Annals of Biomedical Engineering

, Volume 46, Issue 2, pp 233–246 | Cite as

Evaluation of Decoding Algorithms for Estimating Bladder Pressure from Dorsal Root Ganglia Neural Recordings

  • Shani E. Ross
  • Zhonghua Ouyang
  • Sai Rajagopalan
  • Tim M. BrunsEmail author


A closed-loop device for bladder control may offer greater clinical benefit compared to current open-loop stimulation devices. Previous studies have demonstrated the feasibility of using single-unit recordings from sacral-level dorsal root ganglia (DRG) for decoding bladder pressure. Automatic online sorting, to differentiate single units, can be computationally heavy and unreliable, in contrast to simple multi-unit thresholded activity. In this study, the feasibility of using DRG multi-unit recordings to decode bladder pressure was examined. A broad range of feature selection methods and three algorithms (multivariate linear regression, basic Kalman filter, and a nonlinear autoregressive moving average model) were used to create training models and provide validation fits to bladder pressure for data collected in seven anesthetized feline experiments. A non-linear autoregressive moving average (NARMA) model with regularization provided the most accurate bladder pressure estimate, based on normalized root-mean-squared error, NRMSE, (17 ± 7%). A basic Kalman filter yielded the highest similarity to the bladder pressure with an average correlation coefficient, CC, of 0.81 ± 0.13. The best algorithm set (based on NRMSE) was further evaluated on data obtained from a chronic feline experiment. Testing results yielded a NRMSE and CC of 10.7% and 0.61, respectively from a model that was trained on data recorded 2 weeks prior. From offline analysis, implementation of NARMA in a closed-loop scheme for detecting bladder contractions would provide a robust control signal. Ultimate integration of closed-loop algorithms in bladder neuroprostheses will require evaluations of parameter and signal stability over time.


Neural network Kalman filter Microelectrode Lower urinary tract Bladder Dorsal root ganglia DRG 



The authors would like to thank Kaile Bennett, Eric Kennedy, Zachariah Sperry, and other members of the Peripheral Neural Engineering and Urodynamics Lab for assistance with surgeries, data collection, and analysis. Research reported in this publication was supported by the Craig H. Neilsen Foundation (Grant # 314980) and by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under Award Number U18EB021760. The content is solely the responsibility of the authors and does not necessarily represent the official views of the Craig H. Neilsen Foundation or the National Institutes of Health.


  1. 1.
    Baptiste, D., M. Elkelini, M. M. Hassouna, and M. G. Fehlings. The dysfunctional bladder following spinal cord injury: from concept to clinic. Curr. Bladder Dysfunct. Rep. 4(4):192–201, 2009. Scholar
  2. 2.
    Bruns, T. M., R. A. Gaunt, D. J. Weber. Estimating bladder pressure from sacral dorsal root ganglia recordings. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011:4239–4242, 2011.
  3. 3.
    Bruns, T. M., R. A. Gaunt, and D. J. Weber. Multielectrode array recordings of bladder and perineal primary afferent activity from the sacral dorsal root ganglia. J. Neural. Eng. 8(5):56010, 2011. Scholar
  4. 4.
    Bruns, T. M., J. B. Wagenaar, M. J. Bauman, R. A. Gaunt, and D. J. Weber. Real-time control of hind limb functional electrical stimulation using feedback from dorsal root ganglia recordings. J. Neural. Eng. 10(2):26020, 2013. Scholar
  5. 5.
    Bruns, T. M., D. J. Weber, and R. A. Gaunt. Microstimulation of afferents in the sacral dorsal root ganglia can evoke reflex bladder activity. Neurourol. Urodyn. 34(1):65–71, 2015. Scholar
  6. 6.
    Chew, D. J., L. Zhu, E. Delivopoulos, et al. A microchannel neuroprosthesis for bladder control after spinal cord injury in rat. Sci. Transl. Med. 5(210):210ra155, 2013. Scholar
  7. 7.
    Christie, B. P., D. M. Tat, Z. T. Irwin, et al. Comparison of spike sorting and thresholding of voltage waveforms for intracortical brain–machine interface performance. J. Neural. Eng. 12(1):16009, 2015. Scholar
  8. 8.
    Cunningham, J. P., V. Gilja, S. I. Ryu, and K. V. Shenoy. Methods for estimating neural firing rates, and their application to brain-machine interfaces. Neural Netw. 22(9):1235–1246, 2009. Scholar
  9. 9.
    de Groat, W. C., and N. Yoshimura. Plasticity in reflex pathways to the lower urinary tract following spinal cord injury. Exp. Neurol. 235(1):123–132, 2012. Scholar
  10. 10.
    de Groat, W. C., and N. Yoshimura. Changes in afferent activity after spinal cord injury. Neurourol. Urodyn. 29(1):63–76, 2010. Scholar
  11. 11.
    Fry, C. H., F. Daneshgari, K. Thor, et al. Animal models and their use in understanding lower urinary tract dysfunction. Neurourol. Urodyn. 29(4):603–608, 2010. Scholar
  12. 12.
    Geramipour, A., S. Makki, and A. Erfanian. Neural network based forward prediction of bladder pressure using pudendal nerve electrical activity. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2015:4745–4748, 2015.
  13. 13.
    Jezernik, S., W. M. Grill, and T. Sinkjaer. Detection and inhibition of hyperreflexia-like bladder contractions in the cat by sacral nerve root recording and electrical stimulation. Neurourol. Urodyn. 20(2):215–230, 2001.<215::AID-NAU23>3.0.CO;2-0.CrossRefPubMedGoogle Scholar
  14. 14.
    Kao, J. C., P. Nuyujukian, S. Stavisky, S. I. Ryu, S. Ganguli, and K. V. Shenoy. Investigating the role of firing-rate normalization and dimensionality reduction in brain-machine interface robustness. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2013:293-298, 2013.
  15. 15.
    Karam, R., D. J. Bourbeau, S. Majerus, et al. Real-time classification of bladder events for effective diagnosis and treatment of urinary incontinence. IEEE. Trans. Biomed. Eng. 63(4):721–729, 2016. Scholar
  16. 16.
    Khurram, A., S. E. Ross, Z. J. Sperry, et al. Chronic monitoring of lower urinary tract activity via a sacral dorsal root ganglia interface. J. Neural. Eng. 14:36027, 2017. Scholar
  17. 17.
    Lin, Y. T., C. Lai, T. S. Kuo, et al. Dual-channel neuromodulation of pudendal nerve with closed-loop control strategy to improve bladder functions. J. Med. Biol. Eng. 34(1):82–89, 2014. Scholar
  18. 18.
    Majerus, S. J. A., P. C. Fletter, E. K. Ferry, H. Zhu, K. J. Gustafson, and M. S. Damaser. Suburothelial bladder contraction detection with implanted pressure sensor. PLoS ONE. 12(1):e0168375, 2017. Scholar
  19. 19.
    Melgaard, J., and N. J. M. Rijkhoff. Detecting urinary bladder contractions: methods and devices. J. Sens. Technol. 4:165–176, 2014. Scholar
  20. 20.
    Mendez, A., and M. Sawan. Chronic monitoring of bladder volume: a critical review and assessment of measurement tools. Can. J. Urol. 18(1):5504–5516, 2011.PubMedGoogle Scholar
  21. 21.
    Mendez, A., M. Sawan, T. Minagawa, and J. J. Wyndaele. Estimation of bladder volume from afferent neural activity. IEEE Trans. Neural Syst. Rehabil. Eng. 21(5):704–715, 2013. Scholar
  22. 22.
    Nitti, V. W. The prevalence of urinary incontinence. Rev. Urol. 3(Suppl 1):S2–S6, 2001.PubMedPubMedCentralGoogle Scholar
  23. 23.
    Ouyang, Z., S. E. Ross, and T. M. Bruns. Decoding algorithms and dorsal root ganglia neural recordings for estimating bladder pressure. Open Sci. Framew.
  24. 24.
    Park, J. H., C. E. Kim, J. Shin, et al. Detecting bladder fullness through the ensemble activity patterns of the spinal cord unit population in a somatovisceral convergence environment. J. Neural Eng. 10(5):56009, 2013. Scholar
  25. 25.
    Perel, S., P. T. Sadtler, E. R. Oby, et al. Single-unit activity, threshold crossings, and local field potentials in motor cortex differentially encode reach kinematics. J Neurophysiol. 114(3):1500–1512, 2015. Scholar
  26. 26.
    Rizk, M., and P. D. Wolf. Optimizing the automatic selection of spike detection thresholds using a multiple of the noise level. Med. Biol. Eng. Comput. 47(9):955–966, 2009. Scholar
  27. 27.
    Ross, S. E., Z. J. Sperry, C. M. Mahar, and T. M. Bruns. Hysteretic behavior of bladder afferent neurons in response to changes in bladder pressure. BMC Neurosci. 17:57, 2016. Scholar
  28. 28.
    Tibshirani, R. Regression shrinkage and selection via the Lasso. J. R. Stat. Soc. Ser. B. 58(1):267–288, 1996.Google Scholar
  29. 29.
    Weber, D. J., R. B. Stein, D. G. Everaert, and A. Prochazka. Limb-state feedback from ensembles of simultaneously recorded dorsal root ganglion neurons. J. Neural Eng. 4(3):S168–S180, 2007. Scholar
  30. 30.
    Wenzel, B. J., J. W. Boggs, K. J. Gustafson, and W. M. Grill. Closed loop electrical control of urinary continence. J. Urol. 175(4):1559–1563, 2006. Scholar
  31. 31.
    Winter, D. L. Receptor characteristics and conduction velocities in bladder afferents. J. Psychiatr. Res. 8(3):225–235, 1971. Scholar
  32. 32.
    Wu, W., Y. Gao, E. Bienenstock, J. P. Donoghue, and M. J. Black. Bayesian population decoding of motor cortical activity using a Kalman filter. Neural Comput. 18(1):80–118, 2006. Scholar
  33. 33.
    Wu, W., A. Shaikhouni, J. P. Donoghue, and M. J. Black. Closed-loop neural control of cursor motion using a Kalman filter. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2004:4126–4129, 2004. Scholar
  34. 34.
    Yoshimura, N. Bladder afferent pathway and spinal cord injury: possible mechanisms inducing hyperreflexia of the urinary bladder. Prog. Neurobiol. 57(6):583–606, 1999. Scholar

Copyright information

© Biomedical Engineering Society 2017

Authors and Affiliations

  1. 1.Biomedical Engineering DepartmentUniversity of MichiganAnn ArborUSA
  2. 2.Biointerfaces InstituteUniversity of MichiganAnn ArborUSA
  3. 3.Bioengineering DepartmentGeorge Mason UniversityFairfaxUSA
  4. 4.School of MedicineVanderbilt UniversityNashvilleUSA
  5. 5.Ann ArborUSA

Personalised recommendations