Spatial analysis and data mining techniques for identifying risk factors of Out-of-Hospital Cardiac Arrest

Out-of-Hospital Cardiac Arrest (OHCA) is a critical issue of emergency medical service (EMS).Ubiquitous computing technologies could significantly improve the survival rate of OHCA patients.Public health institutions should manage first-aid resources more efficiently and make EMS policies more effectively.New Taipei City, Taiwan was chosen as the scope of this study. Spatial Analysis and Data Mining Techniques were used.Spatial clustering of OHCA events was found. Risk factors to 2-hour survival rate after OHCA were identified. Out-of-Hospital Cardiac Arrest (OHCA) is a critical issue of emergency medical service (EMS). In addition to the first aids given to OHCA patients by witnesses or bystanders, time factors such as arrival of ambulance and transportation from site to EMS are also important. Comprehensive coverage of EMS, especially enhanced by ubiquitous computing technologies, could significantly improve the survival rate of OHCA patients. However, it heavily challenges the resource allocation and management policy in the public health system of a metropolis. ObjectivesIn this study, we first used spatial analysis techniques with a finer granularity to identify high risk areas of OHCA in a metropolis. We then used data mining techniques to elucidate the effects of patients' characteristics, pre-hospital resuscitation treatments, and spatial factors on post-OHCA survivability. With this information, public health institutions can enhance the EMS by allocating properly first-aid resources at the right places to improve the survival rate of OHCA patients. MethodsWe used New Taipei City, Taiwan as the scope of this study. Data of all registered OHCA cases in New Taipei City in 2011 were reviewed retrospectively. The dataset was combined with the National Doorplate Database to enhance the granularity of spatial analyses. Global and local spatial analyses based on Global Moran's Index, Local Moran's Index, and Getis-Ord Gi* statistic were performed to cluster high risk districts for OHCA in New Taipei City. Statistical methods such as Chi-square test, logistic regression, and decision tree were then adopted to analyze factors influencing 2-h survivability after OHCA. ResultsSignificant spatial clustering of OHCA events was found (p<0.05) in the western side of New Taipei City. We found that the 2-h survival rate after OHCA was significantly correlated (p<0.05) with type of OHCA, EMT-P (Emergency Medical Technicians-Paramedic) dispatch, intubation, drug administration, onsite ROSC (Return of Spontaneous Circulation), AED (Automated External Defibrillator) usage, bystander witnessing, AED initial cardiac rhythm, cardiac rhythm recovery before admission, and past histories of diabetes and renal disease. ConclusionsBased on the finding of this study, several important factors of OHCA can be improved to enhance the quality of the EMS service. With the spatial analysis of OHCA hotspots, public health institutions can manage the first-aid resources more efficiently and make EMS policies more effectively. As a result, the survival rate of OHCA patients can be improved.

[1]  Anthony Brown,et al.  Admission glycaemia and its association with acute coronary syndrome in Emergency Department patients with chest pain , 2014, Emergency Medicine Journal.

[2]  Jestin N Carlson,et al.  Comparison of intubation modalities in a simulated cardiac arrest with uninterrupted chest compressions , 2013, Emergency Medicine Journal.

[3]  L. Anselin Local Indicators of Spatial Association—LISA , 2010 .

[4]  D J Roe,et al.  Estimating effectiveness of cardiac arrest interventions: a logistic regression survival model. , 1997, Circulation.

[5]  C. Callaway,et al.  Regional variation in out-of-hospital cardiac arrest incidence and outcome. , 2008, JAMA.

[6]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2014 update: a report from the American Heart Association. , 2014, Circulation.

[7]  Joel Stein,et al.  Executive summary: heart disease and stroke statistics--2014 update: a report from the American Heart Association. , 2014, Circulation.

[8]  Marek R. Ogiela,et al.  Cognitive systems for intelligent business information management in cognitive economy , 2014, Int. J. Inf. Manag..

[9]  Lidia Ogiela,et al.  Cognitive informatics in image semantics description, identification and automatic pattern understanding , 2013, Neurocomputing.

[10]  Richard J. Roiger,et al.  Data Mining: A Tutorial Based Primer , 2002 .

[11]  Conor Deasy,et al.  Out-of-hospital cardiac arrest in Cork, Ireland , 2012, Emergency Medicine Journal.

[12]  M. Kulldorff A spatial scan statistic , 1997 .

[13]  Theodore J Iwashyna,et al.  Small Area Variations in Out-of-Hospital Cardiac Arrest: Does the Neighborhood Matter? , 2010, Annals of Internal Medicine.

[14]  L. Waller,et al.  Applied Spatial Statistics for Public Health Data , 2004 .

[15]  Marcus Eng Hock Ong,et al.  Dynamic ambulance reallocation for the reduction of ambulance response times using system status management. , 2015, The American journal of emergency medicine.

[16]  Marek R. Ogiela,et al.  Semantic Analysis Processes in Advanced Pattern Understanding Systems , 2011 .

[17]  A. Chang,et al.  Relationship between renal dysfunction and outcomes in emergency department patients with potential acute coronary syndromes , 2012, Emergency Medicine Journal.

[18]  Arthur L. Kellermann,et al.  Predictors of Survival From Out-of-Hospital Cardiac Arrest A Systematic Review and Meta-Analysis , 2013 .

[19]  Boller Manuel Will models of naturally occurring disease in animals reduce the bench-to-bedside gap in biomedical research? , 2013, Zhonghua wei zhong bing ji jiu yi xue.

[20]  Comilla Sasson,et al.  Out-of-hospital cardiac arrest surveillance --- Cardiac Arrest Registry to Enhance Survival (CARES), United States, October 1, 2005--December 31, 2010. , 2011, Morbidity and mortality weekly report. Surveillance summaries.

[21]  Åke Grönlund,et al.  Mobile Technologies and Geographic Information Systems to Improve Health Care Systems: A Literature Review , 2014, JMIR mHealth and uHealth.

[22]  Marcus Eng Hock Ong,et al.  Geographic factors are associated with increased risk for out-of hospital cardiac arrests and provision of bystander cardio-pulmonary resuscitation in Singapore. , 2014, Resuscitation.

[23]  Elisabeth Dowling Root,et al.  A tale of two cities: the role of neighborhood socioeconomic status in spatial clustering of bystander CPR in Austin and Houston. , 2013, Resuscitation.

[24]  A. Getis The Analysis of Spatial Association by Use of Distance Statistics , 2010 .

[25]  Benjamin S. Abella,et al.  Increasing cardiopulmonary resuscitation provision in communities with low bystander cardiopulmonary resuscitation rates: a science advisory from the American Heart Association for healthcare providers, policymakers, public health departments, and community leaders. , 2013, Circulation.

[26]  Comilla Sasson,et al.  Multiple cluster analysis for the identification of high-risk census tracts for out-of-hospital cardiac arrest (OHCA) in Denver, Colorado. , 2014, Resuscitation.