Skip to main content

Advertisement

SpringerLink
Log in

Hierarchical Cluster Analysis Identifies Distinct Physiological States After Acute Brain Injury

  • Original work
  • Published:
Neurocritical Care Aims and scope Submit manuscript

Abstract

Background

Analysis of intracranial multimodality monitoring data is challenging, and quantitative methods may help identify unique physiological signatures that inform therapeutic strategies and outcome prediction. The aim of this study was to test the hypothesis that data-driven approaches can identify distinct physiological states from intracranial multimodality monitoring data.

Methods

This was a single-center retrospective observational study of patients with either severe traumatic brain injury or high-grade subarachnoid hemorrhage who underwent invasive multimodality neuromonitoring. We used hierarchical cluster analysis to group hourly values for heart rate, mean arterial pressure, intracranial pressure, brain tissue oxygen, and cerebral microdialysis across all included patients into distinct groups. Average values for measured physiological variables were compared across the identified clusters, and physiological profiles from identified clusters were mapped onto physiological states known to occur after acute brain injury. The distribution of clusters was compared between patients with favorable outcome (discharged to home or acute rehab) and unfavorable outcome (in-hospital death or discharged to chronic nursing facility).

Results

A total of 1704 observations from 20 patients were included. Even though the difference in mean values for measured variables between patients with favorable and unfavorable outcome were small, we identified four distinct clusters within our data: (1) events with low brain tissue oxygen and high lactate-to-pyruvate ratio–values (consistent with cerebral ischemia), (2) events with higher intracranial pressure values without evidence for ischemia (3) events which appeared to be physiologically “normal,” and (4) events with high cerebral lactate without brain hypoxia (consistent with cerebral hyperglycolysis). Patients with a favorable outcome had a greater proportion of cluster 3 (normal) events, whereas patients with an unfavorable outcome had a greater proportion of cluster 1 (ischemia) and cluster 4 (hyperglycolysis) events (p < 0.0001, Fisher–Freeman–Halton test).

Conclusions

A data-driven approach can identify distinct groupings from invasive multimodality neuromonitoring data that may have implications for therapeutic strategies and outcome predictions. These groupings could be used as classifiers to train machine learning models that can aid in the treatment of patients with acute brain injury. Further work is needed to replicate the findings of this exploratory study in larger data sets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Diedler J, Czosnyka M. Merits and pitfalls of multimodality brain monitoring. Neurocrit Care. 2010;12:313–6.

    Article  Google Scholar 

  2. Chesnut RM, Marshall LF, Klauber MR, et al. The role of secondary brain injury in determining outcome from severe head injury. J Trauma. 1993;34:216–22.

    Article  CAS  Google Scholar 

  3. Miller JD, Becker DP, Ward JD, Sullivan HG, Adams WE, Rosner MJ. Significance of intracranial hypertension in severe head injury. J Neurosurg. 1977;47:503–16.

    Article  CAS  Google Scholar 

  4. Roh D, Park S. Brain multimodality monitoring: updated perspectives. Curr Neurol Neurosci Rep. 2016;16:56.

    Article  Google Scholar 

  5. Le Roux P. Intracranial pressure after the BEST TRIP trial: a call for more monitoring. Curr Opin Crit Care. 2014;20:141–7.

    Article  Google Scholar 

  6. Cooper DJ, Rosenfeld JV, Murray L, et al. Decompressive craniectomy in diffuse traumatic brain injury. N Engl J Med. 2011;364:1493–502.

    Article  CAS  Google Scholar 

  7. Andrews PJD, Sinclair HL, Rodriguez A, et al. Hypothermia for intracranial hypertension after traumatic brain injury. N Engl J Med. 2015;373:2403–12.

    Article  CAS  Google Scholar 

  8. Kofke WA, Ren Y, Augoustides JG, et al. Reframing the biological basis of neuroprotection using functional genomics: differentially weighted, time-dependent multifactor pathogenesis of human ischemic brain damage. Front Neurol. 2018;9:497. https://doi.org/10.3389/fneur.2018.00497

    Article  PubMed  PubMed Central  Google Scholar 

  9. Kofke WA, Rajagopalan S, Ayubcha D, et al. Defining a taxonomy of intracranial hypertension: is ICP more than just a number? J Neurosurg Anesthesiol. 2020;32:120–31.

    Article  Google Scholar 

  10. Schinkel M, Paranjape K, Nannan Panday RS, Skyttberg N, Nanayakkara PWB. Clinical applications of artificial intelligence in sepsis: a narrative review. Comput Biol Med. 2019;115:103488.

    Article  CAS  Google Scholar 

  11. Giannini HM, Ginestra JC, Chivers C, et al. A machine learning algorithm to predict severe sepsis and septic shock: development, implementation, and impact on clinical practice. Crit Care Med. 2019;47:1485–92.

    Article  Google Scholar 

  12. Amorim E, van der Stoel M, Nagaraj SB, et al. Quantitative EEG reactivity and machine learning for prognostication in hypoxic-ischemic brain injury. Clin Neurophysiol. 2019;130:1908–16.

    Article  Google Scholar 

  13. Tjepkema-Cloostermans MC, da Silva LC, Ruijter BJ, et al. Outcome prediction in postanoxic coma with deep learning. Crit Care Med. 2019;47:1424–32.

    Article  Google Scholar 

  14. Claassen J, Doyle K, Matory A, et al. Detection of brain activation in unresponsive patients with acute brain injury. N Engl J Med. 2019;380:2497–505.

    Article  Google Scholar 

  15. Lazaridis C, Rusin CG, Robertson CS. Secondary brain injury: predicting and preventing insults. Neuropharmacology. 2019;145:145–52.

    Article  CAS  Google Scholar 

  16. Chen HI, Stiefel MF, Oddo M, et al. Detection of cerebral compromise with multimodality monitoring in patients with subarachnoid hemorrhage. Neurosurgery. 2011;69:53–63; discussion 63.

  17. Connolly ES, Rabinstein AA, Carhuapoma JR, et al. Guidelines for the management of aneurysmal subarachnoid hemorrhage. Stroke. 2012;43:1711–37.

    Article  Google Scholar 

  18. Brain Trauma Foundation; American Association of Neurological Surgeons; Congress of Neurological Surgeons. Guidelines for the management of severe traumatic brain injury. J Neurotrauma. 2007;24 Suppl 1:S1–106.

  19. Oddo M, Frangos S, Milby A, et al. Induced normothermia attenuates cerebral metabolic distress in patients with aneurysmal subarachnoid hemorrhage and refractory fever. Stroke. 2009;40:1913–6.

    Article  Google Scholar 

  20. Oddo M, Levine JM, Frangos S, et al. Brain lactate metabolism in humans with subarachnoid hemorrhage. Stroke. 2012;43:1418–21.

    Article  CAS  Google Scholar 

  21. Oddo M, Milby A, Chen I, et al. Hemoglobin concentration and cerebral metabolism in patients with aneurysmal subarachnoid hemorrhage. Stroke. 2009;40:1275–81.

    Article  CAS  Google Scholar 

  22. Knopf L, Staff I, Gomes J, McCullough L. Impact of a neurointensivist on outcomes in critically ill stroke patients. Neurocrit Care. 2012;16:63–71.

    Article  Google Scholar 

  23. Spiotta AM, Stiefel MF, Gracias VH, et al. Brain tissue oxygen-directed management and outcome in patients with severe traumatic brain injury. J Neurosurg. 2010;113:571–80.

    Article  Google Scholar 

  24. Young B, Moyer M, Pino W, Kung D, Zager E, Kumar MA. Safety and feasibility of early mobilization in patients with subarachnoid hemorrhage and external ventricular drain. Neurocrit Care. 2019;31:88–96.

    Article  Google Scholar 

  25. Boluki S, Zamani Dadaneh S, Qian X, Dougherty ER. Optimal clustering with missing values. BMC Bioinform. 2019;20:321.

    Article  Google Scholar 

  26. Hand DJ, Mannila H, Smyth P. Principles of data mining. London: MIT Press; 2001.

    Google Scholar 

  27. Caliński T, Harabasz J. A dendrite method for cluster analysis. Commun Stat. 1974;3:1–27.

    Google Scholar 

  28. Nelson DW, Bellander BM, Maccallum RM, et al. Cerebral microdialysis of patients with severe traumatic brain injury exhibits highly individualistic patterns as visualized by cluster analysis with self-organizing maps. Crit Care Med. 2004;32:2428–36.

    Article  CAS  Google Scholar 

  29. Sorani MD, Hemphill JC 3rd, Morabito D, Rosenthal G, Manley GT. New approaches to physiological informatics in neurocritical care. Neurocrit Care. 2007;7:45–52.

    Article  Google Scholar 

  30. Cohen MJ, Grossman AD, Morabito D, Knudson MM, Butte AJ, Manley GT. Identification of complex metabolic states in critically injured patients using bioinformatic cluster analysis. Crit Care. 2010;14:R10.

    Article  Google Scholar 

  31. Zeiler FA, Beqiri E, Cabeleira M, et al. Brain tissue oxygen and cerebrovascular reactivity in traumatic brain injury: a collaborative european neurotrauma effectiveness research in traumatic brain injury exploratory analysis of insult burden. J Neurotrauma. 2020;37:1854–63.

    Article  Google Scholar 

  32. Kofke WA, Rajagopalan S, Ayubcha D, et al. Defining a taxonomy of intracranial hypertension: is ICP more than just a number? J Neurosurg Anesthesiol. 2020;32(2):120–31.

    Article  Google Scholar 

  33. Magistretti PJ, Allaman I. Lactate in the brain: from metabolic end-product to signalling molecule. Nat Rev Neurosci. 2018;19:235–49.

    Article  CAS  Google Scholar 

  34. Vespa P, Bergsneider M, Hattori N, et al. Metabolic crisis without brain ischemia is common after traumatic brain injury: a combined microdialysis and positron emission tomography study. J Cereb Blood Flow Metab. 2005;25:763–74.

    Article  CAS  Google Scholar 

  35. Larach DB, Kofke WA, Le Roux P. Potential non-hypoxic/ischemic causes of increased cerebral interstitial fluid lactate/pyruvate ratio: a review of available literature. Neurocrit Care. 2011;15:609–22.

    Article  Google Scholar 

  36. Sala N, Suys T, Zerlauth JB, et al. Cerebral extracellular lactate increase is predominantly nonischemic in patients with severe traumatic brain injury. J Cereb Blood Flow Metab. 2013;33:1815–22.

    Article  CAS  Google Scholar 

  37. Carpenter KLH, Jalloh I, Hutchinson PJ. Glycolysis and the significance of lactate in traumatic brain injury. Front Neurosci. 2015;9:112. https://doi.org/10.3389/fnins.2015.00112

    Article  PubMed  PubMed Central  Google Scholar 

  38. Bouzat P, Oddo M. Lactate and the injured brain: friend or foe? Curr Opin Crit Care. 2014;20:133–40.

    Article  Google Scholar 

  39. Carteron L, Solari D, Patet C, et al. Hypertonic lactate to improve cerebral perfusion and glucose availability after acute brain injury. Crit Care Med. 2018;46:1649–55.

    Article  CAS  Google Scholar 

  40. Zhang Y, Szolovits P. Patient-specific learning in real time for adaptive monitoring in critical care. J Biomed Inform. 2008;41:452–60.

    Article  Google Scholar 

Download references

Funding

This work received National Institutes of Health (Grant Nos. 1R01NS082309-01A1, NS082309, NS060653).

Author information

Authors and Affiliations

  1. Department of Neurology, Cooper Medical School of Rowan University, Camden, NJ, USA

    Swarna Rajagopalan

  2. Department of Neurology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Wesley Baker

  3. Department of Anesthesiology, Perioperative Medicine and Pain Management, University of Miami Miller School of Medicine, Miami, USA

    Elizabeth Mahanna-Gabrielli

  4. Department of Anesthesiology and Critical Care Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

    Andrew William Kofke

  5. Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

    Ramani Balu

Authors
  1. Swarna Rajagopalan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wesley Baker
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Elizabeth Mahanna-Gabrielli
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andrew William Kofke
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ramani Balu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Dr. R and Dr. B developed the presented idea. Dr. R extracted and organized the data. Dr. B the analysis. Dr. WB, Dr. EM-G and Dr. K verified the analytical methods and provided guidance regarding analyses. Dr. R and Dr. B wrote the article in consultation with Dr. WB, Dr. EM-G and Dr. K. All authors approve of the final manuscript.

Corresponding authors

Correspondence to Swarna Rajagopalan or Ramani Balu.

Ethics declarations

Conflict of interest

Dr. Rajagopalan has nothing to disclose. Wesley Baker has nothing to disclose. Dr. Elizabeth Mahanna-Gabrielli has nothing to disclose. Dr. Andrew Kofke and Dr. Ramani Balu have received funding from the National Institutes of Health (NS082309 and NS060653, respectively).

Ethical approval and informed consent

Ethical guidelines were adhered to. The Institutional Review Board of the University of Pennsylvania approved the current retrospective study and waived the need for obtaining informed consent from the patient cohort.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PPTX 255 kb)

Supplementary file2 (DOCX 12 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rajagopalan, S., Baker, W., Mahanna-Gabrielli, E. et al. Hierarchical Cluster Analysis Identifies Distinct Physiological States After Acute Brain Injury. Neurocrit Care 36, 630–639 (2022). https://doi.org/10.1007/s12028-021-01362-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12028-021-01362-6

Keywords

Search

Navigation