The Real-Time Tracking and Alarming the Early Neurological Deterioration Using Continuous Blood Pressure Monitoring in Patient with Acute Ischemic Stroke

  • Youngjo Lee
  • Maengseok Noh
  • Il Do Ha
Conference paper
Part of the ICSA Book Series in Statistics book series (ICSABSS)


In this paper, we develop a real-time prediction of END (Early Neurological Deterioration) using continuous BP (blood pressure) monitoring and clinical parameters and propose to set up an alarming criterion before END. We identified consecutive ischemic stroke patients hospitalized within 48 h of symptom onset from a prospective stroke registry database. BP data during hospitalization were obtained from the electric medical records. Probability of END at each time point of BP measurement was estimated using a logistic model with covariates, which is derived from two models for clinical information and BP parameters. Here, a model for clinical information was fitted using logistic model with clinical characteristics of patients to predict END. A model for BP was fitted using random effects models allowing for temporal correlations at each time point of BP measurement with irregular intervals. Prediction performance was evaluated by sensitivity and specificity. An alarm criterion for a high probability of END at each time point was defined as being above a cutoff point prior to 24 h.


  1. Ay, H., Gungor, L., & Arsava, E. M. (2010). A score to predict early risk of recurrence after ischemic stroke. Neurology, 74, 128–135.CrossRefGoogle Scholar
  2. Jenkins, P. F., Thompson, C. H., & Barton, L. L. (2011). Clinical deterioration in the condition of patients with acute medical illness in Australian hospitals: improving detection and response. Medical Journal of Australia, 194, 596–598.Google Scholar
  3. Lee, Y., & Nelder, J. A. (1996). Hierarchical generalized linear models (with discussion). Journal of the Royal Statistical Society B, 58, 619–678.MathSciNetzbMATHGoogle Scholar
  4. Lee, Y., & Nelder, J. A. (2001). Hierarchical generalised linear models: a synthesis of generalised linear models, random-effect model and structured dispersion. Biometrika, 88, 987–1006.MathSciNetCrossRefzbMATHGoogle Scholar
  5. Lee, Y., Nelder, J. A., & Pawitan, Y. (2017). Generalized Linear Models with Random Effects: Unified Analysis via H-likelihood (2nd ed.). Boca Raton: Chapman & Hall/CRC.Google Scholar
  6. Ois, A., Martinez-Rodriguez, J. E., & Munteis, E. (2008). Steno-occlusive arterial disease and early neurological deterioration in acute ischemic stroke. Cerebrovascular Diseases, 25, 151–156.CrossRefGoogle Scholar
  7. Roquer, J., Rodrguez-Campello, A., & Gomis, M. (2008). Acute stroke unit care and early neurological deterioration in ischemic stroke. Journal of Neurology, 255, 1012–1017.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of StatisticsSeoul National UniversitySeoulKorea
  2. 2.Department of StatisticsPukyong National UniversityBusanKorea

Personalised recommendations