Mr, Ankit (2017) Data Analytics in Healthcare. MTech thesis.
|PDF (Full text is restriced upto 17.01.2020) |
Restricted to Repository staff only
Data Analytics in healthcare assumes to be a viable part in performing significant constant examination on the colossal volume of information and ready to foresee the crisis circumstances before it happens. It depicts about the huge information utilize cases in social insurance and government. Enormous information is one of the most recent advances that have the potential for drastically changing the way associations utilize data to improve the client encounter and change their plans of action. The medicinal services industry has been taking care of a lot of information and is to a great extent driven by consistence, administrative prerequisites, record keeping and comparable parts of patient care.
The objective is to acquaint Healthcare experts and professionals with the headways in the registering field to viably deal with information and make deductions from huge and heterogeneous medicinal services information. Data mining is the way toward removing concealed data from enormous dataset, sorting legitimate and special examples in information. There are numerous data mining procedures like clustering, classification, association analysis, regression and so forth. Data mining concerns hypotheses, methodology, and specifically, PC frameworks for knowledge extraction or mining from a large set of information. Association rule mining is a broadly useful rule discovery scheme. It has been generally utilized for finding rules in medicinal applications. The determination of maladies is a huge also, dull undertaking in prescription.
The primal focus of this thesis is predicting a particular disease using such enormous data, using the above mentioned data mining techniques, pre- processing (data cleaning, data reduction, etc.), classification, analysis, etc. On the basis of several dataset properties, the handling of the data becomes unique and independent. Few of the common diseases namely, diabetes, chronic kidney disease, Parkinson’s disease, have been processed using these data mining and machine learning techniques. Every possible dataset structure has been analyzed and corresponding pre- processing and classification technique been developed. Later their structural as well as behavioural traits are being analyzed. At the end, detailed analysis on few particular diseases are carried out.
|Item Type:||Thesis (MTech)|
|Uncontrolled Keywords:||Data cleaning; Data reduction; Data mining;Classification; Diagnosis of diseases|
|Subjects:||Engineering and Technology > Computer and Information Science > Data Mining|
Engineering and Technology > Computer and Information Science
|Divisions:||Engineering and Technology > Department of Computer Science|
|Deposited By:||Mr. Kshirod Das|
|Deposited On:||07 Mar 2018 14:55|
|Last Modified:||07 Mar 2018 14:55|
Repository Staff Only: item control page