Data-Augmented Modeling of Intracranial Pressure

  • Jian-Xun WangEmail author
  • Xiao Hu
  • Shawn C. Shadden


Precise management of patients with cerebral diseases often requires intracranial pressure (ICP) monitoring, which is highly invasive and requires a specialized ICU setting. The ability to noninvasively estimate ICP is highly compelling as an alternative to, or screening for, invasive ICP measurement. Most existing approaches for noninvasive ICP estimation aim to build a regression function that maps noninvasive measurements to an ICP estimate using statistical learning techniques. These data-based approaches have met limited success, likely because the amount of training data needed is onerous for this complex applications. In this work, we discuss an alternative strategy that aims to better utilize noninvasive measurement data by leveraging mechanistic understanding of physiology. Specifically, we developed a Bayesian framework that combines a multiscale model of intracranial physiology with noninvasive measurements of cerebral blood flow using transcranial Doppler. Virtual experiments with synthetic data are conducted to verify and analyze the proposed framework. A preliminary clinical application study on two patients is also performed in which we demonstrate the ability of this method to improve ICP prediction.


Cerebrovascular dynamics Data assimilation Patient-specific modeling Transcranial Doppler 



JXW would like to thank J. Pyne and J. Wu for helpful discussions. The authors also thank the anonymous reviewers for their comments and suggestions, which helped improve the quality and clarity of the manuscript.


  1. 1.
    Andrews, P. J., G. Citerio, L. Longhi, K. Polderman, J. Sahuquillo, P. Vajkoczy, N.-I. Care, E. M. N. S. of the European Society of Intensive Care Medicine et al. NICEM consensus on neurological monitoring in acute neurological disease. Intensive Care Med. 34:1362–1370, 2008.Google Scholar
  2. 2.
    Arnold, A., C. Battista, D. Bia, Y. Z. German, R. L. Armentano, H. Tran, and M. S. Olufsen. Uncertainty quantification in a patient-specific one-dimensional arterial network model: EnKF-based inflow estimator. J. Verif. Valid. Uncertain. Quantif. 2:011002, 2017.CrossRefGoogle Scholar
  3. 3.
    Arroyo-Palacios, J., M. Rudz, R. Fidler, W. Smith, N. Ko, S. Park, Y. Bai, and X. Hu. Characterization of shape differences among ICP pulses predicts outcome of external ventricular drainage weaning trial. Neurocritical Care 25:424–433, 2016.CrossRefGoogle Scholar
  4. 4.
    Asiedu, D. P., K.-J. Lee, G. Mills, and E. E. Kaufmann. A review of non-invasive methods of monitoring intracranial pressure. J. Neurol. Res. 4:1–6, 2014.Google Scholar
  5. 5.
    Bertoglio, C., P. Moireau, and J.-F. Gerbeau. Sequential parameter estimation for fluid–structure problems: Application to hemodynamics. Int. J. Numer. Methods Biomed. Eng. 28:434–455, 2012.Google Scholar
  6. 6.
    Brandi, G., M. Béchir, S. Sailer, C. Haberthür, R. Stocker, and J. F. Stover. Transcranial color-coded duplex sonography allows to assess cerebral perfusion pressure noninvasively following severe traumatic brain injury. Acta Neurochir. 152:965–972, 2010.CrossRefGoogle Scholar
  7. 7.
    Cardim, D., C. Robba, M. Bohdanowicz, J. Donnelly, B. Cabella, X. Liu, M. Cabeleira, P. Smielewski, B. Schmidt, and M. Czosnyka. Non-invasive monitoring of intracranial pressure using transcranial Doppler ultrasonography: is it possible? Neurocritical Care. 25:473–491, 2016.CrossRefGoogle Scholar
  8. 8.
    Connolly, M., P. Vespa, N. Pouratian, N. R. Gonzalez, and X. Hu. Characterization of the relationship between intracranial pressure and electroencephalographic monitoring in burst-suppressed patients. Neurocritical Care 22:212–220, 2015.CrossRefGoogle Scholar
  9. 9.
    Dennis, B., J. M. Ponciano, S. R. Lele, M. L. Taper, and D. F. Staples. Estimating density dependence, process noise, and observation error. Ecol. Monogr. 76:323–341, 2006.CrossRefGoogle Scholar
  10. 10.
    Ghajar, J. Traumatic brain injury. The Lancet 356:923–929, 2000.CrossRefGoogle Scholar
  11. 11.
    Giller, C. A. A bedside test for cerebral autoregulation using transcranial doppler ultrasound. Acta Neurochir. 108:7–14, 1991.CrossRefGoogle Scholar
  12. 12.
    Hickman, K., B. Mayer, and M. Muwaswes. Intracranial pressure monitoring: review of risk factors associated with infection. Heart & Lung: The J. Criti. Care 19:84–90, 1990.Google Scholar
  13. 13.
    Hu, X., N. Gonzalez, and M. Bergsneider. Steady-state indicators of the intracranial pressure dynamic system using geodesic distance of the icp pulse waveform. Physiol. Meas. 33:2017, 2012.CrossRefGoogle Scholar
  14. 14.
    Hu, X., V. Nenov, M. Bergsneider, T. C. Glenn, P. Vespa, and N. Martin. Estimation of hidden state variables of the intracranial system using constrained nonlinear Kalman filters. IEEE Trans. Biomed. Eng. 54:597–610, 2007.CrossRefGoogle Scholar
  15. 15.
    Hu, X., V. Nenov, M. Bergsneider, and N. Martin. A data mining framework of noninvasive intracranial pressure assessment. Biomed. Signal Process. Control 1:64–77, 2006.CrossRefGoogle Scholar
  16. 16.
    Hu, X., P. Xu, F. Scalzo, P. Vespa, and M. Bergsneider. Morphological clustering and analysis of continuous intracranial pressure. IEEE Trans. Biomed. Eng. 56:696–705, 2009.CrossRefGoogle Scholar
  17. 17.
    Hughes, T. J. and J. Lubliner. On the one-dimensional theory of blood flow in the larger vessels. Math. Biosci. 18:161–170, 1973.CrossRefGoogle Scholar
  18. 18.
    Iglesias, M. A. A regularizing iterative ensemble Kalman method for PDE-constrained inverse problems. Inverse Probl. 32:025002, 2016.CrossRefGoogle Scholar
  19. 19.
    Iglesias, M. A., K. J. Law, and A. M. Stuart. Ensemble Kalman methods for inverse problems. Inverse Probl. 29:045001, 2013.CrossRefGoogle Scholar
  20. 20.
    Iman, R. L. Latin hypercube sampling. Encyclopedia of quantitative risk analysis and assessment , 2008.Google Scholar
  21. 21.
    Itu, L., P. Sharma, C. Suciu, F. Moldoveanu, and D. Comaniciu. Personalized blood flow computations: A hierarchical parameter estimation framework for tuning boundary conditions. Int. J. Numer Methods Biomed. Eng. 33:e02803, 2017.Google Scholar
  22. 22.
    Kashif, F. M., G. C. Verghese, V. Novak, M. Czosnyka, and T. Heldt. Model-based noninvasive estimation of intracranial pressure from cerebral blood flow velocity and arterial pressure. Sci. Transl. Med. 4:129ra44–129ra44, 2012.Google Scholar
  23. 23.
    Kim, S., R. Hamilton, S. Pineles, M. Bergsneider, and X. Hu. Noninvasive intracranial hypertension detection utilizing semisupervised learning. IEEE Trans. Biomed. Eng. 60:1126–1133, 2013.CrossRefGoogle Scholar
  24. 24.
    Kim, S., F. Scalzo, M. Bergsneider, P. Vespa, N. Martin, and X. Hu. Noninvasive intracranial pressure assessment based on a data-mining approach using a nonlinear mapping function. IEEE Trans. Biomed. Eng. 59:619–626, 2012.CrossRefGoogle Scholar
  25. 25.
    Lal, R., F. Nicoud, E. Le Bars, J. Deverdun, F. Molino, V. Costalat, and B. Mohammadi. Non invasive blood flow features estimation in cerebral arteries from uncertain medical data. Ann. Biomed. Eng. 45:2574–2591, 2017.CrossRefGoogle Scholar
  26. 26.
    Linninger, A. A., K. Tangen, C.-Y. Hsu, and D. Frim. Cerebrospinal fluid mechanics and its coupling to cerebrovascular dynamics. Annu. Rev. Fluid Mech. 48:219–257, 2016.CrossRefGoogle Scholar
  27. 27.
    Linninger, A. A., M. Xenos, B. Sweetman, S. Ponkshe, X. Guo, and R. Penn. A mathematical model of blood, cerebrospinal fluid and brain dynamics. J. Math. Biol. 59:729–759, 2009.CrossRefGoogle Scholar
  28. 28.
    Marsden, A. L. Optimization in cardiovascular modeling. Annu. Rev. Fluid Mech. 46:519–546, 2014.CrossRefGoogle Scholar
  29. 29.
    Moireau, P., C. Bertoglio, N. Xiao, C. A. Figueroa, C. Taylor, D. Chapelle, and J.-F. Gerbeau. Sequential identification of boundary support parameters in a fluid-structure vascular model using patient image data. Biomech. Model. Mechanobiol. 12:475–496, 2013.CrossRefGoogle Scholar
  30. 30.
    Moré, J. J. The Levenberg-Marquardt algorithm: implementation and theory. In: Numerical Analysis, edited by G. A. Watson, Berlin: Springer, pp. 105–116, 1978.Google Scholar
  31. 31.
    Pant, S., C. Corsini, C. Baker, T.-Y. Hsia, G. Pennati, and I. E. Vignon-Clementel. Data assimilation and modelling of patient-specific single-ventricle physiology with and without valve regurgitation. J. Biomech. 49:2162–2173, 2016.CrossRefGoogle Scholar
  32. 32.
    Piper, I. R., K. Chan, I. R. Whittle, and J. D. Miller. An experimental study of cerebrovascular resistance, pressure transmission, and craniospinal compliance. Neurosurgery 32:805–816, 1993.CrossRefGoogle Scholar
  33. 33.
    Piper, I. R., J. D. Miller, N. M. Dearden, J. R. Leggate, and I. Robertson. Systems analysis of cerebrovascular pressure transmission: an observational study in head-injured patients. J. Neurosurg. 73:871–880, 1990.CrossRefGoogle Scholar
  34. 34.
    Ryu, J., X. Hu, and S. C. Shadden. A coupled lumped-parameter and distributed network model for cerebral pulse-wave hemodynamics. J. Biomech. Eng. 137:101009, 2015.CrossRefGoogle Scholar
  35. 35.
    Ryu, J., N. Ko, X. Hu, and S. C. Shadden. Numerical investigation of vasospasm detection by extracranial blood velocity ratios. Cerebrovasc. Dis. 43:214–222, 2017.CrossRefGoogle Scholar
  36. 36.
    Serban, R. and A. C. Hindmarsh. CVODES: the sensitivity-enabled ODE solver in SUNDIALS. In: ASME 2005 international design engineering technical conferences and computers and information in engineering conference. American Society of Mechanical Engineers, pp. 257–269, 2005.Google Scholar
  37. 37.
    Shi, Y., P. Lawford, and R. Hose. Review of zero-D and 1-D models of blood flow in the cardiovascular system. Biomed. Eng. Online 10:33, 2011.CrossRefGoogle Scholar
  38. 38.
    Stevens, S. A., W. D. Lakin, and P. L. Penar. Modeling steady-state intracranial pressures in supine, head-down tilt and microgravity conditions. Aviation Space Environ. Med. 76:329–338, 2005.Google Scholar
  39. 39.
    Tiago, J., T. Guerra, and A. Sequeira. A velocity tracking approach for the data assimilation problem in blood flow simulations. Int. J. Numer. Methods Biomed. Eng. 33:e2856, 2017.Google Scholar
  40. 40.
    Ursino, M. and M. Giannessi. A model of cerebrovascular reactivity including the circle of Willis and cortical anastomoses. Ann. Biomed. Eng. 38:955–974, 2010.CrossRefGoogle Scholar
  41. 41.
    Ursino, M. and C. A. Lodi. Interaction among autoregulation, CO2 reactivity, and intracranial pressure: a mathematical model. Am. J. Physiol.-Heart Circ. Physiol. 274:H1715–H1728, 1998.CrossRefGoogle Scholar
  42. 42.
    Wakeland, W. and B. Goldstein. A review of physiological simulation models of intracranial pressure dynamics. Comput. Biol. Med. 38:1024–1041, 2008.CrossRefGoogle Scholar
  43. 43.
    Xu, P., M. Kasprowicz, M. Bergsneider, and X. Hu. Improved noninvasive intracranial pressure assessment with nonlinear kernel regression. IEEE Trans. Inf. Technol. Biomed. 14:971–978, 2010.CrossRefGoogle Scholar
  44. 44.
    Zhang, X., J. E. Medow, B. J. Iskandar, F. Wang, M. Shokoueinejad, J. Koueik, and J. G. Webster. Invasive and noninvasive means of measuring intracranial pressure: a review. Physiol. Meas. 38:R143, 2017.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2019

Authors and Affiliations

  1. 1.Mechanical EngineeringUniversity of CaliforniaBerkeleyUSA
  2. 2.Aerospace and Mechanical Engineering, Center of Informatics and Computational ScienceUniversity of Notre DameNotre DameUSA
  3. 3.Department of Physiological Nursing, Department of Neurological surgery, Institute of Computational Health Sciences, UCSF Joint Bio-Engineering Graduate ProgramUniversity of CaliforniaSan FranciscoUSA

Personalised recommendations