CARE COLLEGE OF ENGINEERING, TRICHY

DEPARTMENT OF AI&DS

2023-24 (Even) III year/ VI sem Elective paper

AD3002 – Health Care Analytics

Lecture
Unit -3 Healthcare Management 1
No
Topic IOT -Definition, Architecture, application
Bloom’s
Learning Outcome (LO) At the end of this lecture, students will be able to
Knowledge Level
LO1 Define IOT K1
LO2 Describe IOT healthcare architecture K1
LO3 Explain the various application of IOT devices in healthcare K2
LO4 Explain IOT devices feature K2

IOT:

Internet of Things (IoT) technologies in healthcare, often referred to as IoT in Healthcare (IoT-
HC) or Healthcare IoT (HIoT), offer numerous benefits and applications to improve patient care,
enhance efficiency, and streamline healthcare processes. Here are some key areas where IoT is
making a significant impact in healthcare:

IoT technology brings numerous applications in healthcare, from remote monitoring to smart
sensors to medical device integration. It keeps the patients safe and healthy as well as
improves the physician delivers care towards the patients.

Healthcare devices collect diverse data from a large set of real-world cases that increases the
accuracy and the size of medical data.

Factor affecting IoT Healthcare Application

There are various factors that affect the IoT healthcare application. Some of them are mention
below:
Continuous Research: It requires continuous research in every field (smart devices, fast
communication channel, etc.) of healthcare to provide a fast and better facility for patients.
Smart Devices: Need to use the smart device in the healthcare system. IoT opens the potential of
current technology and leads us toward new and better medical device solutions.
Better Care: Using IoT technology, healthcare professionals get the enormous data of the patient,
analysis the data and facilitate better care to the patient.
Medical Information Distribution: IoT technology makes a transparency of information and
distributes the accurate and current information to patients. This leads the fewer accidents from
miscommunication, better preventive care, and improved patient satisfaction.

Simple Healthcare System Architecture

The application of the Internet of Things (IoT ) in healthcare transforms it into more smart, fast and
more accurate. There is different IoT architecture in healthcare that brings start health care system.

Product Infrastructure: IoT product infrastructure such as hardware/software component read the
sensors signals and display them to a dedicated device.

Sensors: IoT in healthcare has different sensors devices such as pulse-oximeter, electrocardiogram,
thermometer, fluid level sensor, sphygmomanometer (blood pressure) that read the current patient
situation (data).

Connectivity: IoT system provides better connectivity (using Bluetooth, WiFi, etc.) of devices or
sensors from microcontroller to server and vice-versa to read data.

Analytics: Healthcare system analyzes the data from sensors and correlates to get healthy
parameters of the patient and on the basis of their analyze data they can upgrade the patient health.

Application Platform: IoT system access information to healthcare professionals on their monitor
device for all patients with all details.
IoT challenges in Healthcare
Data security & privacy
Integration: multiple devices & protocols
Data overload & accuracy
Cost

Advantages and Disadvantages of (IoT)

Any technology available today has not reached to its 100 % capability. It always has a gap to go.
So, we can say that Internet of Things has a significant technology in a world that can help other
technologies to reach its accurate and complete 100 % capability as well.
Advantages of IoT

Efficient resource utilization: If we know the functionality and the way that how each device
work we definitely increase the efficient resource utilization as well as monitor natural resources.
Minimize human effort: As the devices of IoT interact and communicate with each other and do
lot of task for us, then they minimize the human effort.
Save time: As it reduces the human effort then it definitely saves out time. Time is the primary
factor which can save through IoT platform.
Enhance Data Collection:
Improve security: Now, if we have a system that all these things are interconnected then we can
make the system more secure and efficient.

Disadvantages of IoT
Security: As the IoT systems are interconnected and communicate over networks. The system
offers little control despite any security measures, and it can be lead the various kinds of network
attacks.
Privacy: Even without the active participation on the user, the IoT system provides substantial
personal data in maximum detail.
Complexity: The designing, developing, and maintaining and enabling the large technology to IoT
system is quite complicated.
Remote Patient Monitoring:

Wearable Devices: IoT-enabled wearable devices can monitor and transmit real-time health data,
such as heart rate, blood pressure, glucose levels, and activity levels, to healthcare providers. This
allows for continuous monitoring of patients outside of traditional healthcare settings.
Smart Health Devices: Devices like smart inhalers, glucometers, and blood pressure monitors
connected to the IoT can provide healthcare professionals with valuable data for proactive patient
management.
Telemedicine and Virtual Care:

IoT Sensors and Cameras: Integrating IoT devices into telehealth solutions allows for remote
patient assessments. Sensors and cameras can provide real-time data, enabling healthcare
professionals to monitor patients and make informed decisions during virtual consultations.
Hospital Asset Management:

RFID Tags and IoT Sensors: Hospitals can use IoT technologies to track the location and status of
medical equipment, medications, and other assets. This helps in reducing equipment downtime,
minimizing losses, and optimizing resource allocation.
• Smart Hospitals:

Building Automation Systems: IoT in healthcare extends to building management systems that
optimize energy usage, ensure patient comfort, and enhance the overall efficiency of hospital
operations. Smart lighting, temperature control, and security systems contribute to a more patient-
friendly environment.

Medication Adherence:

Smart Pill Dispensers: IoT devices can be used to monitor and enhance medication adherence.
Smart pill dispensers remind patients to take medications on time, and healthcare providers can
receive alerts if a patient misses a dose.
Supply Chain Management:

IoT-enabled Tracking: Ensuring the proper storage and transportation of medical supplies and
pharmaceuticals is crucial. IoT sensors can monitor temperature, humidity, and other conditions
during transit to maintain the integrity of medical products.
Chronic Disease Management:

IoT-enabled Implants and Devices: Implantable IoT devices can continuously monitor patients
with chronic conditions and transmit data to healthcare providers. This enables early detection of
issues and timely intervention.

Fall Detection and Elderly Care:

Wearable Sensors and Smart Homes: IoT sensors can be used to detect falls or changes in
activity patterns, especially in elderly populations. Smart home devices can help create a safe
environment for seniors and provide caregivers with insights into their well-being.
Data Analytics and Predictive Healthcare:

Big Data and Analytics Platforms: IoT-generated data can be analyzed to identify patterns,
predict disease outbreaks, and optimize treatment plans. Machine learning algorithms applied to
large datasets can offer valuable insights for personalized healthcare.

Implementing IoT in healthcare requires careful consideration of security and privacy concerns to
ensure the confidentiality and integrity of patient data. Standards and regulations, such as the Health
Insurance Portability and Accountability Act (HIPAA) in the United States, play a critical role in
guiding the secure deployment of IoT solutions in healthcare environments.

Assessment questions to the lecture

Bloom’s
Qn
Question Answer Knowledge
No
Level
1. How does the Internet of Things (IoT) contribute
to healthcare analytics?
A Remembering
A) By providing real-time data from connected
devices for monitoring and analysis
B) By enhancing the security of healthcare data
C) By automating administrative tasks in
healthcare organizations
D) By creating virtual healthcare simulations for
training purposes

Which aspect of IoT in healthcare involves the B Remembering

2. pairing of patients' health conditions with
appropriate interventions or responses through
connected devices?
A) Device Synchronization
B) Condition Matching
C) Health Integration
D) Adaptive Networking
3. Match the following:
i.A, Remembering
i. Wearable Sensors– A. Monitoring vital signs such ii.C,
as heart rate and activity levels iii.B,
ii. Smart Pill Dispensers–B. Remotely tracking the iv.D
location and condition of medical equipment.
iii. Remote Patient Monitoring Devices– c.
Dispensing medication doses according to a
prescribed schedule.
iv. IoT-enabled Medical Imaging Devices- d.
 Capturing and transmitting real-time images for
diagnostic purposes.

A. 1A, 2C, 3B, 4D

B. 1B, 2A, 3D, 4C
C. 1C, 2B, 3A, 4D
D. 1D, 2C, 3A, 4B

Students have to prepare answers for the following questions at the end of the lecture

Marks CO Bloom’s
Qn
Question Knowledge
No
Level
1. What is IOT in Healthcare 2 1 K1
2, List out the healthcare application for an IOT devices 2 1 K1
3. Explain in detail of IOT in healthcare architecture 13 1 K2
4. Discuss in detail of IOT in healthcare 13 1 K2

Reference Book:
 CARE COLLEGE OF ENGINEERING, TRICHY
DEPARTMENT OF AI&DS

2023-24 (Even) III year/ VI sem Elective paper

AD3002 – Health Care Analytics

Lecture
Unit -3 Healthcare Management 2
No
Topic Migration of healthcare Relational database to NoSQL Cloud Database
Bloom’s
Learning Outcome (LO) At the end of this lecture, students will be able to
Knowledge Level
LO1 Define NOSQL Database. K1
LO2 Differentiate RDBMS and NoSQL database K1
LO3 Discuss the importance of migration from RDBMS to NOSQL K2
LO4 Identify the application of NoSQL K1

NoSQL Database
NoSQL databases, often interpreted as "Not Only SQL," are a class of database management
systems that differ from traditional relational databases. They are designed to handle various types
of data, including structured, semi-structured, and unstructured data. NoSQL databases provide a
flexible and scalable solution for managing large volumes of diverse data in distributed
environments.
In healthcare we migrate from Relational Database to NoSQL (Non Relational SQL) cloud
database. Here are some common reasons for migrating from a relational database to a NoSQL
database:

Flexible Schema:

• Relational Database (RDBMS): Requires a predefined schema with a fixed structure. Any
changes to the schema may require altering tables, which can be a time-consuming process.
o NoSQL Database: Offers flexible schema design, allowing for dynamic changes to data
structures. This flexibility is particularly beneficial in scenarios where the data model
evolves frequently.
Scalability:

• Relational Database (RDBMS): Scaling vertically (adding more resources to a single server)
is a common approach. This has limitations and can become expensive.
o NoSQL Database: Designed to scale horizontally by adding more servers to a distributed
system. This makes it easier to handle large volumes of data and traffic, providing better
scalability.
Performance:
 • Relational Database (RDBMS): Well-suited for complex queries and transactions but may
face challenges with read and write scalability in high-traffic scenarios.
o NoSQL Database: Optimized for specific use cases, offering high performance for read and
write operations, especially in scenarios where quick access to large amounts of data is
crucial.

Big Data and Unstructured Data:

• Relational Database (RDBMS): Traditional databases may struggle to handle large volumes
of unstructured or semi-structured data.
o NoSQL Database: Well-suited for handling various types of data, including unstructured or
semi-structured data often associated with big data analytics and real-time applications.
Agile Development and Rapid Prototyping:

• Relational Database (RDBMS): Schemas can create obstacles in agile development

environments where requirements change frequently.
o NoSQL Database: Allows for quick prototyping and adaptation to changing requirements
due to its schema-less nature.

Cost Efficiency:
• Relational Database (RDBMS): Licensing costs and hardware requirements can be high,
especially as data volumes grow.
o NoSQL Database: Often more cost-effective for scaling horizontally as it can leverage
commodity hardware and open-source software.

High Availability and Fault Tolerance:

• Relational Database (RDBMS): Achieving high availability and fault tolerance can be
challenging without significant investment in replication and clustering.
o NoSQL Database: Built with distributed architectures, providing inherent support for high
availability and fault tolerance.
Real-Time Analytics:

• Relational Database (RDBMS): May struggle with real-time analytics due to the complexity
of queries and indexing.
o NoSQL Database: Better suited for real-time analytics and processing of large datasets.
Specific Use Cases:

• Relational Database (RDBMS): Ideal for traditional transactional applications where ACID
properties (Atomicity, Consistency, Isolation, Durability) are crucial.
o NoSQL Database: Suited for various use cases, including content management systems, IoT
applications, social media platforms, and scenarios where scalability and flexibility are
priorities.
It's important to note that the decision to migrate from a relational to a NoSQL database should be
based on a careful analysis of the organization's specific needs, the nature of the data, and the
characteristics of the application. The choice between the two depends on factors such as data
structure, scalability requirements, and the agility needed in the development process. In some
cases, a hybrid approach or polyglot persistence (using multiple databases for different needs) might
be appropriate.

Migrating a healthcare relational database to a NoSQL cloud database involves careful planning and
execution to ensure the seamless transition of data while maintaining security, compliance, and data
integrity.

1. Assessment and Planning:

Data Inventory: Identify all tables, relationships, stored procedures, and other objects in the existing
healthcare relational database.
Schema Mapping: Understand the differences between the relational schema and the NoSQL
database schema. Map the existing relational schema to the new NoSQL structure.
Data Volume and Size: Analyze the size of the existing data to estimate storage requirements in the
NoSQL cloud database.
2. Choose a NoSQL Cloud Database:

Select a NoSQL cloud database provider based on your specific requirements. Popular options
include MongoDB, Couchbase, Amazon DynamoDB, Azure Cosmos DB, and Google Cloud
Firestore.
Consider factors such as data model, scalability, performance, security, and compliance.
3. Data Cleansing and Transformation:

Identify and clean inconsistent or incomplete data in the existing relational database.
Transform data as needed to fit the NoSQL data model. This may involve denormalization and
restructuring of data.
4. Backup and Version Control:

Take a complete backup of the existing relational database.

Implement version control to track changes made during the migration process.

5. Data Migration Tools:

Choose appropriate tools for data migration. Some NoSQL databases provide native tools for data
import.
Consider using ETL (Extract, Transform, Load) tools if necessary.
6. Security and Compliance:

Ensure that security measures, encryption standards, and compliance requirements for healthcare
data are met in the NoSQL cloud environment.
Implement access controls, encryption, and auditing as necessary.
7. Testing:
Conduct thorough testing of the migration process in a non-production environment to identify and
address any issues.
Validate data consistency, accuracy, and integrity after migration.
8. Rollback Plan:

Develop a rollback plan in case any issues arise during the migration.
Test the rollback plan to ensure a quick and smooth transition back to the original state if needed.
9. User Training and Communication:

Train users on any changes to the database structure or access methods.

Communicate the migration plan and potential downtime to stakeholders.
10. Execute Migration:

Schedule a planned maintenance window for the actual migration.

Execute the migration plan, monitor progress, and address any issues promptly.
11. Post-Migration Verification:

Verify data integrity and consistency in the NoSQL cloud database.

Monitor system performance and address any post-migration issues.
12. Optimization and Continuous Improvement:

Optimize the performance of the NoSQL cloud database as needed.

Implement continuous improvement processes based on post-migration feedback and observations.
In healthcare environments, it's crucial to adhere to data privacy and security regulations such as
HIPAA. Engage with stakeholders, including healthcare professionals, database administrators, and
IT teams, throughout the migration process to ensure a successful transition.

Migrating a healthcare relational database to a NoSQL cloud database requires careful planning,
considering the specific characteristics of both healthcare data and NoSQL databases. Here is a
comprehensive guide for such a migration:

1. Data Assessment and Planning:

Data Inventory: Identify and document all tables, relationships, and constraints in the existing
healthcare relational database.
Schema Mapping: Understand the data model differences between relational and NoSQL databases.
Map the relational schema to the appropriate NoSQL data model (document, key-value, column-
family, graph).
Data Quality Assessment: Evaluate and clean the data for inconsistencies, missing values, and
anomalies.

2. Choose a NoSQL Cloud Database:

Database Selection: Choose a NoSQL database that aligns with your healthcare data requirements.
Options include MongoDB, Cassandra, Couchbase, or others based on the specific use case.
Cloud Provider: Select a cloud provider that supports the chosen NoSQL database. Major cloud
providers such as AWS, Azure, and Google Cloud offer managed NoSQL database services.
3. Data Modeling:
Schema Design: Design the NoSQL database schema based on the chosen NoSQL data model.
Consider denormalization to optimize for query performance.
Indexing Strategy: Define appropriate indexes to support the querying patterns of your healthcare
application.
4. Security and Compliance:
Data Encryption: Implement encryption mechanisms for data in transit and at rest to comply with
healthcare data security standards.
Access Control: Set up role-based access control to restrict access to sensitive healthcare
information.
Compliance Checks: Ensure compliance with healthcare regulations such as HIPAA or other
relevant standards.
5. Data Transformation:
ETL Process: Develop Extract, Transform, Load (ETL) processes to migrate data from the
relational database to the NoSQL cloud database.
Data Conversion: Convert data types and formats as needed during the migration process.
6. Testing:
Data Integrity Testing: Perform thorough testing to ensure data integrity after migration.
Query Performance Testing: Test and optimize queries to ensure that they perform well with the
new NoSQL data model.
7. Backup and Rollback Planning:
Backup Strategy: Implement a robust backup strategy for both the relational and NoSQL databases
before the migration.
Rollback Plan: Develop a rollback plan in case issues arise during or after migration.
8. User Training and Communication:
User Education: Train end-users and IT staff on the new data model, query language, and any
changes in the application interface.
Communication Plan: Communicate the migration plan, potential downtime, and any changes to
stakeholders.
9. Execution:
Scheduled Downtime: Plan a scheduled maintenance window for the migration to minimize the
impact on healthcare services.
Migration Execution: Execute the migration plan and monitor progress closely.
10. Post-Migration Verification:
Data Validation: Verify data consistency, accuracy, and completeness in the NoSQL database.
Performance Monitoring: Monitor the performance of the NoSQL database and optimize as needed.
11. Optimization and Continuous Improvement:
Performance Tuning: Optimize the NoSQL database based on performance feedback.
Continuous Monitoring: Implement continuous monitoring and improvement processes for ongoing
database management.
12. Documentation:
Documentation Update: Update documentation to reflect the changes in the data model and
database architecture.
Lessons Learned: Document lessons learned from the migration process for future reference.
Remember to involve key stakeholders, including healthcare professionals, database administrators,
and IT staff, throughout the migration process to ensure a smooth transition and compliance with
healthcare regulations.

Assessment questions to the lecture

Bloom’s
Qn
Question Answer Knowledge
No
Level
1. Why might healthcare organizations consider
migrating from RDBMS to NoSQL?
c Remembering
a. To improve data integrity
b. To handle complex relationships between
entities
c. To scale horizontally and accommodate large
volumes of unstructured data
d. To reduce query performance
Which type of data in the healthcare industry is d Remembering
2. often unstructured and can benefit from a NoSQL
database?

a. Patient demographics
b. Lab results
c. Billing information
d. Electronic Health Records (EHR) in text
format
3. Choosing of NoSQL Database depends on Database
_________, __________ selection, Remembering
cloud
provider

Students have to prepare answers for the following questions at the end of the lecture

Marks CO Bloom’s
Qn
Question Knowledge
No
Level
1 Explain the migration from RDBMS to NoSQL 13 3 Understanding
 CARE COLLEGE OF ENGINEERING, TRICHY
DEPARTMENT OF AI&DS

2023-24 (Even) III year/ VI sem Elective paper

AD3002 – Health Care Analytics

Lecture
Unit -3 Healthcare Management 3
No
Topic Decision support system
Bloom’s
Learning Outcome (LO) At the end of this lecture, students will be able to
Knowledge Level
LO1 Define Decision Support System K1
LO2 Describe different types of DSS in hospitals K1
LO3 Explain the types of decision support system in general K2

In healthcare management, Decision Support Systems (DSS) play a vital role in improving
decision-making processes and enhancing overall healthcare delivery. As the technology associated
with data analysis continues to advance, modern-day physicians are able to rely on decision support
systems to make an even more accurate diagnosis and suggest more effective treatment options for
their patients. In general, clinical support system block diagram depicted in figure

Figure1: Clinical Decision support

Decision support systems are computers that take a patient’s entire medical history, current
symptoms, and other data, then analyze it using a series of complex algorithms. Based on this
analysis, decision support systems are then able to make a diagnosis that physicians can use to back
up their own diagnosis.
In addition to making a diagnosis, decision support systems are also able to recommend treatments
and procedures that will have the highest chance of being successful for a particular patient.

Decision Support Systems for the Healthcare Industry

While some may worry that decision support systems are replacing real, live physicians, the exact
opposite is true. Decision support systems are an incredibly valuable tool that physicians can use to
better aid their patients, but they are just that – a tool. Even the name itself tells you that decision
support systems exist to “support” a physician’s own analysis. As valuable as these systems are,
they won’t be replacing the experience and instinct of talented healthcare professionals anytime
soon.

Different types of decision-making in hospitals

Hospitals are complex, multi-faceted organizations with many levels of decision-makers, including
managers, directors, executives, and more. At a fundamental level, some of the different types of
decision-making in hospitals include:

Clinical care decisions such as diagnosis, treatment, and therapy

Workforce/staffing decisions such as shift times, staffing levels, and salary/wages
Supply chain decisions such as order quantities, brands, and supply companies for medical and
non-medical supply purchases
Service line management decisions including necessary staff, equipment, and facilities
Ancillary services management decisions such as hospital food vendors and services
Care transfer decisions governing patient flow to different levels of care within the care
continuum
Facility management decisions such as routine maintenance needs, repairs, renovations, and
upgrades
A decision support system or “DSS system” is used in a hospital to facilitate
• timely and accurate data-driven decision-making, and to bring transparency and visibility to
clinical, financial, and operational decisions.
• By leveraging data, healthcare decision support systems provide analytics that can help
healthcare leaders determine the best ways to reduce rapidly rising healthcare costs,
improve efficiencies, enhance patient safety, improve patient care, and achieve better
patient outcomes.

The primary types of decision support in healthcare are:

• Financial decision support

• Clinical decision support
• Clinical analytics
Healthcare financial decision support is focused on helping hospital executives, department
managers, and other healthcare leaders determine how best to manage their organizations.
Healthcare financial decision support software aggregates and analyzes data from a variety of
sources so leaders can make informed, data-driven decisions on how to maximize efficiencies,
reduce costs, optimize revenue, and position their organizations for growth. For example, a
financial decision support system applies cost data to department operations to support budgeting,
productivity, and performance monitoring. It also can provide data for assessing service-line
profitability, performing health plan analyses, and quantifying the cost of quality.

Clinical decision support is a core component of ensuring high quality patient care at the bedside.
A clinical decision support system provides data and analytics to help physicians, advanced practice
nurses, and other caregivers more accurately diagnose patient conditions and identify the best
treatments. Clinical decision support systems sort through large amounts of data from electronic
health records (EHRs) and other sources to help clinicians as they provide patient care in real time.
The goal of a clinical decision support system is to help avoid adverse events and enhance the
quality, effectiveness, and efficiency of care. For example, it can help a physician link symptoms to
a specific diagnosis, determine an appropriate medication dosage, and avoid harmful medication
interactions.

Clinical analytics refers to a type of healthcare decision support that takes a more comprehensive
view of care delivery within an organization, as opposed to clinical decision support which focuses
on care decisions for individual patients. With clinical analytics, healthcare executives and clinical
and finance leaders can compare their organization’s clinical data to peer organizations to gauge
performance down to specific departments or service lines. It allows them to establish an accurate
picture of costs and utilization at the encounter level, then perform meaningful analysis across
various patient cohorts or clinical service lines. These insights are then used to make vital decisions
such as how to reduce unwarranted and often costly variations in care, enhance care coordination,
and track and improve workforce productivity.

Here are some key aspects of how DSS is applied in healthcare management:

1. **Clinical Decision Support Systems (CDSS):** These systems assist healthcare professionals in
making clinical decisions by providing relevant information and recommendations based on patient
data. CDSS can analyze electronic health records (EHRs), laboratory results, and other clinical data
to offer insights into diagnosis, treatment options, and medication choices. They help clinicians
adhere to best practices, reduce errors, and improve patient outcomes.

2. **Health Information Systems (HIS):** Decision Support Systems are integrated into broader
Health Information Systems, which manage and disseminate health-related information. HIS
includes electronic health records, health data analytics, and other tools that facilitate decision-
making at various levels of healthcare management.

3. **Operational Decision Support:** DSS in healthcare management helps in optimizing day-to-

day operations. It can assist in resource allocation, scheduling, and workforce management. For
example, DSS can aid in predicting patient admission rates, optimizing staff schedules, and
managing inventory levels for medical supplies.

4. **Financial Decision Support:** Healthcare organizations need to make financial decisions to

ensure sustainability. DSS can assist in budgeting, financial planning, and cost analysis. By
providing insights into revenue streams, expenses, and financial performance, DSS helps healthcare
managers make informed decisions to maintain fiscal health.
5. **Population Health Management:** DSS supports healthcare managers in addressing
population health challenges. By analyzing health data from various sources, these systems help
identify trends, assess risk factors, and design interventions to improve the health of specific
populations. This is especially important in managing chronic diseases and preventive care.

6. **Strategic Planning:** DSS aids in strategic decision-making by providing data-driven insights

into long-term planning. It can assist healthcare administrators in identifying areas for expansion,
assessing the need for new services, and planning for technology adoption.

7. **Compliance and Quality Management:** Healthcare organizations must adhere to regulatory

requirements and maintain high-quality standards. DSS can help in monitoring and ensuring
compliance with regulations, as well as assessing and improving the quality of care provided.

8. **Telemedicine and Remote Patient Monitoring:** With the rise of telehealth, DSS is
increasingly used to support decision-making in remote patient monitoring. It assists healthcare
providers in interpreting data from wearable devices, tracking patient progress, and making
decisions about adjusting treatment plans.

9. **Interoperability:** Ensuring interoperability between different healthcare systems is crucial.

DSS can facilitate the exchange of information between disparate systems, allowing healthcare
managers to access comprehensive data for decision-making.

In summary, Decision Support Systems in healthcare management contribute to more informed and
efficient decision-making across clinical, operational, financial, and strategic aspects of healthcare
delivery. They are integral tools for improving patient outcomes, resource utilization, and overall
healthcare system performance.

Students have to prepare answers for the following questions at the end of the lecture

Marks CO Bloom’s
Qn
Question Knowledge
No
Level
1 Explain in detail of Decision Support system in healthcare 15 1 K3

Reference Book:
 Lecture
Unit -3 Healthcare Management 4
No
Topic Matrix block cipher system
Bloom’s
Learning Outcome (LO) At the end of this lecture, students will be able to
Knowledge Level
LO1 Define the term Block cipher K1
LO2 Describe the modes of block cipher system K1
LO3 Explain the applications of block cipher system K2
LO4 Explain generic approaches using block cipher K2

Encryption algorithms are divided into two categories based on the input type, as a block
cipher and stream cipher. Block cipher is an encryption algorithm that takes a fixed size of
input say b bits and produces a ciphertext of b bits again. If the input is larger than b bits it can
be divided further. For different applications and uses, there are several modes of operations for a
block cipher.

Electronic Code Book (ECB)

Electronic code book is the easiest block cipher mode of functioning. It is easier because of direct
encryption of each block of input plaintext and output is in form of blocks of encrypted ciphertext.
Generally, if a message is larger than b bits in size, it can be broken down into a bunch of blocks
and the procedure is repeated.

Procedure of ECB is illustrated below in figure 1

Figure 1 Electronic code book

Cipher Block Chaining
Cipher block chaining or CBC is an advancement made on ECB since ECB compromises some
security requirements. In CBC, the previous cipher block is given as input to the next encryption
algorithm after XOR with the original plaintext block. In a nutshell here, a cipher block is produced
by encrypting an XOR output of the previous cipher block and present plaintext block.

The process is illustrated in figure 2

Figure 2: Cipher Block Chaining

Cipher Feedback Mode (CFB) :

In this mode the cipher is given as feedback to the next block of encryption with some new
specifications: first, an initial vector IV is used for first encryption and output bits are divided as a
set of s and b-s bits.The left-hand side s bits are selected along with plaintext bits to which an XOR
operation is applied. The result is given as input to a shift register having b-s bits to lhs,s bits to rhs
and the process continues. The encryption and decryption process for the same is shown below,
both of them use encryption algorithms. The process is illustrated in figure 3.
Figure 3: Cipher Feedback Mode (CFB) :

Output Feedback Mode

The output feedback mode follows nearly the same process as the Cipher Feedback mode except
that it sends the encrypted output as feedback instead of the actual cipher which is XOR output. In
this output feedback mode, all bits of the block are sent instead of sending selected s bits. The
Output Feedback mode of block cipher holds great resistance towards bit transmission errors. It also
decreases the dependency or relationship of the cipher on the plaintext. Output Feedback Mode
process is explained in Figure 4.
Figure 4: Output Feedback Mode

Counter Mode
The Counter Mode or CTR is a simple counter-based block cipher implementation. Every time a
counter-initiated value is encrypted and given as input to XOR with plaintext which results in
ciphertext block. The CTR mode is independent of feedback use and thus can be implemented in
parallel is shown in figure 5.

Figure 5: Counter mode

Applications of Block Ciphers

Data Encryption: Block Ciphers are widely used for the encryption of private and sensitive data
such as passwords, credit card details and other information that is transmitted or stored for a
communication. This encryption process converts a plain data into non-readable and complex form.
Encrypted data can be decrypted only by the authorised person with the private keys.
File and Disk Encryption: Block Ciphers are used for encryption of entire files and disks in order
to protect their contents and restrict from unauthorised users. The disk encryption softwares such as
BitLocker, TrueCrypt aslo uses block cipher to encrypt data and make it secure.
Virtual Private Networks (VPN): Virtual Private Networks (VPN) use block cipher for the
encryption of data that is being transmitted between the two communicating devices over the
internet. This process makes sure that data is not accessed by unauthorised person when it is being
transmitted to another user.
Secure Sockets Layer (SSL) and Transport Layer Security (TLS): SSL and TLS protocols use
block ciphers for encryption of data that is transmitted between web browsers and servers over the
internet. This encryption process provides security to confidential data such as login credentials,
card information etc.
Digital Signatures: Block ciphers are used in the digital signature algorithms, to provide
authenticity and integrity to the digital documents. This encryption process generates the unique
signature for each document that is used for verifying the authenticity and detecting if any
malicious activity is detected.

Here's a generic approach using block ciphers in healthcare management:

1. Data Encryption:
Block Cipher Usage: A block cipher, such as the Advanced Encryption Standard (AES), could be
employed to encrypt patient records and other sensitive information.
Matrix Consideration: While the term "matrix block cipher system" isn't standard, if it refers to a
matrix-based encryption scheme, it could involve using matrices in the encryption process.
2. Key Management:
Proper key management is crucial. Encryption keys should be securely stored and managed to
prevent unauthorized access.
3. Access Controls:
Use block ciphers in conjunction with access controls to ensure that only authorized personnel can
decrypt and access sensitive healthcare data.
4. Secure Communication:
Implement encrypted communication channels to secure the transmission of patient data between
different entities within the healthcare system.
5. Audit Trails:
Maintain audit trails to track access to sensitive data. This helps in monitoring and investigating any
potential security incidents.
6. Regulatory Compliance:
Ensure that the chosen cryptographic methods and key management practices comply with
healthcare regulations, such as HIPAA.
7. Continuous Monitoring and Updating:
Regularly monitor the security landscape for any new cryptographic vulnerabilities or updates and
promptly apply patches or changes to enhance the security of the system.

Assessment questions to the lecture

 Bloom’s
Qn
Question Answer Knowledge
No
Level
1. What is the primary purpose of using block ciphers
in healthcare management systems?
a. Data compression b Remembering
b. Data encryption
c. System authentication
d. Error detection
What is the role of the key in a block cipher d Remembering
2. system
a. Determines the block size
b. Determines the encryption algorithm
c. Initiates the encryption process
d. Enables decryption of the data
3. Match the following:
i. Sensor analysis – a.MRI,CT i….b Remembering
ii. Biomedical Image analysis –b. EEG ii…a
iii. Electromyogram – c.ECG iii…d
iv. Electrocardiogram- d.EMG iv…c

Students have to prepare answers for the following questions at the end of the lecture

Marks CO Bloom’s
Qn
Question Knowledge
No
Level
1 Explain in detail of Modes of operation in Block cipher 15 3 K3
system in healthcare management system

Reference Book: