Demand Forecast Using Data Analytics for the Preallocation of Ambulances

The objective of prehospital emergency medical services (EMSs) is to have a short response time. By increasing the operational efficiency, the survival rate of patients could potentially be increased. The geographic information system (GIS) is introduced in this study to manage and visualize the spatial distribution of demand data and forecasting results. A flexible model is implemented in GIS, through which training data are prepared with user-desired sizes for the spatial grid and discretized temporal steps. We applied moving average, artificial neural network, sinusoidal regression, and support vector regression for the forecasting of prehospital emergency medical demand. The results from these approaches, as a reference, could be used for the preallocation of ambulances. A case study is conducted for the EMS in New Taipei City, where prehospital EMS data have been collected for three years. The model selection process has chosen different models with different input features for the forecast of different areas. The best daily mean absolute percentage error during testing of the EMS demand forecast is 23.01%, which is a reasonable forecast based on Lewis' definition. With the acceptable prediction performance, the proposed approach has its potential to be applied to the current practice.

[1]  Sungjune Park,et al.  EMS call volume predictions: A comparative study , 2009, Comput. Oper. Res..

[2]  Muhammad Tayyab Asif,et al.  Bayesian Support Vector Regression for traffic speed prediction with error bars , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[3]  Poh-Chin Lai,et al.  Weather factors in the short-term forecasting of daily ambulance calls , 2013, International Journal of Biometeorology.

[4]  Rosbi Mamat,et al.  Impact of Ambulance Dispatch Policies on Performance of Emergency Medical Services , 2011, IEEE Transactions on Intelligent Transportation Systems.

[5]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[6]  M. L. Larsen,et al.  FirstAED Emergency Dispatch, Global Positioning of First Responders with Distinct Roles - A Solution to Reduce the Response Times and Ensuring Early Defibrillation in the Rural Area Langeland , 2014 .

[7]  D. Basak,et al.  Support Vector Regression , 2008 .

[8]  Armann Ingolfsson,et al.  The application of forecasting techniques to modeling emergency medical system calls in Calgary, Alberta , 2007, Health care management science.

[9]  R. Lefering,et al.  Pre-hospital rescue times and actions in severe trauma. A comparison between two trauma systems: Germany and the Netherlands. , 2014, Injury.

[10]  Hadi Sadoghi Yazdi,et al.  ECG Arrhythmia Classification with Support Vector Machines and Genetic Algorithm , 2009, 2009 Third UKSim European Symposium on Computer Modeling and Simulation.

[11]  Shane G. Henderson,et al.  Ambulance Service Planning: Simulation and Data Visualisation , 2005 .

[12]  Baxter Larmon,et al.  Are EMS Call Volume Predictions Based on Demand Pattern Analysis Accurate? , 2007, Prehospital emergency care : official journal of the National Association of EMS Physicians and the National Association of State EMS Directors.

[13]  Joseph S. Pliskin,et al.  A geographic information system simulation model of EMS: reducing ambulance response time. , 2004, The American journal of emergency medicine.

[14]  Cem Saydam,et al.  Ambulance Deployment and Shift Scheduling: An Integrated Approach , 2011 .

[15]  Yen-Jen Oyang,et al.  Ambulance Service Area Considering Disaster-Induced Disturbance on the Transportation Infrastructure , 2015 .

[16]  Chuang-Chien Chiu,et al.  Classification of Diabetics with Various Degrees of Autonomic Neuropathy Based on Linear and Nonlinear Features Using Support Vector Machine , 2010, ICMB.

[17]  C. Lewis.  Industrial and business forecasting methods : a practical guide to exponential smoothing and curve fitting , 1982 .

[18]  Jay Fitch.  Response times: myths, measurement & management. , 2005, JEMS : a journal of emergency medical services.

[19]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[20]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[21]  S. S. Mehta,et al.  SVM-based algorithm for recognition of QRS complexes in electrocardiogram , 2008 .

[22]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[23]  F. Lippert,et al.  Evaluation of pre-hospital transport time of stroke patients to thrombolytic treatment , 2014, Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine.

[24]  P. Trudeau,et al.  AN OPERATIONS RESEARCH APPROACH FOR THE PLANNING AND OPERATION OF AN AMBULANCE SERVICE , 1989 .

[25]  Jerzy Krysiński,et al.  Clinical data analysis using artificial neural networks (ANN) and principal component analysis (PCA) of patients with breast cancer after mastectomy , 2007 .

[26]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[27]  G B Hall,et al.  Assessment of ambulance response performance using a geographic information system. , 1999, Social science & medicine.

[28]  Alexander Skabardonis,et al.  A spatial queuing model for the emergency vehicle districting and location problem , 2009 .