Early Prediction of Cardiac Arrest (Code Blue) using Electronic Medical Records

@article{Somanchi2015EarlyPO,
  title={Early Prediction of Cardiac Arrest (Code Blue) using Electronic Medical Records},
  author={Sriram Somanchi and Samrachana Adhikari and Allen Lin and Elena Eneva and Rayid Ghani},
  journal={Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2015}
}
  • S. Somanchi, Samrachana Adhikari, +2 authors R. Ghani
  • Published 2015
  • Medicine, Computer Science
  • Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Code Blue is an emergency code used in hospitals to indicate when a patient goes into cardiac arrest and needs resuscitation. [...] Key Result Based on these results, this system is now being considered for deployment in hospital settings.Expand

Figures and Topics from this paper

Sudden Cardiac Arrest Prediction Using Predictive Analytics
TLDR
A framework is proposed that can be implemented for emergency situations of people with such medical history and these raw datasets are further analyzed at scratch to predict the upcoming life threatening pain that might cause death. Expand
An intelligent warning model for early prediction of cardiac arrest in sepsis patients
TLDR
The proposed model predicts the arrest incidence of up to six hours earlier with the accuracy and sensitivity over 70% and illustrated that machine learning techniques, especially ensemble algorithms have high potentials to be used in prognostic systems for sepsis patients. Expand
Development and Use of a Tablet-based Resuscitation Sheet for Improving Outcomes during Intensive Patient Care
TLDR
The design of a tablet-based application and its use by 20 nurses at the Mayo Clinic hospital showed that the nurses preferred the tablet application over the paper based form, and a qualitative survey showed the clinicians perceived the electronic version to be more accurate and efficient than paper-based documentation. Expand
Toward analyzing and synthesizing previous research in early prediction of cardiac arrest using machine learning based on a multi-layered integrative framework
TLDR
A systematic review of cardiac arrest prediction studies carried out through Pubmed, ScienceDirect, Google Scholar and SpringerLink databases illustrated the prediction capability of machine learning methods in predicting cardiac arrest. Expand
Proposed Model/Framework to Avoid Sudden Cardiac Arrest (SCA) and Sudden Cardiac Death (SCD) at Early Stage
TLDR
Various factors and parameters deciding the health of the human heart including strong family history of CVD or SCD, physical activity, proper nutrition, balanced diet, early follow-up of the Health of human heart, etc., in order to avoid heart disease risks at early stages are emphasized. Expand
Prediction of In-Hospital Cardiac Arrest Using Shallow and Deep Learning
TLDR
The proposed Logistic Regression demonstrated a higher positive predictive value and sensitivity than traditional early warning systems. Expand
Predicting Hospital Readmission via Cost-Sensitive Deep Learning
TLDR
It is found that early prediction of readmission is possible and when compared with state-of-the-art existing methods used by hospitals, the methods perform significantly better. Expand
Fuzzy risk stratification and risk assessment model for clinical monitoring in the ICU
  • A. Dervishi
  • Medicine, Computer Science
  • Comput. Biol. Medicine
  • 2017
TLDR
The potential for using models in risk assessment to estimate a patient's physiological status, stable or deteriorating, within 4 h has been demonstrated and the impact on clinical outcomes is evaluated. Expand
Cost-sensitive Deep Learning for Early Readmission Prediction at A Major Hospital
With increased use of electronic medical records (EMRs), data mining on medical data has great potential to improve the quality of hospital treatment and increase the survival rate of patients. EarlyExpand
Mining Electronic Health Records (EHRs)
TLDR
A structured and comprehensive overview of data mining techniques for modeling EHRs is provided and a detailed understanding of the major application areas to which EHR mining has been applied is provided. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 14 REFERENCES
Predicting cardiac arrest on the wards: a nested case-control study.
TLDR
The MEWS was significantly different between patients experiencing CA and control patients by 48 h prior to the event, but includes poor predictors of CA such as temperature and omits significant predictors such as diastolic BP and pulse pressure index. Expand
Predicting out of intensive care unit cardiopulmonary arrest or death using electronic medical record data
TLDR
An automated model harnessing EMR data offers great potential for identifying RED and was superior to both a prior risk model and the human judgment-driven RRT. Expand
Validation of a modified Early Warning Score in medical admissions.
TLDR
The ability of a modified Early Warning Score (MEWS) to identify medical patients at risk of catastrophic deterioration in a busy clinical area was investigated and could be created, using nurse practitioners and/or critical care physicians, to respond to high scores and intervene with appropriate changes in clinical management. Expand
Hospital-wide code rates and mortality before and after implementation of a rapid response team.
TLDR
In this large single-institution study, rapid response team implementation was not associated with reductions in hospital-wide code rates or mortality. Expand
Recognising clinical instability in hospital patients before cardiac arrest or unplanned admission to intensive care: A pilot study in a tertiary‐care hospital
TLDR
To investigate the nature and duration of clinical instability in hospital patients before a “critical event” (ie, a cardiac arrest or an unplanned admission to intensive care). Expand
Rapid-response teams.
TLDR
The prevalence and consequences of sudden critical illness outside the ICU is described and the rationale for rapid-response systems is discussed. Expand
Effective Probability Forecasting for Time Series Data Using Standard Machine Learning Techniques
TLDR
It is demonstrated that effective probability forecasts can be generated on time series data and the practical implications of this are discussed. Expand
1 Trend Filtering
TLDR
This paper proposes a variation on Hodrick-Prescott (H-P) filtering, a widely used method for trend estimation that substitutes a sum of absolute values for the sum of squares used in H-P filtering to penalize variations in the estimated trend. Expand
The Elements of Statistical Learning
  • E. Ziegel
  • Computer Science, Mathematics
  • Technometrics
  • 2003
TLDR
Chapter 11 includes more case studies in other areas, ranging from manufacturing to marketing research, and a detailed comparison with other diagnostic tools, such as logistic regression and tree-based methods. Expand
Segmenting Time Series: A Survey and Novel Approach
TLDR
This paper undertake the first extensive review and empirical comparison of all proposed techniques for mining time series data and introduces a novel algorithm that is empirically show to be superior to all others in the literature. Expand
...
1
2
...