DIGITAL

TWIN
CONTENTS
Executive Summary 3

Introduction 4

Digital Twin 4

Evolution of Digital Twins 4

The Digital Twin Market 5

Digital Twin Components 6

Digital Twin Components within the Saudi 8

Healthcare System

Future Vision of the Digital Twin within the Saudi 9

Healthcare System

Promoting innovation in Saudi Healthcare with the 10

Digital Twin

Powering Vision 2030 with Digital Twins 10

Enabling Value-Based Healthcare and the New 11

Model of Care

The First Phase of the Digital Twin 13

Digital Twin Elements 13

Technical Framework of the Digital Twin 16

The Risk Engine 17

Machine Learning Methods for Risk Engine 18

Development

Data Collection 18

Data Preprocessing 19

Modeling 19

Model Training 19
Table Of

Evaluation and Testing 19

Resulting models 19

The Recommendations Engine 20

Conclusion 21

References 22
 EXECUTIVE SUMMARY
Saudi Arabia’s healthcare sector is undergoing
a significant transformation, driven by the Saudi
Vision 2030 and the Health Sector Transformation
Program. The program aims to improve the sector
by prioritizing prevention, quality, and efficiency. At
the heart of this transformation is the adoption of
digital technologies. One of them is the digital twin,
a cutting-edge technology that is set to transform
healthcare service delivery.

The digital twin is a virtual representation of an

individual, implemented through the Sehhaty app,
that manages and monitors their health status by
leveraging various health data inputs. This enables
the digital twin to provide insights for preventative
measures and early interventions.

The digital twin enhances both the model of care and

value-based healthcare by facilitating healthcare
service delivery, precise cost predictions, and
outcome measurements. It also has the potential to
improve patient experience and population health
outcomes, while optimizing resource utilization.

The digital twin provides multiple innovative

elements to optimize personalized healthcare. It
currently includes health status visualization, body
mass index assessment, biological age calculation,
step tracking, vaccination guidance, and chronic
disease risk prediction, with more promising
elements to be added in the future.

The adoption of digital twin technology marks an

important moment in the healthcare transformation
journey of Saudi Arabia. The era of personalized
healthcare has begun.

3 Digital Twin
INTRODUCTION
Advances in the Saudi healthcare system have significantly increased the population's life expectancy. This
success comes with new challenges. A longer lifespan is associated with a rise in chronic conditions, putting
mounting pressure on the Kingdom’s healthcare system. To help mitigate this, there's a clear need for
innovative solutions that can effectively prevent and manage these health issues. One promising approach
is the digital twin.

DIGITAL TWIN
Digital twin technology is revolutionizing our
understanding and management of complex
systems. A digital twin is defined as a virtual
replica or copy of a physical object, process,
or system that is continuously updated
with real-time data. This digital counterpart
enables accurate monitoring, analysis, and
prediction. By bridging the physical and
digital worlds, digital twins make it possible to
optimize performance, anticipate issues, and
simulate scenarios in a risk-free environment.

Evolution of Digital Twins

200,000 Miles
Imagine being in space, 200,000 miles from Earth, with limited oxygen and a damaged spacecraft. This
was the reality for the Apollo 13 astronauts in 1970 after an explosion occurred in their spacecraft. To save
their lives, NASA engineers had to act fast: They tested different scenarios using physical simulators and
mathematical models, which helped them develop a plan that successfully saved the astronauts.1

In 2002, Dr. Michael Grieves revisited the idea and introduced the modern digital twin concept.1 Since then, this
innovation has revolutionized how we approach complex problems across various sectors.

4 Digital Twin
The Digital Twin Market

The digital twin market is set to expand dramatically, growing from $10.1 billion in 2023 to $110.1 billion by
2028, with a remarkable 61% growth rate yearly,2 as companies worldwide rush to enter this fast-growing
field (Figure 1).

Global Digital Twin Market Size in Billion Dollars

Other East Asia Europe North America

110
100
Market size (billion dollars)

80

60

40

20
7 10
0
2022 2023 2028

Years

Figure 1. Global Digital Twin Market Size Projection (2022-2028). The stacked bar chart displays the projected size of the global
digital twin market in billion dollars for the years 2022, 2023, and 2028. The market is segmented into four geographical categories, each
represented by a different color in the stacked bars. The chart includes a compound annual growth rate (CAGR) indicator between 2023
and 2028, and the total market size values are labeled for each year shown.

5 Digital Twin
Digital Twin Components

A digital twin is a complex system that consists of five core components. These components work together to
create an interactive system that simulates, analyzes, and optimizes the behavior of the beneficiary (Figure
2).3

Analytical
Environment

Model Model
Generation Interaction
Process Process

DATA
ENVIRONMENT

Physical Virtual
Environment Environment

Model Application
Process

Figure 2. Architecture of a digital twin. A schematic of the core components and processes of a digital twin. At the center is the Data
Environment, which stores the data. It is interconnected with three primary environments: the Physical Enviroment, which measures the
physical system providing data for the digital twin; the Analytical Enviroment, which involves simulations and artificial intelligence; and
the Virtual Enviroment, which visualizes the digital twin. The Connection Environment functions as the invisible structure that integrates
the various components together. Bidirectional arrows indicate data flow and interactions between these components. The diagram
also depicts three key processes: Model generation, Model interaction, and Model application which link the various environments.

The first component is the Physical Environment, where the physical object, process, or system exists and is
measured. It is the source of the data that feeds into the digital twin, which enables the creation of the virtual
replica. The second component is the Data Environment, where the raw data from the Physical Environment
is stored. Third is the Analytical Environment, where simulations, artificial intelligence, and automation occurs.
Fourth is the Virtual Environment, where the digital twin is visualized. This is often the only part that users
interact with. Lastly, the Connection Environment, where all the environments are connected and integrated,
and it includes access channels.3

6 Digital Twin
What is a “Digital Twin” in
personalized healthcare?
It is a virtual representation of an
individual that visualizes and monitors
their health status in an easy-to-
understand format by leveraging
various health data inputs such as
step count, body weight, and medical
history.

7 Digital Twin
In a step towards transforming its healthcare system, Saudi Arabia is embracing the digital twin by integrating
this technology into the Sehhaty app. Sehhaty is an application that offers a variety of health services to
individuals in Saudi Arabia, enabling users to access healthcare needs, including health information and
medical e-services provided by various health organizations across the Kingdom.

Digital Twin Components within the Saudi Healthcare System

The digital twin environments are integrated within the Saudi healthcare system and designed to facilitate
seamless data exchange. The process begins with the physical and data environments which utilize the Internet
of Things (IoT), the Sehhaty app, and the Unified Health Record (nphies) platform to collect and transmit
data. The analytical environment then analyzes the data and extracts insights. These insights are visualized
in the virtual environment along with health recommendations. Finally, the connection environment, which
includes access channels, allows seamless integration with various Saudi healthcare platforms, including
Anat, Seha, Sehhaty, and Raqeem (Figure 3).

INPUTS RISK ASSESSMENT OUTPUTS

• Heath data Sending

Recommendations
Physical and data environments

Analytical environment

Virtual environment

Connection environment
• Behavioral
data Individual
• Genetic data
• Social data
• Practitioner RISK RECOMMENDATION
ENGINE ENGINE Practitioner
data

Internet of Business rules Knowledge Previous

Things Bases Experiences
Artificial
Simulation
Intelligence
Models

Figure 3. Digital twin components within the Saudi healthcare system. This diagram illustrates the application of digital twin
architecture within the Saudi healthcare context.

8 Digital Twin
FUTURE VISION OF THE DIGITAL TWIN
WITHIN THE SAUDI HEALTHCARE SYSTEM
In the future, we aim to develop the digital twin further by integrating various additional elements that
provide a virtual overview of health. Digital twin solutions hold great potential to transform several aspects
of personal health management and optimization as they continue to evolve. Examples of these elements
include but are not limited to health status visualization, physical activity and diet tracking, genetic data
integration, personalized health recommendations, mental health screening, vaccination guidance, chronic
disease simulation and risk prediction (Figure 4).

Health Status Physical Activity

Visualization Tracking and Analysis

Chronic Disease Vaccination Guidance

Simulation

Body Mass Index (BMI)

Chronic Disease Risk
Assessment
Prediction

Health Recommendations Biological Age

Personalization Assessment

Genetic Information Dietary Intake Tracking

Integration and Analysis

Medical History Mental Health

Synchronization Screening

Figure 4. Current and upcoming digital twin elements to support personalized healthcare. The digital twin elements for personalized
healthcare include tools for health status visualization, activity tracking, vaccination guidance, Body Mass Index (BMI) and biological
age assessments, dietary and mental health monitoring, medical history synchronization, genetic data integration, personalized health
recommendations, chronic disease simulation and risk prediction.

9 Digital Twin
PROMOTING INNOVATION IN SAUDI
HEALTHCARE WITH THE DIGITAL TWIN
Powering Vision 2030 with Digital Twins

The digital twin is an enabler of Saudi Arabia’s Vision 2030. By leveraging the power of digital technologies,
the digital twin can help achieve the first pillar of Vision 2030 “A Vibrant Society with Fulfilling Lives” and the
following strategic objectives:5

Strategic Alignment:

Digital Twins and Vision 2030’s Healthcare Objectives:

Improve healthcare
service (2.1):

• Ease access to healthcare services (2.1.1): The digital twin can provide
remote access to personalized health information.
• Improve value of healthcare services (2.1.2): The digital twin can enhance
the efficiency of healthcare delivery.
• Strengthen prevention against health threats (2.1.3): The digital twin can

01 use prediction models to predict disease risk.

lifestyle (2.2):
a healthy
Promote

• Increase public participation in sports and athletic activities (2.2.1): The

digital twin can track and encourage physical activity.

02
Improve performance

apparatus (5.2):
of government

• Enhance the performance of government entities (5.2.2): The digital twin

can optimize healthcare system performance.
• Improve the productivity of government employees (5.2.3): The digital
twin can help healthcare workers manage patient care more efficiently.
• Develop the e-Government (5.2.4): The digital twin can be integrated into

03 e-government health services.

10 Digital Twin
Enabling Value-Based Healthcare and the New Model of Care

The digital twin is poised to be a transformative force in healthcare, enabling both value-based healthcare6
and the model of care7 (Figures 5 and 6). It can support the healthcare system by offering unique benefits
to multiple stakeholders, including:

HEALTHCARE PROVIDERS HEALTHCARE

PATIENTS
DECISION-MAKERS
• Personalizes health • Enables daily • Provides data-driven
interventions engagement with patients insights
• Makes individuals • Facilitates early and cost- • Enables value-based
active participants in effective interventions agreements
their care

A Digital Twin-Enabled Framework for Value-Based Healthcare

Digital twin serves Digital twin informs

as a central value-based payment
repository for models through
health data Informatics Payments accurate health risk
assessments

Population
Segments

Outcomes
+
Costs

Segment-Specific
Interventions

Delivery Benchmarking,
organization research, and
Digital twin
tools Digital twin provides
improves care a virtual environment
delivery by offering for testing and
predictive insights comparing different
for personalized treatments and
treatment plans = Potential Digital Twin influence outcomes

Figure 5. Integration of the digital twin into value-based healthcare framework. The integration of the digital twin into a value-
based healthcare framework can enhace healthcare by optimizing informatics as a central data repository, facilitating value-based
payments through accurate disease risk assessments, providing a virtual environment for benchmarking and research to compare
treatments and outcomes, and supporting care delivery through personalized health management to improve outcomes and reduce
costs.

11 Digital Twin
 A Digital Twin-Enabled Model of Care

Mother and Child Care System:

The digital twin can monitor health
status and vaccination schedules for
pregnant women and children,
supporting optimal family health
m Mother
yste
management
& Chi
reS ld
Ca Ca
re
e
tiv S
lized Hosp
ec

Specia

ys
ital
El

s
General Hospitals

te
m
P rim a ry Care
Virtual Care
em

unities He
Primary Care: mm

Pall
o a Healthy Communities:
C ual Empo lth
ncy Care Syst

Digital twin optimizes primary divid w Digital twin can show community

iative Care System

In

y
care by predicting individual health trends to optimize

er
health risks to enable targeted interventions and predict impacts

ed
preventive measures Physical Health on the population-level
Social Health
Mental Health
Virtual Care: Empowered Individual:
Digital twin enhances telehealth The digital twin can empower
erge

by supporting virtual individuals with personalized

consultations with the user’s data health insights
Em

em

Pr
ev
st

en
Sy tiv
se e
ea Ca
Dis ic
re
Syst
Chronic Disease Care System Chron em Preventive Care System
The digital twin can monitor and The digital twin can monitor
present patient information to give a health information to help
clear picture of ongoing chronic identify potential health risks,
conditions, supporting better chronic supporting preventive care
disease management

= Potential Digital Twin influence

Figure 6. Integration of the digital twin into the model of care. Integration of the digital twin into the model of care can be beneficial
across the layers of service, including primary care, virtual care, healthy communities, and empowered individuals. And the systems of
care, such as mother and child care, preventive care, and, chronic disease care.

12 Digital Twin
THE FIRST PHASE OF THE DIGITAL TWIN
The journey towards personalized medicine in Saudi Arabia has just begun. The digital twin is at the forefront
of this promising field.

Digital Twin Elements

The first phase of the digital twin introduces six key elements that work together to provide a comprehensive
view of the user’s health, which are:

01
HEALTH STATUS VISUALIZATION

Visualizes the user’s health condition with a digital model of the

human body by highlighting any affected anatomical areas.

• Functional Highlights:

i) Comprehensive Visualization: Provides a visual of impacted

organs on the 3D human body model.
ii) Comparative Analysis: Allows users to assess their model and
health conditions against percentile rankings derived from
aggregated data of peers with similar profiles.
iii) Educational Content: Presents personalized insights based on
the user’s health status.

02
BODY MASS INDEX (BMI) ASSESSMENT

Provides an assessment of the user’s BMI.

• Functional Highlights:

i) Comparative Analysis: Allows users to assess their BMI result

against percentile rankings derived from aggregated data of
peers with similar profiles.
ii) Educational Content: Presents personalized insights to
improve the user’s health based on their BMI results.

13 Digital Twin
 03
BIOLOGICAL AGE CALCULATION

Calculates a prediction of the user’s biological age, which is known

as the estimated age of the body’s health and functioning, by
evaluating a range of health metrics.

• Functional Highlights:

i) Age Comparison: Compares the user’s chronological and

biological ages.
ii) Personalized Insights: Delivers insights into the effects of
lifestyle habits on aging.

04
PHYSICAL ACTIVITY

Monitors and reports on the user’s steps activity.

• Functional Highlights:

i) Activity Tracking: Monitors daily steps count and calculates

weekly averages.
ii) Comparative Analysis: Compares the user’s activity levels with
peers who have similar profiles and nudges for improvements.
iii) Goal Setting: Facilitates personalized goal setting based on
activity data.
iv) Educational Content: Presents personalized insights to
enhance physical activity and overall health.

14 Digital Twin
 05
VACCINATION GUIDANCE

Employs a risk-based evaluation approach considering age, health

status, and vaccination history to determine the user’s vaccination
needs.

• Functional Highlights:

i) Personalized Recommendations: Suggests future vaccinations

based on related risk factors.
ii) Appointment Booking: Allows the user to book vaccination
appointments directly.
iii) Educational Content: Provides vaccination insights to inform
and educate users.

06
CHRONIC DISEASE RISK PREDICTION

Employs a risk engine that utilizes a machine learning approach

to analyze user data, predict potential disease risk, and facilitate
proactive prevention.

• Functional Highlights:

i) Risk Prediction: Identifies potential disease risk based on the

user’s health data.
ii) Healthcare Network: Facilitates connections between users
and healthcare practitioners for further consultations and
examinations.
iii) Educational Content: Presents personalized insights to help
users understand and avoid disease risk.

15 Digital Twin
TECHNICAL FRAMEWORK
OF THE DIGITAL TWIN
A technical infrastructure is required to bring these digital twin elements to life within the Saudi healthcare
system (Figure 7). The process flows through various decision points and engines to provide data-driven
insights. The process involves both Sehhaty users and healthcare practitioners utilizing other Saudi healthcare
apps and platforms, including Sehhaty, Anat, and Raqeem. As well as population health officers who operate
the Yamamah platform. It contains a feedback loop, where responses are monitored and reminders are sent
when necessary.

Evaluation Recommendations/Interventions*

User
Implementing
No necessary
Questionaries Send Healthcare interventions
Response?
Engine Reminders at the
individual level
Yes
Database No Mother and Child Care System:
The digital twin can monitor health
status and vaccination schedules for
pregnant women and children,

Analysis Recommendations Practitioner

supporting optimal family health
Mother
tem & management
Sys Chi
ld
re
Ca Ca

Engine
e re

Engine
tiv S

ec
lized Hosp
Specia

ys
ital

El
s
General Hospitals

te
m
Primary Care
Virtual Care

em
unities He
Primary Care: mm

Pall
Healthy Communities:
Co dual Emp alth

ncy Care Syst

Digital twin optimizes primary div
i ow Digital twin can show community

iative Care System

In

y
care by predicting individual health trends to optimize

er
health risks to enable targeted interventions and predict impacts

ed
Informational
Scope
preventive measures Physical Health on the population-level
Social Health
Mental Health
Virtual Care: Empowered Individual:

Yes No Yes intervention

Digital twin enhances telehealth The digital twin can empower

erge
by supporting virtual individuals with personalized
consultations with the user’s data health insights

Em
Complete
Candidate? Diagnosed? Behavioral

em

Pr
ev
st
en

information?
Sy tiv

intervention
e e
as Ca
ise
Machine Business
re
ic D Syst
Chronic Disease Care System Chron em Preventive Care System
The digital twin can monitor and The digital twin can monitor
Learning Rules present patient information to give a
clear picture of ongoing chronic
health information to help
identify potential health risks,
conditions, supporting better chronic

Awareness
supporting preventive care
disease management

No Yes intervention
Population
Cognitive
Analysis Health Officer
intervention Implementing
Result
Previous necessary
Stop Patient Population interventions
Health at the
Risk Engine components community
level
Resources KPI’s

Feedback is recalculated after a specified period.

* Not all interventions require actual use of health services (such as hospital visits, prescriptions, etc..)

Figure 7. The standard technical infrastructure for implementing the digital twin in Saudi healthcare. The technical
infrastructure of the digital twin in Saudi healthcare includes multiple decision points with a risk engine, analysis engine, and
recommendations engine at its core. These components evaluate patient data, process responses, and generate personalized
recommendations or interventions at both individual and community levels through platforms like Sehhaty, Raqeem, Yamamah,
and Anat.

As we explore the digital twin more, it’s essential to highlight the risk
engine which offers the greatest value to users.

16 Digital Twin
THE RISK ENGINE
Patients are often diagnosed with diseases at a late stage, leading to poorer conditions and complicated
treatment journeys. Early disease detection often results in better health outcomes. However, many individuals
remain unaware of their disease risk until it’s too late and their disease has progressed. Numerous risk factors,
such as poor diet, smoking, low physical activity, family history, and high BMI, are known to contribute to the
development of chronic diseases.

To address this challenge, the risk engine has been developed as an AI-based solution comprising five
machine learning models, that are designed to predict the likelihood of a user developing specific diseases
based on their individual risk factors.

The targeted diseases in these models include:

Diabetes and Arteriosclerotic

Prediabetes Cardiovascular Disease

Colorectal Breast Stroke

Cancer Cancer

The main objective of the risk engine is to detect high-

risk users early and nudge them toward addressing
their health risks before disease onset or progression.

17 Digital Twin
Machine Learning Methods for Risk Engine Development

The following sections outline the development process of the five machine learning models, starting from
data collection (Figure 8).

Data Collection Data Preprocessing Building ML model Model Completion

Data cleaning and Model Selection:

Data source: Logistic regression
standardization
models
National data
Feature selection
extracted from Validation Approach:
and scaling
electronic health Stratified K-Fold Cross-
records (EHRs) in Validation
Missing value
Saudi Arabia
treatment
Parameter
Class balancing Optimization:
Hyperparameter tuning

Figure 8. Risk engine development process. The development process for the risk engine includes data collection from national
Electronic Health Records (EHRs) in Saudi Arabia, data preprocessing (cleaning, feature selection, missing value treatment, and class
balancing), and building machine learning models with logistic regression, cross-validation, and hyperparameter tuning.

Data Collection

National data extracted from electronic health records (EHRs) in Saudi Arabia was used to comprehensively
represent the population. The dataset had various types of information, including:

Demographics Diagnoses
Including gender, age, and marital status Coded using ICD-10 (International Classification
of Diseases, Tenth Revision) codes

Procedures Medications
Documented with ACHI (Australian Identified using codes like ATC (Anatomical
Classification of Health Interventions) Therapeutic Chemical Classification System),
GTIN (Global Trade Item Number), and others

Laboratory Results Family History

Recorded using LOINC (Logical Observation Information on familial medical conditions
Identifiers Names and Codes)

Habits and Lifestyle Factors

Data on smoking status, physical activity levels, diet, and other lifestyle aspects

18 Digital Twin
This broad dataset was crucial for developing accurate and effective machine learning models within the
risk engine. By accounting for a wide range of health-related information, the models can better predict the
likelihood of users developing specific diseases based on their distinct risk factors.

Data Preprocessing Model Training

Several preprocessing steps were undertaken To optimize our models, we conducted multiple
to prepare the dataset for modeling, including experiments during the training phase. In
standardizing medication and laboratory test each experiment, we fine-tuned the models’
names with natural language processing, scaling hyperparameters and evaluated their performance.
numerical features, and handling missing values.
Feature selection was based on risk factors Evaluation and Testing
through exploratory data analysis (EDA), and class
imbalance was addressed with down-sampling. To accurately evaluate our models, we obtained a
representative test sample using the stratification
Modeling method. Stratification factors varied between
models based on the features included in each.
We employed logistic regression models to predict We then applied stratified k-fold cross-validation to
disease occurrence using individuals' features to assess the performance of our models.
estimate risk probabilities for developing diabetes,
prediabetes, arteriosclerotic cardiovascular disease, Resulting models
stroke, colorectal cancer, and breast cancer. We
identified factors that may increase disease risk The purpose of these models is to screen for
to create personalized interventions. Next, we diseases and help predict the likelihood of their
conducted an association analysis to determine occurrence at early stages. To achieve this goal, the
the relationships between these risk factors and resulting models focus on identifying as many high-
disease outcomes, assessing whether our data risk individuals as possible, capturing those with a
accurately reflected these connections. high potential of developing the disease in the
future. Each model categorizes users into defined
risk groups—low risk, medium risk, and high risk—
which contributes to more accurate and meaningful
results and supports the recommendation engine
in generating the most appropriate outputs.

19 Digital Twin
THE RECOMMENDATIONS ENGINE
The recommendations engine is a supporting component of the risk engine. It translates complex risk analyses
into personalized nudges. These notifications form a communication strategy designed to inform users and
encourage specific responses. The engine generates different types of notifications, including informational
notifications, awareness notifications, and behavioral notifications, each serving a specific purpose.

The recommendations engine determines the most suitable notification type for each scenario. A team of
specialists has carefully crafted the wording of the notifications to ensure that all communications adhere to
four key principles:

Clarity Sensitivity

Easy to understand for the general Avoiding language that may scare or
public stigmatize users

Accuracy Empowerment

Reflecting accurate, updated medical Providing information that supports

knowledge informed decision-making

By adhering to these principles, the engine ensures that users receive appropriate, relevant, and timely
guidance. This empowers users to make well-informed decisions and take appropriate actions to manage
their disease risk effectively.

20 Digital Twin
CONCLUSION
The integration of digital twin technology into Saudi Arabia’s healthcare system represents a transformative
leap toward realizing Vision 2030. This cutting-edge approach not only aligns with but supports the Health
Sector Transformation Program’s core objectives of prevention, quality, and efficiency. By harnessing
the power of digital twins, Saudi Arabia stands poised to revolutionize personalized healthcare, enabling
a paradigm shift towards truly patient-centered, value-based care models.

21 Digital Twin
REFERENCES
1. Grieves M. Origins of the digital twin concept [Internet]. 2016. Available from: https://10.13140/
RG.2.2.26367.61609

2. MarketsandMarkets. Digital Twin Market Size Worth USD 110.1 billion by 2028 [Internet].
MarketsandMarkets. 2024. Available from: https://www.marketsandmarkets.com/Market-Reports/
digital-twin-market-225269522.html

3. Grübel J, Thrash T, Aguilar L, Gath-Morad M, Chatain J, Sumner RW, et al. The Hitchhiker’s Guide to
Fused Twins: A review of access to digital twins in situ in smart cities. Remote Sensing [Internet]. 2022
Jun 27;14(13):3095. Available from: https://www.mdpi.com/2072-4292/14/13/3095

4. Health Sector Transformation Program. Health Sector Transformation Program - Delivery

Plan [Internet]. 2021 Sep [cited 2024 Sep 24]. Available from: https://www.vision2030.gov.sa/
media/0wop2tds/hstp_eng.pdf

5. Vision 2030: The Themes, Programs, Strategic Objectives, and Goals [Internet]. [cited 2024 Sep 16].
Available from: https://www.iau.edu.sa/sites/default/files/vission2030sheetenglish.pdf

6. Council of Health Insurance in Saudi Arabia. Value-Based Healthcare Action plan [Internet]. [cited 2024
Sep 16]. Available from: https://vbhc.chi.gov.sa/assets/pdf/CHI%20VBHC%20action%20book.pdf

7. Saudi Ministry of Health. The new model of care [Internet]. [cited 2024 Sep 16]. Available from: https://
www.moh.gov.sa/vro/Pages/namouzaj_al_ri3aya.aspx

22 Digital Twin
23 Digital Twin