Healthcare Analytics Dashboard for Data-Driven Insights
A Project Report
Submitted in partial fulfilment of the requirements for the
Award of the degree of
“Master of Computer Application”
By
Nikhil Tripathi
323102281
Centre for Distance and Online Education
LOVELY PROFESSIONAL UNIVERSITY
PHAGWARA, PUNJAB
2023-2025
1
Table Of Contents
S. No Title Page. No
1 Declaration by Student 03
2 Acknowledgement 04
3 Abstract 05
4 List of Tables 06
5 List of Figures/ Charts 07
6 List of Schemes/Algorithms 08-11
7 List of Symbols 12
8 List of Abbreviations 13
9 Chapter-1 Introduction 14-18
10 Chapter-2 Review of Literature 19-20
11 Chapter-3 Implementation of project 21-25
12 Chapter-4 Results and Discussions 26-29
13 Final Chapter- Conclusion and Future Scope 30-32
14 Annexures- (Cover Page) Annexures- 01
(Project Summary) 33
15 References 34
Declaration by the Student
2
To whom-so-ever it may concern
I, NIKHIL TRIPATHI 323102281, hereby declare that the work
done by me on “Healthcare Analytics Dashboard for Data-Driven
Insights”, is a record of original work for the partial fulfilment of the
requirements for the award of the degree, Master of Computer
Applications.
NIKHIL TRIPATHI (323102281)
Signature of the Student
Date: 29 April 2025
Acknowledgement
I would like to express my heartfelt thanks to everyone who supported
me in completing this project, “Healthcare Analytics Dashboard for
Data-Driven Insights.”
3
I am sincerely grateful to my faculty and institution for providing the
opportunity and resources to work on this project. I would also like to
thank the online learning platforms, particularly Microsoft Power BI
tutorials which guided me through the technical aspects of dashboard
creation and data analysis.
Lastly, I appreciate the constant motivation and encouragement from my
family and friends throughout the project.
NIKHIL TRIPATHI
Abstract
This project focuses on the development of a Healthcare Patient
Analytics Dashboard using Microsoft Excel and Power BI.
The primary objective is to transform raw patient data into
meaningful visual insights that support informed
decisionmaking in healthcare environments.
The dataset includes patient records, appointments, insurance
status, doctor assignments, and bed availability. Using Power
4
BI’s powerful visualization tools, the project highlights key
metrics such as total patients, active doctors, insurance coverage
percentage, and bed occupancy.
Different visual elements like KPI Cards, Bar Charts, Pie Charts,
Tree maps, and Slicers were used for interactive analysis. The
project emphasizes the importance of data cleaning, proper
model structuring, and visual design in creating an intuitive and
informative dashboard.
The outcome delivers a dynamic, real-time overview of
healthcare performance, helping institutions monitor patient
flow, doctor efficiency, and resource allocation. This project
demonstrates how healthcare analytics can improve operational
efficiency and patient care quality.
List of Tables
1: Overview of Patient Demographic Details
2: Doctor-Wise Appointment Distribution
3: Patient Insurance Coverage Status
4: Bed Occupancy: Occupied vs. Vacant Analysis
5: Specialization-Wise Active Doctors Count
6: Monthly Appointment Volume Trend
7: Gender-Based Patient Distribution
8: Admission and Discharge Summary
5
9: Insurance Patient Ratio Comparison
10: Specialization-Wise Patient Consultation Summary
11: Patient Appointment Status Summary.
12: Doctor-Wise Patient Load Analysis.
13: Insurance Type vs. Appointment Count.
List of Figures / Charts
1. Healthcare Patient Analytics Dashboard Overview
2. KPI Cards: Total Patients, Active Doctors, Occupied Status, Insurance
Percentage.
3.Stacked Bar Chart Showing Appointment by Specialization and Doctor
Name.
4. Pie Chart representing Occupied vs Vacant Beds Percentage.
5. Tree Map displaying Count of patient ID by Doctor Name and
Specialization.
6. Clustered Column Chart Showing Count of Patient ID by
Specialization.
7. Slicer Filtering on Doctor Name, Expert, Specialization, Insurance
status, Date, First Name.
6
8. Table Visual Presenting Details in Doctor Name, Insurance, Count of
Appointment ID, Specialization, Date of Birth, First Name, Gender,
Patient ID.
9. Stacked Column Chart displaying Count of Patient ID by First Name
and Expert.
10. Donut Chart Showing Count of Appointment ID by Name.
List of Schemes / Algorithms
In this project, several logical schemes and data-handling
algorithms were applied to ensure clean data preparation,
effective visualization, and accurate insights from the healthcare
dataset. Below is a list of the core schemes and concepts used:
1. Data Cleaning Algorithm:
Duplicate detection and removal.
Handling missing values.
Consistent formatting of patient names, appointment dates, and
insurance status.
2. Data Aggregation Scheme:
7
Summarization of large records using aggregation functions like
COUNT (), SUM (), AVERAGE (), MAX (), and MIN ().
For example: counting total patients, active doctors, total
appointments, and insurance-covered patients.
3. Grouping and Filtering Algorithm
Grouping data based on fields like Doctor Name,
Department, Appointment Date, and Specialization.
Using Power BI’s slicers for real-time filtering by Doctor,
Date, Department, Insurance status, etc.
4. Sorting Algorithm:
Sorting data by ascending/descending order for better
visualization clarity, especially in Bar Charts and Tables.
5. Visualization Scheme:
Selection of appropriate chart types based on data patterns:
Bar Chart — Doctor-wise appointments.
Pie Chart — Occupied Vs Vacant Beds.
Tree Map — Count of Patient id by doctor name and
specialization.
8
Table Show — Raw data representation for crossreference.
6. DAX (Data Analysis Expressions):
Use of DAX formulas for creating calculated fields like:
Total Appointments = COUNT (Appointment ID)
Insurance Percentage = (Insurance Patients / Total Patients) * 100
Bed Occupancy Rate = (Occupied Beds / Total Beds) * 100
7. KPI Scheme:
Implementing KPIs to track important metrics:
Active Doctors-10
Total Patients-60
Insurance Coverage % - 51.67%
Bed Availability-60
Appointment Completion Rate.
9
8. Time-Series Handling Scheme:
Plotting appointment trends based on Appointment Date
using Line Charts and Date Hierarchies.
9. Slicer Interaction Logic:
Applying slicers to filter multiple visuals simultaneously, giving
the end-user the power to explore data based on real-time
selections.
List of Symbols
% – Percentage (e.g., Occupied Bed %, Insurance Coverage %)
↑ / ↓ – Indicates increase or decrease in data trends
(Appointments, Occupancy)
# – Represents count or number (e.g., # of patients, # of
Appointments)
Ø – Denotes average values (e.g., Average Appointments per
Doctor)
10
→ – Flow representation (e.g., Patient Flow Direction or Process
Stages)
₹ – Currency symbol for financial values (if cost data is
involved)
⬤ — Represents a data point in charts and graphs.
⇌ — Indicates a dynamic or reversible state.
∅ — Denotes a null or empty value.
∞ — Represents infinity or an undefined large value.
√ — Represents square root.
⬛ — Used as a legend marker in Power BI charts.
List of Abbreviations
PID — Patient ID
DOB — Date of Birth
DOA — Date of Admission
DOD — Date of Discharge
ICU — Intensive Care Unit
OPD — Outpatient Department
LOS — Length of Stay
MRN — Medical Record Number
BP — Blood Pressure
HR — Heart Rate
BMI — Body Mass Index
ID — Identification
Dr. — Doctor
11
Dept. — Department
Appt. — Appointment
Tx — Treatment
Rx — Prescription
Ins. — Insurance
% — Percentage
EMR — Electronic Medical Record
EHR — Electronic Health Record
PBI — Power BI
KPIs — Key Performance Indicators
Chapter 1: Introduction
1.1 Purpose
The aim of this project — Healthcare Patient Analytics
Dashboard is to present a wise and effective means of grasping
healthcare data through contemporary visualization tools such
as Microsoft Excel and Power BI. Hospitals and medical
centers produce huge amounts of data on a daily basis, i.e.,
patient records, appointment schedules, doctor appointments,
insurance, departmental allocation, and bed occupancy. In the
absence of a suitable dashboard, the healthcare team may not be
able to grasp the data at a glance easily and effectively.
This project aims to solve that problem by transforming raw
healthcare data into clean, structured, and visualized data. The
dashboard transforms complex data into actionable KPIs, charts,
and filters, allowing decision-makers to easily grasp hospital
12
performance, resource utilization, patient care quality, and more.
The project also highlights the growing importance of datadriven
decision-making within the healthcare sector, especially in terms
of enhanced planning, resource utilization, and overall efficiency
of services.
1.2 Applicability: This Healthcare Analytics Dashboard
proves to be highly effective in all the departments of a
hospital or clinic infrastructure. Be it front desk managing
appointments, the administrative staff tracking occupancy levels,
or even the management staff tracking the performance of
doctors, this dashboard can facilitate effective, real-time
decision-making.
The project can be applied to many real-world healthcare
scenarios such as:
Hospital Administration: To manage patient flow,
physician assignments, and bed availability.
Insurance Departments: In order to monitor the insurance
coverage of patients.
Department Heads: For tracking appointments, specializations,
and healthcare workload.
Government Health Agencies: For the analysis of public health
data, resource planning, and healthcare capacity planning.
Academic Research: To analyze health care trends
13
and enhance hospital organizational structures.
1.3 Types of Projects: This project falls under the category of
Data Analytics and Visualization Projects with an industry theme
of healthcare systems. The following types of projects are
relevant:
1. Academic Data Visualization Project — For students to
learn data analysis in real-case scenarios, visualization design,
and report generation.
2. Business Intelligence Project — Designed for healthcare
organizations to leverage real-time data insights for improved
decision-making and operational excellence.
3. Research and Development Project — Used by health data
scientists and researchers to study trends, predict future
healthcare requirements, and identify areas of improved patient
care.
4. Performance Monitoring System — Hospitals may use this
type of dashboard for continuous monitoring of KPIs like
patient inflow, appointments, occupancy, insurance status, etc.
The modularity of the dashboard makes it possible to reuse or
extend it with more data, other visualization techniques, and
advanced reporting systems as needed.
1.4 Important Dates:
14
The timeline of this project was carefully designed to ensure systematic
completion:
Data Collection Phase: Initial healthcare dataset was collected, cleaned,
and verified to maintain accuracy and integrity.
Data Preparation Phase: Data was imported into Excel, duplicates
were removed, and errors were corrected before loading into Power BI.
Dashboard Design Phase: KPIs, charts, slicers, and filters were
designed in Power BI based on the prepared dataset. Iterative changes
were applied to improve the look, feel, and functionality of the
dashboard.
Report Writing Phase: Once the dashboard was completed, the detailed
documentation (this report) was created, describing each part of the
process from problem identification to solution deployment.
Final Submission Date: The project is scheduled for presentation
and submission on the assigned deadline by the college faculty.
Tracking these milestones helped ensure the project remained
organized and professional throughout its development.
This chapter sets the stage for understanding the entire project
scope. The next sections will cover Project Objectives,
Literature Review, Methodology, Results, and Conclusion in
depth, providing a clear and structured explanation of how the
Healthcare Patient Analytics Dashboard was developed and why
it is an essential tool for modern healthcare management.
15
Chapter 2: Review of Literature
Healthcare analytics has become a central
discipline in contemporary
medical management that marries data science and visualization to
enable evidence-based decision-making. Through the use of structured
data with the help of tools such as Excel and Power BI, healthcare
systems and hospitals can transform complicated patient records into
actionable intelligence.
1. Significance of Healthcare Data Analysis:
Various studies identify that healthcare organizations generate
vast quantities of patient information, which remain untapped
in the absence of analytics.
Analytics allows healthcare organizations to monitor patient admissions,
treatment outcomes, appointment volumes, and insurance claims, with
real-time decision-making data.
2. Data Visualization Tools Role:
16
Literature identifies software like Power BI as key enablers to mold
raw data sets into interactive dashboards. Graphical elements
like bar charts, pie charts, KPIs, and slicers allow users to
identify trends, outliers, and variations in performance between
departments, and this improves efficiency and quality of patient
care.
3. Predictive Healthcare Models:
Researchers have shown that algorithms and data visualization on
historical patient data help hospitals in predicting disease outbreaks,
reducing readmissions, and optimizing doctor-patient assignments. BI
with Machine Learning and healthcare analytics research is gaining
popularity.
4. Application in Patient-Centered Care:
Literature indicates that data analytics provides better patient
experience through the advantage of being able to monitor bed
occupancy, treatment, and discharge planning. Through patientlevel
data, hospitals can allocate resources efficiently and enhance the
delivery of health services.
5. Policy and Decision-Making Influence:
Many studies emphasize that government health authorities, health
insurers, and hospital administrators increasingly rely on dashboards to
guide policy, claims, and performance audits. Healthcare analytics offers
a factbased platform to enhance operational and strategic decision-
making.
17
Chapter-3 Implementation of project
3.1 Introduction: The Implementation phase is the most significant part of
any project, as it involves the translation of conceptual design into a functional and
interactive dashboard. In this Healthcare Analytics project, patient-related data from
hospitals were compiled, cleaned, and visualized using Microsoft Excel and Power
BI to provide deep insights for decision-making.
3.2 Data Collection Patient data was collected from various hospital departments
and compiled into an Excel sheet. The dataset included vital information such
as:
Patient ID
First Name & Last Name
Gender
Date of Birth
Doctor Assigned
Specialization
Appointment Date
Appointment ID
Insurance Coverage
18
3.3 Data Cleaning and Preprocessing Data cleaning was done
in Microsoft Excel to ensure:
Removal of duplicates
Correction of inconsistent spellings and formats
Handling of missing values
Date formatting for temporal analysis
19
3.4 Visualization Using Power BI The cleaned dataset was imported into
Microsoft Power BI for visualization and analysis. Several visualizations were
created to make the data interactive and easy to interpret:
Card Visuals (KPIs): Displaying Total Patients, Total Appointments,
Total Doctors, Total Occupied Beds, and Average Insurance Coverage.
Pie Chart: Representing Occupied vs Vacant Beds Distribution.
Clustered Column Chart: Showing Count of Appointments by
Specialization.
Donut Chart: Count of Appointment ID By Doctor Name.
Tree Map: Visualizing Patient ID distribution across Doctor Names
and Specializations.
Stacked Column Chart: Showing Patient ID By First Name
And Expert.
Stacked Bar Chart: Appointment ID By Specialization And
Doctors Name.
20
Table Visual: Displaying Doctor Name, Insurance, Count of
Appointment ID, Specialization, Date of Birth, First Name
And Gender.
Slicers: Allowing filtering based On First Name, Doctor
Name, Expert, Specialization, Insurance Status And
Appointment Date.
“The Following Screenshot illustrates the Final design
of the Healthcare Analytics Dashboard, highlighting key
insights derived from real-time data visualization.
21
Summary of Implementation: Through this implementation
process, the healthcare dataset was successfully converted
into a fully functional analytical dashboard, ensuring data
driven decision-making for hospital management.
Chapter-4 Results and Discussions
The Healthcare Analytics Dashboard was developed based on patient
appointment and physician specialty data to provide meaningful insights
into hospital resource utilization and service patterns. After developing
the available dataset in Excel and graphically portraying the same in
Power BI, the results indicate unique patterns, which are discussed
below.
4.1 Patient Distribution
According to the analysis, the hospital treated a total of 60 patients. The
Bar Chart visualization of specialization indicates that the maximum
number of patients fall under the departments of Psychiatry and
Pediatrics, which have been
noted as priority fields of patient treatment. The number of patients was f
ewer in departments like Dermatology and Cardiology.
4.2 Appointment Insights
22
The Donut Chart showed that some of the doctors, such as Dr. Randeep
and Dr. Ashok, have much more appointments than other doctors,
which indicates their popularity or demand for the services.
The appointments are evenly distributed among the doctors but with
distinct spikes for a couple of names.
4.3 Bed Occupancy Status
The Vacant vs. Occupied Beds Pie Chart indicated that 23.33% of the
beds were vacant and only 76.67% were occupied throughout the
observation period. This indicates the facility has ample capacity,
though resource optimization may be an area for consideration, or it
may be indicative of varying patient admission rates.
4.4 Doctor Specialization and Patient Mapping
The Tree Map gave a clear indication of which specializations had
the highest patient encounters. Physicians in General Medicine,
Pediatrics, and Psychiatry dominated the chart, affirming these
departments as high-engagement departments.
4.5 Insurance Coverage Analysis
The dashboard presented the fact that only 51.67% of the patients were
insured and highlighted that nearly half of the hospital's patients are
self-pay or uninsured. This is an observation that will help the
administration understand the need for improved insurance tieups or
patient financial counseling.
23
4.6 Patient Trends and Expert Guidelines
The Stacked Column Chart indicated that the majority of patients
were treated or referred by physicians designated as Experts in
their specific categories. Patients under Brain Tumor, Cancer, and
Pediatrics specialists were much higher than others, showing the
immense reliance on experienced healthcare professionals.
4.7 Summary of Results
In summary, the dashboard uncovered the following critical
observations:
Psychiatry, Pediatrics, and General Medicine have the highest patient
inflow.
Bed Utilization is below optimal, suggesting opportunities for admission
rate review or outreach.
Half the patients do not have insurance, creating potential for
hospitallevel insurance policy collaborations.
Appointment trends show concentration toward a few doctors, implying
possible resource allocation or scheduling optimization.
Discussion:
This data-driven strategy with Power BI made it easy to convert raw
patient data into meaningful visualizations. Through the analysis of
various parameters such as occupancy, patient distribution, frequency of
appointments, and insurance, healthcare management can make sound
24
decisions about staffing, marketing, patient care, and optimal utilization
of resources.
The visualizations not only enable big data but also help
administrators identify bottlenecks, patient patterns, and the most
sought-after services. The findings of this project can directly lead to
improved hospital management, improved patient care, and effective
doctor allocation.
Final Chapter- Conclusion and Future Scope
Conclusion:
The Healthcare Analytics Dashboard project has evidently demonstrated
the power of data analytics and visualization in rendering complex sets
of patient information more understandable. Using Excel to prepare the
data and Power BI to create interactive dashboards, the project has
readily demonstrated key points about patien t flow, physician
specialties, appointment distribution, bed utilization, and insurance
coverage patterns.
25
The graphical representation of the findings showed that Pediatrics,
Psychiatry, and General Medicine are the top demand specializations,
and Insurance Coverage is seen in nearly half of the patients, which is a
gap that can be filled by hospital administration. Likewise, analysis of
bed occupancy status showed that utilization of resources can be
maximized by utilizing vacant capacities or enhancing patient inflow.
This project effectively shows how modern healthcare systems can
benefit from real-time data analysis and how decisions can be improved
based on facts rather than assumptions.
Future Scope:
Although this project provided informative results, there are still
other more general areas where the system can be improved:
1. Real-time Data Integration:
Later extensions can involve admission and discharge live updates to the
dashboard, wherein the hospital employees can track the bed availability,
appointment scheduling, and physician designation more effectively.
2. Predictive Analytics: Machine
learning model incorporation can be utilized to predict patient inflow
trends, peak admissions times, or disease seasonal patterns to facilitate
enhanced planning for personnel, beds, and resources.
3. Patient Feedback Analytics:
Merging patient satisfaction scores and comments would be
useful to collect data on the quality of service and support
hospital performance improvement.
4. Integration with EMR Systems:
26
Direct integration with Electronic Medical Records (EMR) will enable
real-time and accurate data capture, avoiding the possibility of manual
errors and improving the reliability of reports.
5. Geographical Analysis: Extension of the system to track the
geographical spread of the patients would help in outreach
programmes or in branch planning.
Final Words:
The project has given an excellent learning experience in data
handling, visualization, and understanding of the healthcare
system. Using such dashboards in real hospitals can improve
patient services, reduce resource waste, and enhance hospital
management decisions. The generated insights can also help
healthcare professionals to deliver improved and efficient
care.
Project Summary
27
Registration No: 323102281 Name of Student: Nikhil Tripathi Title
of Capstone Project / Project Work:
Healthcare Analytics Dashboard for Data-Driven Insights
Objectives of the Project:
1. To visualize healthcare data for clear understanding.
2. To analyze bed occupancy and doctor specialization.
3. To present appointment trends graphically.
4. To optimize healthcare operations via data insights.
Results and Findings:
The analysis revealed how bed occupancy and appointments vary Based on specialization and demand. The
Power BI dashboard supported real-time monitoring and helped management make data-driven decisions.
Specific outcomes of the Project:
Created dynamic dashboards for better healthcare insights.
Delivered real-time occupancy and appointment data.
Improved understanding of patient flow and resources.
Learnings from the Project:
Learned data cleaning and transformation using Excel.
Mastered Power BI dashboards and Dax Formulas.
Gained Knowledge of healthcare operational data.
Any Challenges/issues faced during the Project:
Faced missing and inconsistent data during cleaning.
Relationship error between multiple datasets.
Signature of the Student
References
1. [Nikhil Tripathi]. (2025). Self-Created Healthcare Patient
Dataset for Academic Visualization Project. Unpublished raw data.
28
2. Microsoft Learn. (2024). Power BI Documentation: Visualize
and Share Insights. URL:
https://learn.microsoft.com/en-us/powerhttps://learn.microsoft.com/en-us/power-
bi/fundamentals/bi/fundamentals/.
3. [Nikhil Tripathi]. (2025). Data Cleaning and Preprocessing using
Microsoft Excel & Power Query. Self-executed data transformation
for academic purpose.
4.Microsoft Power BI for Healthcare. (2025). Healthcare analytics and
insights using Power BI. Retrieved from.
URL: https://www.microsoft.com/en-in/powerhttps://www.microsoft.com/en-in/
power-platform/products/power-bi/industry/healthcareplatform/products/power-bi/
industry/healthcare.
5.Microsoft Learn Power BI Documentation: Visualize and Share
Insights. Available at: URL:
https://learn.microsoft.com/enhttps://learn.microsoft.com/en-us/power-bi/
fundamentals/us/power-bi/fundamentals/.
These references provided valuable information and inspiration for
creating the content, design, and structure of the Healthcare Analytics
Dashboard.
29
