Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach

Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Management Information Systems (TMIS) Association for Computing Machinery

Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach

Download PDF
23 pages

Loading next page...
 
/lp/association-for-computing-machinery/near-infrared-spectroscopy-for-bladder-monitoring-a-machine-learning-I0FFgvXYpF
Publisher
Association for Computing Machinery
Copyright
Copyright © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISSN
2158-656X
eISSN
2158-6578
DOI
10.1145/3563779
Publisher site
See Article on Publisher Site

Abstract

Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients.

Journal

ACM Transactions on Management Information Systems (TMIS) – Association for Computing Machinery

Published: Jan 25, 2023

Keywords: Machine learning

References

  • TensorFlow: Large-scale machine learning on heterogeneous distributed systems
    [,
  • The standardisation of terminology in lower urinary tract function: Report from the standardisation sub-committee of the International Continence Society
    [,
  • A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion
    [,
  • The meaning of incontinence: A qualitative study of non-geriatric urinary incontinence sufferers
    [,
  • A new typology design of performance metrics to measure errors in machine learning regression algorithms
    [,
  • Random forests
    [,
  • A wireless strain sensor system for bladder volume monitoring
    [,
  • Smart wearable systems: Current status and future challenges
    [,
  • Designing an Internet-of-Things (IoT) and sensor-based in-home monitoring system for assisting diabetes patients: Iterative learning from two case studies
    [,
  • Recurrent neural networks for multivariate time series with missing values
    [,
  • FedHealth: A federated transfer learning framework for wearable healthcare
    [,
  • Keras: Deep Learning for Humans
    [,
  • ESR statement on portable ultrasound devices
    [,
  • Validation of a reference ELISA for estrone glucuronide using urine samples normalized by dilution to a constant rate of urine production
    [,
  • Wearable and implantable wireless sensor network solutions for healthcare monitoring
    [,
  • The potential for artificial intelligence in healthcare
    [,
  • The impact of movement, physical activity and position on urine production: A pilot study
    [,
  • Measurements of urinary bladder volume: comparison of five ultrasound calculation methods in volunteers
    [,
  • Machine learning for sequential data: A review
    [,
  • Neurogenic bladder
    [,
  • A guide to deep learning in healthcare
    [,
  • Towards fog-driven IoT eHealth: Promises and challenges of IoT in medicine and healthcare
    [,
  • Restoring the sense of bladder fullness for spinal cord injury patients
    [,
  • Generating synthetic time series to augment sparse datasets
    [,
  • Near-infrared spectroscopy: A report from the McDonnell infant methodology consortium
    [,
  • Diurnal blood pressure and urine production in acute spinal cord injury compared with controls
    [,
  • Balance between health risks and benefits for outdoor workers exposed to solar radiation: An overview on the role of near infrared radiation alone and in combination with other solar spectral bands
    [,
  • A comparative analysis of various regularization techniques to solve overfitting problem in artificial neural network
    [,
  • Data augmentation using synthetic data for time series classification with deep residual networks
    [,
  • Bladder filling by autologous urine production during cystometry: A urodynamic pitfall! Neurourol
    [,
  • Design principles for industrie 4
    [,
  • Design science in information systems research
    [,
  • Nocturia in the adult: Classification on the basis of largest voided volume and nocturnal urine production
    [,
  • Catheterization: Possible complications and their prevention and treatment
    [,
  • Deep learning for time series classification: A review
    [,
  • Random search for hyper-parameter optimization
    [,
  • Feasibility of approximate measurement of bladder volume in male patients using the Lilium α-200 portable ultrasound bladder scanner
    [,
  • An efficient method to determine the size of bladder using electrical impedance tomography
    [,
  • Wearable biosensors for healthcare monitoring
    [,
  • Wireless sensor networks for healthcare
    [,
  • Design and evaluation of an ultrasound-based bladder volume monitor
    [,
  • Model of urine accumulation in the bladder and method for predicting unconstrained urine volume based on absorption spectrum of urine
    [,
  • Clean intermittent catheterization revisited
    [,
  • Deep learning
    [,
  • Electric impedance tomography for monitoring volume and size of the urinary bladder
    [,
  • Preliminary study of assessing bladder urinary volume using electrical impedance tomography Löschen
    [,
  • Early diagnosis of Alzheimer's disease with deep learning
    [,
  • Medical management of neurogenic bladder for children and adults: A review
    [,
  • The various types of neurogenic bladder dysfunction: An update of current therapeutic concepts
    [,
  • What are the causes and consequences of bladder overdistension? ICI-RS 2011
    [,
  • Design and natural science research on information technology
    [,
  • The prevalence of urinary incontinence
    [,
  • Deep learning for healthcare: Review, opportunities and challenges
    [,
  • Noninvasive optical monitoring of bladder filling to capacity using a wireless near infrared spectroscopy device
    [,
  • Design of a machine learning system for prediction of chronic wound management decisions
    [,
  • Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations
    [,
  • The qualitative interview in IS research: Examining the craft
    [,
  • A comprehensive survey on non-invasive wearable bladder volume monitoring systems
    [,
  • Urinary incontinence in women
    [,
  • Novioscan–Wearable ultrasound care
    [,
  • Urine volume estimation by electrical impedance tomography with fewer electrodes: A simulation study
    [,
  • Long-Term complications of the neurogenic bladder
    [,
  • Deep learning vs
    [,
  • Depressive symptoms of patients using clean intermittent catheterization for neurogenic bladder secondary to spinal cord injury
    [,
  • A model for predicting the amount of urine in the bladder based on App-generated tracking data
    [,
  • The effectiveness of the ultrasound bladder scanner in reducing urinary tract infections: A meta-analysis
    [,
  • Scikit-learn: Machine learning in python
    [,
  • A design science research methodology for information systems research
    [,
  • Design of a miniaturized ultrasonic bladder volume monitor and subsequent preliminary evaluation on 41 enuretic patients
    [,
  • Early Stopping - But When? In Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, Vol
    [,
  • Unblackboxing smart things—A multilayer taxonomy and clusters of nontechnical smart thing characteristics
    [,
  • Deep learning for health informatics
    [,
  • A Non-invasive wearable bioimpedance system to wirelessly monitor bladder filling
    [,
  • Ensemble learning: A survey
    [,
  • Neurogenic bladder in spinal cord injury
    [,
  • Effect of electrode arrangements on bladder volume estimation by electrical impedance tomography
    [,
  • Bladder volume estimation from electrical impedance tomography
    [,
  • Urodynamic patterns of normal male micturition: influence of water consumption on urine production and detrusor function
    [,
  • Designing interviews to generate rich data for information systems research
    [,
  • Continuous bladder volume monitoring system for wearable applications
    [,
  • Predictive analytics for care and management of patients with acute diseases: Deep learning-based method to predict crucial complication phenotypes
    [,
  • Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning
    [,
  • Positioning and presenting design science research for maximum impact
    [,
  • Evaluation patterns for design science research artefacts
    [,
  • Dropout: A simple way to prevent neural networks from overfitting
    [,
  • Soft electronic strain sensor with chipless wireless readout: Toward Real-Time monitoring of bladder volume
    [,
  • DFree—US Site Wearable Bladder Scanner for Incontinence
    [,
  • Comparing different supervised machine learning algorithms for disease prediction
    [,
  • Implantable device-related infection
    [,
  • The neurogenic bladder: Medical treatment
    [,
  • Comparison of SVM and LS-SVM for regression
    [,
  • Deep learning for sensor-based activity recognition: A survey
    [,
  • The significance of the difference between two means when the population variances are unequal
    [,
  • Health information technology: Promise and progress
    [,
  • Anatomy of the bladder and bladder outlet
    [,
  • Complications of intermittent catheterization: Their prevention and treatment
    [,
  • Evolving deep CNN-LSTMs for inventory time series prediction
    [,
  • Convolutional neural networks: An overview and application in radiology
    [,
  • Artificial intelligence in healthcare
    [,
  • Human identification for activities of daily living: A deep transfer learning approach
    [,