Application of Cloud Computing for Emergency Medical Services: A Study of Spatial Analysis and Data Mining Technology
Out of Hospital Cardiac Arrest (OHCA) is an important medical and public health issue. Emergency first aid service prior to hospital admission is an important indicator for the quality evaluation of the emergency medical service. OHCA frequently occurs without warning, and while there are clear steps in emergency first aid concerning the treatment of OHCA patients, their survivability diminishes if they cannot receive emergency first aid services in time. Using statistical methods such as chi-square test, logistic regression, and decision tree, the influence factors were analyzed and extracted. In addition, combining the strengths of three independent spatial clustering analysis methods, namely, the Global Moran’s Index for finding the spatial clustering, as well as the Local Moran’s Index and spatial autocorrelation analysis Getis-Ord Gi* algorithm, a novel summary approach to identify high-risk OHCA areas. The Global Moran’s Index of OHCA event locations were 0.025861, with a Z-score of 8.178045, indicating significance spatial clustering phenomenon of OHCA locations, Getis-Ord Gi* covers more towns (urban areas), but the High-High area reaching statistical standards obtained through the Local Moran’s Index also has also appeared in the high clusters Area found through search using the Getis-Ord Gi*. In addition, the important factors found through the decision tree analysis method have more space distribution coverage. When OHCA occurs, based on findings in this study, the 119-dispatch duty officer may make further inquiries regarding medical history of heart disease or diabetes, which shall serve as a reference for future dispatch of senior technicians. Based on the OHCA-prone hot zone generated by the Getis-Ord Gi* and targeting OHCA patients’ past medical history of heart disease or diabetes, public health units may adopt information technology or wearable devices as intervention in order to increase the probability of eyewitnesses and prioritize the dispatch of emergency aid resources into the hot zone, thereby enhancing OHCA patient survival rates.
KeywordsOut-of-hospital cardiac arrest Cardiopulmonary resuscitation Geographic information systems Spatial statistics Public health interventions
This research was supported by grant entitled “Multidisciplinary Health Cloud Research Program: Technology Development and Application of Big Health Data” from the Academia Sinica. We would also like to express our sincere gratitude to Mr. Kent M. Suárez for his English editing.
The authors declare that we do not have any competing interests related to this study.
- 3.Sasson C, Rogers MA, Dahl J et al (2010) Predictors of survival from out-of-hospital cardiac arrest a systematic review and meta-analysis. Circ Cardiovasc Qual Outcomes 3(1):63–81Google Scholar
- 4.McNally B, Valderrama AL (2011) Out-of-hospital cardiac arrest surveillance: Cardiac Arrest Registry to Enhance Survival (CARES), United States, Oct 1, 2005–Dec 31, 2010Google Scholar
- 5.Manuel B (2013) Will models of naturally occurring disease in animals reduce the bench-to-bedside gap in biomedical research? Zhonghua wei zhong bing ji jiu yi xue 25(1):5–7Google Scholar
- 6.Lee C-K (2010) The Analysis of Ilan’s Out-of-Hospital Cardiac Arrest (OHCA) PatientsGoogle Scholar
- 7.China MoHaWRo. The cause of death statistics. Secondary The cause of death statistics. http://www.mohw.gov.tw/cht/DOS/Statistic.aspx?f_list_no=312. Access date, 2015/05/18
- 9.Sasson C, Keirns CC, Smith D et al (2010) Small area variations in out-of-hospital cardiac arrest: does the neighborhood matter? Ann Internal Med 153(1):19–22Google Scholar
- 11.Sasson C, Meischke H, Abella BS et al (2013) 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. Circulation 127(12):1342–1350CrossRefGoogle Scholar
- 13.Waller LA, Gotway CA (2004) Applied spatial statistics for public health data. Wiley, New YorkGoogle Scholar
- 16.Geatz MW, Roiger R (2011) Data mining: a tutorial based primer. Pearson Education, LondonGoogle Scholar
- 17.Automated icd9-cm coding employing bayesian machine learning: a preliminary exploration. Simposio de Informtica y Salud; 2004Google Scholar
- 18.Hosmer DW Jr, Lemeshow S, Sturdivant RX (2000) Model-building strategies and methods for logistic regression. Third Edition, Applied Logistic Regression, pp 89–151Google Scholar
- 19.Chan T-C, Fu Y-c, Wang D-W, et al (2014) Determinants of receiving the pandemic (H1N1) 2009 vaccine and intention to receive the seasonal influenza vaccine in TaiwanGoogle Scholar
- 20.Gardner LS, Nguyen-Pham S, Greenslade JH et al (2014) Admission glycaemia and its association with acute coronary syndrome in Emergency Department patients with chest pain. Emerg Med J emermed-2014-204046Google Scholar
- 21.Tandon N, McCarthy M, Forehand B et al (2013) Comparison of intubation modalities in a simulated cardiac arrest with uninterrupted chest compressions. Emerg Med J emermed-2013-202783Google Scholar
- 23.Henry K, Murphy A, Willis D et al (2012) Out-of-hospital cardiac arrest in Cork, Ireland. Emerg Med J emermed-2011-200888Google Scholar
- 26.Nhavoto JA, Grönlund Å (2014) Mobile technologies and geographic information systems to improve health care systems: a literature review. JMIR mHealth and uHealth 2(2)Google Scholar