The Statistical Analysis of Patients Clinical Data in Emergency Department by Using Hospital Information System using bigdata

ABSTRACT:
Using hospital information system (HIS) to classify the patients who were treated in the emergency department and discuss the spectrum of diseases. We collected the clinical information of the patients who were treated in the emergence department from July 1, 2010 to June 30, 2011. The patients were divided into different groups by their disease, and analyzed the numbers and frequencies of each subgroup. From the data of 12 months, we concluded that the most frequencies of diseases are cardiovascular diseases, respiratory diseases, neurological diseases and digestive diseases. There were no significant difference among the first three diseases, but the patient’s number of digestive diseases was increased in the winter. And the mortality of critical patients in January and February was higher than other months. In proposed Work we have used 911(Emergency Helpline Number) Dataset to predict the reasons of calling the emergency number.
EXISTING SYSTEM

1. Using hospital information system (HIS) to classify the patients who were treated in the emergency department and discuss the spectrum of diseases.
2. We collected the clinical information of the patients who were treated in the emergence department from July 1, 2010 to June 30, 2011.
3. The patients were divided into different groups by their disease, and analyzed the numbers and frequencies of each subgroup.
4. From the data of 12 months, we concluded that the most frequencies of diseases are cardiovascular diseases, respiratory diseases, neurological diseases and digestive diseases. There were no significant difference among the first three diseases
5. but the patients number of digestive diseases were increased in the winter. And the mortality of critical patients in January and February was higher than other months.
6. The increasing patients number of cardio-cerebrovascular diseases was corresponding to the increasing of aging population, and there were no difference in 12 months. The increasing number of digestive diseases between December to February maybe associated with diet change. The mortality of critical patients in January and February was higher than other months.

DISADVANTAGE:

1. Hospital system dataset has been collected to analysis disease. So, prediction on this not so accurate.

PROPOSED WORK:

1. We will be performing analysis on the data provided the callers who had called the emergency helpline number in North America.
2. In many countries, the public telephone network has a single emergency telephone number (sometimes known as the universal emergency telephone number or the emergency services number) that allows a caller to contact local emergency services for assistance. This emergency number differs from country to country and typically consists of three digits numbers that can be easily remembered and dialed quickly. Some countries have a different emergency number for each of the different emergency services.
3. Here we have two data sets; one is the data that the callers have given when they called the emergency helpline number. The other data set contains the details about the zip code. 
4. The data description for 911 lat, lng, desc, zip, title, timestamp, twp, addr, e. The data description for zip code zip, city, state, latitude, timezone, dst
5. We will use scala & spark code for parsing the data into a dataframe. Here, we are joining the datasets by keeping the key as zipcode, so that we can get the city and the state from where we are getting the call.
6. Using this we will find what kind of problems are prevalent, and in which state and What kind of problems are prevalent, and in which city

ADVANTAGE :

1. The exact 911 dataset is used here for classification so prediction accuracy is good
2. We use hadoop as framework to store dataset. so we can store large datasets to get exact accuracy of our classification


SYSTEM ARCHITECTURE

SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:

System : INTEL I3
Hard Disk            : 500 GB.
Mouse : Logitech.
Ram : 4GB.
Operating system             :          64-bit.

SOFTWARE REQUIREMENTS:

Operating system : Linux.
Coding Language : spark
Database : HDFS
TOOL                    :         Spark  
Algorithm              :         Map-reduce              


REFERENCES:

[1] Khan S, Maclean CD, Littenberg B. The effect of the Vermont Diabetes Information System on inpatient and emergency room use: results from a randomized trial. Health Outcomes Res Med. 2010; 1: e61-e66.
[2] Xu XD, Mao Ym, Liu T, et al. Structure design and analysis on outpatient emergency care information system. Chinese Medical Equiment Journal. 2007; 28: 45-47.
[3] Ding F, Hu CL, Li Q. The emergency attendance in one tertiary first-class hospital on major public holidays. Modern Preventive Medicine. 2008; 35: 4116-4117.