Journal of Clinical Monitoring and Computing

, Volume 33, Issue 1, pp 95–105 | Cite as

Predicting delayed cerebral ischemia after subarachnoid hemorrhage using physiological time series data

  • Soojin ParkEmail author
  • Murad Megjhani
  • Hans-Peter Frey
  • Edouard Grave
  • Chris Wiggins
  • Kalijah L. Terilli
  • David J. Roh
  • Angela Velazquez
  • Sachin Agarwal
  • E. Sander ConnollyJr.
  • J. Michael Schmidt
  • Jan Claassen
  • Noemie Elhadad
Original Research


To develop and validate a prediction model for delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) using a temporal unsupervised feature engineering approach, demonstrating improved precision over standard features. 488 consecutive SAH admissions from 2006 to 2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Baseline information and standard grading scales were evaluated: age, sex, Hunt Hess grade, modified Fisher Scale (mFS), and Glasgow Coma Scale (GCS). An unsupervised approach applying random kernels was used to extract features from physiological time series (systolic and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (Partial Least Squares, linear and kernel Support Vector Machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset. The performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.58. Combined demographics and grading scales: AUC 0.60. Random kernel derived physiologic features: AUC 0.74. Combined baseline and physiologic features with redundant feature reduction: AUC 0.77. Current DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high-frequency physiologic time series data, we demonstrated that our models achieve higher classification accuracy.


Subarachnoid hemorrhage Random kernels Time series Machine learning Critical care 



Data Collection (SP, HF, JC, SA, DJR, ESC, JMS, AV, KT), Analysis (SP, HF, EG, MM, CW, NE), Writing (SP, HF, MM), Editing (All).


National Institutes of Health K01-ES026833-02 (SP), National Institutes of Health U54-CA193313-01 (CW). National Science Foundation 1305023 (CW). National Science Foundation 1344668 (CW, NE).

Compliance with ethical standards

Conflict of interest

Authors do not have any other disclosures of potential conflicts of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. This study has been approved by the Columbia University Medical Center Institutional Review Board.

Informed consent

Informed consent was obtained from all individual participants or their surrogates included in the study.


  1. 1.
    Suarez J. PRINCE Neurocritical Care Point-Prevalence Study Preliminary Results Revealed, vol. 9. Currents: News Magazine of the Neurocritical Care Society; 2014.Google Scholar
  2. 2.
    Report of World Federation of Neurological Surgeons Committee on a Universal Subarachnoid Hemorrhage Grading Scale. J Neurosurg. 1988;68(6):985–6.Google Scholar
  3. 3.
    Shea AM, Reed SD, Curtis LH, Alexander MJ, Villani JJ, Schulman KA. Characteristics of nontraumatic subarachnoid hemorrhage in the United States in 2003. Neurosurgery 2007;61(6):1131–7. (discussion 1137–1138).Google Scholar
  4. 4.
    Qureshi AI, Suri MF, Nasar A, Kirmani JF, Divani AA, He W, Hopkins LN. Trends in hospitalization and mortality for subarachnoid hemorrhage and unruptured aneurysms in the United States. Neurosurgery 2005;57(1):1–8 (discussion 1–8).Google Scholar
  5. 5.
    Molyneux AJ, Kerr RS, Birks J, Ramzi N, Yarnold J, Sneade M, Rischmiller J, Collaborators I. Risk of recurrent subarachnoid haemorrhage, death, or dependence and standardised mortality ratios after clipping or coiling of an intracranial aneurysm in the International Subarachnoid Aneurysm Trial (ISAT): long-term follow-up. Lancet Neurol. 2009;8(5):427–33. Scholar
  6. 6.
    Springer MV, Schmidt JM, Wartenberg KE, Frontera JA, Badjatia N, Mayer SA. Predictors of global cognitive impairment 1 year after subarachnoid hemorrhage. Neurosurgery 2009;65(6):1043–50. (discussion 1050–1041).Google Scholar
  7. 7.
    Roos YB, Dijkgraaf MG, Albrecht KW, Beenen LF, Groen RJ, de Haan RJ, Vermeulen M. Direct costs of modern treatment of aneurysmal subarachnoid hemorrhage in the first year after diagnosis. Stroke 2002;33(6):1595–9.Google Scholar
  8. 8.
    Mayer SA, Kreiter KT, Copeland D, Bernardini GL, Bates JE, Peery S, Claassen J, Du YE, Connolly ES Jr. Global and domain-specific cognitive impairment and outcome after subarachnoid hemorrhage. Neurology. 2002;59(11):1750–8.Google Scholar
  9. 9.
    Hackett ML, Anderson CS. Health outcomes 1 year after subarachnoid hemorrhage: An international population-based study. The Australian Cooperative Research on Subarachnoid Hemorrhage Study Group. Neurology. 2000;55(5):658–62.Google Scholar
  10. 10.
    Charpentier C, Audibert G, Guillemin F, Civit T, Ducrocq X, Bracard S, Hepner H, Picard L, Laxenaire MC. Multivariate analysis of predictors of cerebral vasospasm occurrence after aneurysmal subarachnoid hemorrhage. Stroke 1999;30(7):1402–8.Google Scholar
  11. 11.
    Dorsch N. A clinical review of cerebral vasospasm and delayed ischaemia following aneurysm rupture. Acta Neurochir Suppl. 2011;110(Pt 1):5–6. Scholar
  12. 12.
    Schmidt JM, Wartenberg KE, Fernandez A, Claassen J, Rincon F, Ostapkovich ND, Badjatia N, Parra A, Connolly ES, Mayer SA. Frequency and clinical impact of asymptomatic cerebral infarction due to vasospasm after subarachnoid hemorrhage. J Neurosurg. 2008;109(6):1052–9. Scholar
  13. 13.
    Rabinstein AA, Pichelmann MA, Friedman JA, Piepgras DG, Nichols DA, McIver JI, Toussaint LG 3rd, McClelland RL, Fulgham JR, Meyer FB, Atkinson JL, Wijdicks EF. Symptomatic vasospasm and outcomes following aneurysmal subarachnoid hemorrhage: a comparison between surgical repair and endovascular coil occlusion. J Neurosurg. 2003;98(2):319–25. Scholar
  14. 14.
    Kirmani JF, Qureshi AI, Hanel RA, Siddiqui AM, Safdar A, Yahia AM, Kim SH, Guterman LR, Hopkins LN. Silent cerebral infarctions in poor-grade patients with subarachnoid hemorrhage. Neurology 2002;58(7):A159.Google Scholar
  15. 15.
    Frontera JA, Fernandez A, Schmidt JM, Claassen J, Wartenberg KE, Badjatia N, Connolly ES, Mayer SA. Defining vasospasm after subarachnoid hemorrhage: what is the most clinically relevant definition? Stroke (2009);40(6):1963–8. Scholar
  16. 16.
    Vergouwen MD, Vermeulen M, van Gijn J, Rinkel GJ, Wijdicks EF, Muizelaar JP, Mendelow AD, Juvela S, Yonas H, Terbrugge KG, Macdonald RL, Diringer MN, Broderick JP, Dreier JP, Roos YB. Definition of delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage as an outcome event in clinical trials and observational studies: proposal of a multidisciplinary research group. Stroke 2010;41(10):2391–5. Scholar
  17. 17.
    Rosen DS, Macdonald RL. Subarachnoid hemorrhage grading scales: a systematic review. Neurocrit Care. 2005;2(2):110–8. Scholar
  18. 18.
    Fisher CM, Kistler JP, Davis JM. Relation of cerebral vasospasm to subarachnoid hemorrhage visualized by computerized tomographic scanning. Neurosurgery 1980;6(1):1–9.Google Scholar
  19. 19.
    Claassen J, Bernardini GL, Kreiter K, Bates J, Du YE, Copeland D, Connolly ES, Mayer SA. Effect of cisternal and ventricular blood on risk of delayed cerebral ischemia after subarachnoid hemorrhage: the Fisher scale revisited. Stroke 2001;32(9):2012–20.Google Scholar
  20. 20.
    Gaieski DF, Mikkelsen ME, Band RA, Pines JM, Massone R, Furia FF, Shofer FS, Goyal M. Impact of time to antibiotics on survival in patients with severe sepsis or septic shock in whom early goal-directed therapy was initiated in the emergency department. Criti Care Med. 2010;38(4):1045–53. Scholar
  21. 21.
    Diringer MN. Management of aneurysmal subarachnoid hemorrhage. Criti Care Med. 2009;37(2):432–40. Scholar
  22. 22.
    Heros RC, Zervas NT, Varsos V. Cerebral vasospasm after subarachnoid hemorrhage: an update. Ann Neurol. 1983;14(6):599–608. Scholar
  23. 23.
    Lindegaard KF, Nornes H, Bakke SJ, Sorteberg W, Nakstad P. Cerebral vasospasm diagnosis by means of angiography and blood velocity measurements. Acta Neurochir. 1989;100(1–2):12–24.Google Scholar
  24. 24.
    Krejza J, Szydlik P, Liebeskind DS, Kochanowicz J, Bronov O, Mariak Z, Melhem ER. Age and sex variability and normal reference values for the V(MCA)/V(ICA) index. AJNR 2005;26(4):730–5.Google Scholar
  25. 25.
    Naval NS, Thomas CE, Urrutia VC. Relative changes in flow velocities in vasospasm after subarachnoid hemorrhage: a transcranial Doppler study. Neurocrit Care. 2005;2(2):133–40. Scholar
  26. 26.
    Grosset DG, Straiton J, McDonald I, Cockburn M, Bullock R. Use of transcranial Doppler sonography to predict development of a delayed ischemic deficit after subarachnoid hemorrhage. J Neurosurg. 1993;78(2):183–7. Scholar
  27. 27.
    Sekhar LN, Wechsler LR, Yonas H, Luyckx K, Obrist W. Value of transcranial Doppler examination in the diagnosis of cerebral vasospasm after subarachnoid hemorrhage. Neurosurgery 1988;22(5):813–21.Google Scholar
  28. 28.
    Lysakowski C, Walder B, Costanza MC, Tramer MR. Transcranial Doppler versus angiography in patients with vasospasm due to a ruptured cerebral aneurysm: A systematic review. Stroke 2001;32(10):2292–8.Google Scholar
  29. 29.
    Harders AG, Gilsbach JM. Time course of blood velocity changes related to vasospasm in the circle of Willis measured by transcranial Doppler ultrasound. J Neurosurg. 1987;66(5):718–28. Scholar
  30. 30.
    Crobeddu E, Mittal MK, Dupont S, Wijdicks EF, Lanzino G, Rabinstein AA. Predicting the lack of development of delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage. Stroke 2012;43(3):697–701. Scholar
  31. 31.
    Frontera JA, Claassen J, Schmidt JM, Wartenberg KE, Temes R, Connolly ES Jr, MacDonald RL, Mayer SA. Prediction of symptomatic vasospasm after subarachnoid hemorrhage: the modified Fisher Scale. Neurosurgery 2006;59(1):21–7. (discussion 21–27).Google Scholar
  32. 32.
    Foreman PM, Chua MH, Harrigan MR, Fisher WS 3rd, Tubbs RS, Shoja MM, Griessenauer CJ. External validation of the Practical Risk Chart for the prediction of delayed cerebral ischemia following aneurysmal subarachnoid hemorrhage. J Neurosurg. 2016. Scholar
  33. 33.
    de Rooij NK, Greving JP, Rinkel GJ, Frijns CJ. Early prediction of delayed cerebral ischemia after subarachnoid hemorrhage: development and validation of a practical risk chart. Stroke 2013;44(5):1288–94. Scholar
  34. 34.
    Calviere L, Nasr N, Arnaud C, Czosnyka M, Viguier A, Tissot B, Sol JC, Larrue V. Prediction of delayed cerebral ischemia after subarachnoid hemorrhage using cerebral blood flow velocities and cerebral autoregulation assessment. Neurocrit Care. 2015;23(2):253–8. Scholar
  35. 35.
    Roederer A, Holmes JH, Smith MJ, Lee I, Park S. Prediction of significant vasospasm in aneurysmal subarachnoid hemorrhage using automated data. Neurocrit Care. 2014;21(3):444–50. Scholar
  36. 36.
    Sacchi L, Dagliati A, Bellazzi R. Analyzing complex patients’ temporal histories: new frontiers in temporal data mining. Methods Mol Biol. 2015;1246:89–105. Scholar
  37. 37.
    Stacey M, McGregor C. Temporal abstraction in intelligent clinical data analysis: a survey. Artif Intell Med. 2007;39(1):1–24. Scholar
  38. 38.
    Verduijn M, Sacchi L, Peek N, Bellazzi R, de Jonge E, de Mol BA. Temporal abstraction for feature extraction: a comparative case study in prediction from intensive care monitoring data. Artif Intell Med. 2007;41(1):1–12. Scholar
  39. 39.
    Saria S, Rajani AK, Gould J, Koller D, Penn AA. Integration of early physiological responses predicts later illness severity in preterm infants. Sci Transl Med. 2010;2(48):48ra65. Scholar
  40. 40.
    Mayer CC, Bachler M, Hortenhuber M, Stocker C, Holzinger A, Wassertheurer S. (2014) Selection of entropy-measure parameters for knowledge discovery in heart rate variability data. BMC Bioinform. 15(Suppl 6):S2. Scholar
  41. 41.
    Dua S, Saini S, Singh H. Temporal pattern mining for multivariate time series classification. J Med Imag Health Inform. 2011;1(2):164–9. Scholar
  42. 42.
    Lehman LW, Adams RP, Mayaud L, Moody GB, Malhotra A, Mark RG, Nemati S. A physiological time series dynamics-based approach to patient monitoring and outcome prediction. IEEE J Biomed Health Inform. 2015;19(3):1068–76. Scholar
  43. 43.
    Schulam P, Wigley F, Saria S. Clustering longitudinal clinical marker trajectories from electronic health data. Applications to phenotyping and endotype discovery. In: AAAI, Citeseer; 2015. pp. 2956–64.Google Scholar
  44. 44.
    Nemati S, Adams R. Supervised learning in dynamic bayesian networks. Neural information processing systems (NIPS) workshop on deep learning and representation learning, Montreal; 2014.Google Scholar
  45. 45.
    Luo Y, Xin Y, Joshi R, Celi L, Szolovits P, Predicting ICU. Mortality risk by grouping temporal trends from a multivariate panel of physiologic measurements. In: AAAI, Phoenix; 2016. pp. 42–50.Google Scholar
  46. 46.
    Saria S, Koller D, Penn A. Learning individual and population level traits from clinical temporal data. In: Proceeding of neural information processing systems (NIPS), predictive models in personalized medicine workshop; 2010.Google Scholar
  47. 47.
    Lipton ZC, Kale DC, Wetzell RC. (2015) Phenotyping of clinical time series with LSTM recurrent neural networks. arXiv preprint arXiv:151007641.Google Scholar
  48. 48.
    Lipton ZC, Kale DC, Elkan C, Wetzell R. (2015) Learning to diagnose with LSTM recurrent neural networks. ArXiv e-prints 1511.Google Scholar
  49. 49.
    Kale DC, Gong D, Che Z, Liu Y, Medioni G, Wetzel R, Ross P An examination of multivariate time series hashing with applications to health care. In: Data Mining (ICDM), 2014 IEEE international conference on, 2014. IEEE, pp 260–269.Google Scholar
  50. 50.
    Bahadori MT, Kale DC, Fan Y, Liu Y. Functional subspace clustering with application to time series. In: ICML, Lille; 2015. pp. 228–37.Google Scholar
  51. 51.
    Marlin BM, Kale DC, Khemani RG. Wetzel RC Unsupervised pattern discovery in electronic health care data using probabilistic clustering models. In: Proceedings of the 2nd ACM SIGHIT international health informatics symposium, 2012. ACM, pp 389–98.Google Scholar
  52. 52.
    Rahimi A, Recht B. Random features for large-scale kernel machines. NIPS. 2007;3(4):5.Google Scholar
  53. 53.
    Rahimi A, Recht B. Weighted sums of random kitchen sinks: replacing minimization with randomization in learning. Adv Neural Inform Process Syst. 2008;885:1313–20.Google Scholar
  54. 54.
    Saxe A, Koh PW, Chen Z, Bhand M, Suresh B, Ng AY. (2011) On random weights and unsupervised feature learning. Paper presented at the proceedings of the 28th international conference on machine learning (ICML-11).Google Scholar
  55. 55.
    Johnson AE, Ghassemi MM, Nemati S, Niehaus KE, Clifton DA, Clifford GD. Machine learning and decision support in critical care. Proc IEEE Inst Electr Electron Eng (2016);104(2):444–66. Scholar
  56. 56.
    Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27(8):1226–38. Scholar
  57. 57.
    Ding C, Peng H. Minimum redundancy feature selection from microarray gene expression data. J Bioinform Comput Biol. 2005;3(2):185–205.Google Scholar
  58. 58.
    Peng HC, Ding C, Long FH. Minimum redundancy—maximum relevance feature selection. IEEE Intell Syst. 2005;20(6):70–1.Google Scholar
  59. 59.
    Huang YM, Du SX. (2005) Weighted support vector machine for classification with uneven training class sizes. In: Proceedings of 2005 international conference on machine learning and cybernetics, Guangzhou, vol. 1–9, pp 4365–69.Google Scholar
  60. 60.
    Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–97. Scholar
  61. 61.
    Geladi P, Kowalski BR. Partial least-squares regression: a tutorial. Anal Chim Acta. 1986;185:1–17.Google Scholar
  62. 62.
    Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM T Intel Syst Tec. 2011;2(3):27. Scholar
  63. 63.
    Steyerberg EW, Pencina MJ, Lingsma HF, Kattan MW, Vickers AJ, Van Calster B. Assessing the incremental value of diagnostic and prognostic markers: a review and illustration. Eur J Clin Invest. 2012;42(2):216–28. Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2018

Authors and Affiliations

  • Soojin Park
    • 1
    Email author
  • Murad Megjhani
    • 1
  • Hans-Peter Frey
    • 1
  • Edouard Grave
    • 2
  • Chris Wiggins
    • 3
  • Kalijah L. Terilli
    • 1
  • David J. Roh
    • 1
  • Angela Velazquez
    • 1
  • Sachin Agarwal
    • 1
  • E. Sander ConnollyJr.
    • 4
  • J. Michael Schmidt
    • 1
  • Jan Claassen
    • 1
  • Noemie Elhadad
    • 2
  1. 1.Department of NeurologyColumbia UniversityNew YorkUSA
  2. 2.Department of Biomedical InformaticsColumbia UniversityNew YorkUSA
  3. 3.Department of Applied Physics and Applied MathematicsColumbia UniversityNew YorkUSA
  4. 4.Department of NeurosurgeryColumbia UniversityNew YorkUSA

Personalised recommendations