Page 245 - Big Data Analytics for Intelligent Healthcare Management

238 CHAPTER 9 INTELLIGENCE-BASED HEALTH RECOMMENDATION SYSTEM

• Physical exercise: generating recommendations on what type of yoga and physical exercise the
patients should do for quick recovery based on users’ requirements. The user requirements may
include location, disease-related, weather, etc.
• Diagnosis: generating recommendations on the diagnosis of patients by the doctor based on
symptoms shown in similar cases.
• Therapy/Medication: generating recommendations about different types of medication for a
particular disease or patient-specific therapy.
The second part of the framework is the data analysis process. During the data analysis process, health-
specific recommendations can be generated. We should first talk about users who will be using this
domain. The end users of the system are medical researchers, doctors, and patients. Apart from these
end users, there are other people who can benefit from the HRS such as pharmacists, clinicians, and
researchers. Minimizing the cost of healthcare could be the ultimate aim of these recommendation sys-
tems. Analytical methods involve the Hadoop approach that uses MapReduce. This approach increases
the speed of medical diagnosis and finding the optimal parameters for doctors so that he/she can detect
the type of disease the patient is suffering from and check the condition of the patient.
The third part of the framework is visualization. This part contains elements that affect how recom-
mended items should be presented. Visualization and knowledge representation techniques are used to
present the mined knowledge to the end users. The healthiest recommendation is the one that should be
chosen, but sometimes topic-specific criteria play a role in evaluating a product. Data-driven ap-
proaches apply data mining and machine learning methods to extract insights from the heterogeneous
data. It provides individual recommendations based on the past learning experience and the patterns
extracted from clinical data. Combination of information retrieval and machine learning can be used
for medical database classification. The entire framework of the HRS comprises of the following
stages:

i. Training phase
ii. Patient profile generation
iii. Sentiment analysis
iv. Recommendation
v. Privacy preservation

i. Training phase
In order to detect various diseases such as T.B., cholera, flu, etc. doctors organize clinical tests on
patients. Therefore, to study and analyze various diseases and find a cure for the same, doctors require
information through parameters and variables. Moreover, there is tremendous growth in the quantities
of information being generated in healthcare. This phase includes data collection and accumulation.
But the absence of proper tools for collection and accumulation of data will hamper the whole process.
The whole process includes collecting various data and information of patients, demographic
information of patients, diagnoses, research, clinical tests, patient’s health record, real-time data from
hospitals and clinics so that real-time data collection can enhance the effectiveness of the
recommendation.

ii. Patient profile generation
During this stage, for every patient, the user profile is created, which contains various information. For
every user, there will be a health record with the patients’ clinical history. This record contains