data were collected for construction and verification of a long short-term memory (LSTM) deep-learning algorithm. The initial sample size comprised 34 patients; 27 patients were included in the final analysis. Uroflow sounds generated from flow impacts on a structure were analyzed by loudness and roughness parameters. (3) Results: A similar signal pattern to the clinical urological measurements was observed and applied for health diagnosis. (4) Conclusions: Consistent flowrate values were obtained by applying the uroflow sound samples from the randomly selected patients to the constructed model for validation. The flowrate predicted using the acoustic signature accurately demonstrated actual physical characteristics. This could be used for developing a new smart flowmetry device applicable in everyday life with minimal constraints from settings and enable remote diagnosis of urinary system diseases by objective continuous measurements of bladder emptying function.https://www.mdpi.com/1424-8220/21/16/5328acoustic signalclassificationflowrate predictionlower urinary tract symptomslong short-term memory |
spellingShingle | Jie Jin Youngbeen Chung Wanseung Kim Yonggi Heo Jinyong Jeon Jeongkyu Hoh Junhong Park Jungki Jo Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures Sensors acoustic signal classification flowrate prediction lower urinary tract symptoms long short-term memory |
title | Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures |
title_full | Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures |
title_fullStr | Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures |
title_full_unstemmed | Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures |
title_short | Classification of Bladder Emptying Patterns by LSTM Neural Network Trained Using Acoustic Signatures |
title_sort | classification of bladder emptying patterns by lstm neural network trained using acoustic signatures |
topic | acoustic signal classification flowrate prediction lower urinary tract symptoms long short-term memory |
url | https://www.mdpi.com/1424-8220/21/16/5328 |
work_keys_str_mv | AT jiejin classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT youngbeenchung classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT wanseungkim classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT yonggiheo classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT jinyongjeon classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT jeongkyuhoh classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT junhongpark classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures AT jungkijo classificationofbladderemptyingpatternsbylstmneuralnetworktrainedusingacousticsignatures |