Spatial analysis and data mining techniques for identifying risk factors of Out-of-Hospital Cardiac Arrest
Journal
International Journal of Information Management
Journal Volume
37
Journal Issue
1
Pages
1528-1538
Date Issued
2017
Author(s)
Abstract
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. Objectives In 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. Methods We 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. Results Significant 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. Conclusions Based 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. © 2016 Elsevier Ltd
Other Subjects
Decision trees; Defibrillators; Emergency services; Factor analysis; Heart; Hospitals; Medical computing; Public health; Resuscitation; Risk assessment; Spatial variables measurement; Statistical tests; Ubiquitous computing; Automated external defibrillator; Cardiac arrest; Emergency medical services; Emergency medical technicians; Public health systems; Resource allocation and management; Spatial analysis; Ubiquitous computing technology; Data mining
Type
journal article