Health Analytics Optimization for Enhanced Patient

Care data

Batch Members(Reg No)

1.Johnson Dass Christo(113320106017)
2.Thillai Krishna(113320106046)
3.Akash(113320106002)

Project Guide
Mrs.D.Jeyamani Latha
Associate Professor/ECE
 Outline
• Introduction
• Literature Survey
• Existing method
• Objective
• Block diagram
• Project Model ( Simulation/Hardware model)
• Summary
• References

•
 Introduction
• Today’s healthcare industries are moving from volume-based business into value-based
business, which requires an overwork from doctors and nurses to be more productive
and efficient. This will improve healthcare practice, changing individual life style and
driving them into longer life, prevent diseases, illnesses and infections.
• Over the last few years, healthcare data has become more complex for the reason that
large amount of data are being available lately, along with the rapid change of
technologies and mobile applications and new diseases have discovered.
• Therefore, healthcare sectors have believed that healthcare data analytics tools are really
important subject in order to manage a large amount of complex data, which can lead
to improve healthcare industries and help medical practice to reach a high level of
efficiency and work flow accuracy.
• Healthcare data analytics techniques are not efficient enough and suitable anymore these
days in order to manage big data issue and improve healthcare data analytics due to the
rapid growth and evolution of technology
• In order to meet our goals, we should work on critically weaknesses, disadvantages,
problems and gaps of traditional healthcare data analytics techniques in order to
manage healthcare big data
 Literature Survey 1
Predictive analysis of heart diseases with machine learning approaches TR Ramesh,
Umesh Kumar Lilhore, M Poongodi, Sarita Simaiya, Amandeep Kaur, Mounir Hamdi
Malaysian Journal of Computer Science, 132-148, 2022
Proposed Method:

Predictive analytics may be more effective when combined with structured and
unstructured EHR data. Clinical events can be extracted from EHR data, and
comparable phrases can be categorized in semantic space. By concatenating
their representation using semantic space, structured and unstructured data
are integrated more efficiently than if the occurrences are represented
separately. Using semantic spaces to extract clinical language from EHR, diverse
and distributed representations can predict clinical outcomes effectively.
Various types of information can be collected from health records for purposes
such as pharmacovigilance, phenotyping, and illness detection. Data from EHRs,
EMRs, PHRs, and omics provide a a wealth of information for many different
medical fields.
 Literature Survey 2
A comprehensive survey on machine learning-based big data analytics for IoT-enabled smart
healthcare system Wei Li, Yuanbo Chai, Fazlullah Khan, Syed Rooh Ullah Jan, Sahil Verma,
Varun G Menon, fnm Kavita, Xingwang Li ,Mobile networks and applications 26, 234-252,
2021.
•

Proposed Method:
Multiple forms of healthcare data include biomedical signals, genomic data, sensing data,
biomedical images, and social media. Genomic data analysis lets someone realize more
about genetic markers, disease condition, consanguinity, and mutations; clinical text mining
converts data from practical medical notes from disorganized format to applicable
information, extraction of information, and natural language processing which extract helpful
information from the massive volume of practical text. Social network analytics such as Web
logs, Twitter, Facebook, social networking sites, and search engines helps to discover new
health methods and worldwide health issues and trends based on different social media
sources before analyzing the severity of the disease; therefore, reasonable diagnostic
patterns should be used.
Overall Inference from Literature Survey
●
Literature ●
Literature
Survey 1 Survey 2
●
Method adopted ●
Predictive ●
Genomic
●
analysis data analysis
●
Advantage ●
Improved ●
Various
Patient types of
Outcomes: information
Enhanced can be
decision- collected
making from health
based on records
data-driven
●
Limitation ●
Incomplete ●
Healthcare
or data often
inaccurate contains
data can sensitive
 Existing Method
• One existing method in healthcare data analytics involves
using machine learning algorithms to analyze patient data,
identify patterns, and predict health outcomes. These
algorithms can assist in early disease detection,
personalized treatment plans, and resource optimization
within healthcare systems.
• EHRs are a means to store patient-related data in an
organized manner. They are like digital records that can be
accessed anytime by the concerned parties for the patient's
treatment. EHRs usually store data such as past medical
history, allergies, lab results, doctors' diagnoses, etc.
• Using statistical algorithms and machine learning models to
forecast future outcomes, like predicting patient
readmissions or identifying individuals at risk of developing
certain conditions.
 Objective
• The objective of patient healthcare data analytics is to extract
valuable insights from diverse healthcare data sources,
enhancing decision-making, optimizing resource allocation,
improving patient outcomes, and ultimately advancing the
overall quality and efficiency of healthcare delivery.
• Anticipating and preventing potential health issues by
analyzing historical data and identifying risk factors.
• Tailoring treatments based on individual patient data to
optimize efficacy and minimize side effects.
• Monitoring and improving the quality of healthcare services
through data-driven assessments and feedback loops.
Block diagram
 Design Equations

K-means Clustering

K-Means Clustering is an Unsupervised Machine Learning

algorithm, which groups the unlabeled dataset into different
clusters.
Project Model
 Work Plan

●
WORK ●
PERIOD

●
Literature survey ●
1/2/24-7/2/24
●
Design of block
diagram ●
10/2/24-12/2/24
●
Algorithm
implementation ●
12/2/24-19/2/24
●
Design and error of
code ●
19/2/24-29/2/24
●
Acquiring of dataset ●
1/3/24-10/3/24
 Summary
• Healthcare has evolved with the development of technology to improve
the quality of life and save lives. Today, big data is considered as one of
the most essential and promising future technology areas and has
been attracting the medical community’s attention.
• As a result of big data, we can improve patient outcomes, personalize
care, improve relationships between the patient and the provider, and
decrease hospital costs.
• The effect of big data is very large since medical societies are known for
their size, diversity of complexity, and a high degree of dynamism.
• Big data has been discussed from different viewpoints in recent years,
protecting its involvement in many aspects, specifically those related to
the healthcare system.
• Assembling health information, sharing data, and integrating health are
essential in spreading health care
 References

1. Gillum RF. From papyrus to the electronic tablet: a brief history of the clinical
medical record with lessons for the digital Age. Am J Med. 2013;126(10):853–7.
2. Nasi G, Cucciniello M, Guerrazzi C. The role of mobile technologies in health care
processes: the case of cancer supportive care. J Med Internet Res.
2015;17(2):e26.
3. Stephens ZD, et al. Big data: astronomical or genomical? PLoS Biol.
2015;13(7):e1002195.
4. Reisman M. EHRs: the challenge of making electronic data usable and interoperable.
Pharm Ther. 2017;42(9):572–5.
5. Mauro AD, Greco M, Grimaldi M. A formal definition of big data based on its
essential features. Libr Rev. 2016;65(3):122–35..
6.
7.
•
•
THANK YOU
•