Scribd
Upload
13 views8 pages

AIT 580 - Final Project

This project analyzes COVID-19 mortality trends across U.S. states using data analytics and machine learning to uncover healthcare disparities and improve public health strategies. The study utilizes a dataset of over 16,000 records and implements various predictive models, achieving high accuracy in forecasting deaths. Key findings highlight the importance of equitable healthcare access and suggest future enhancements, including additional datasets and global model expansions.

Uploaded by

Pavan Chilukuri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
13 views8 pages

AIT 580 - Final Project

This project analyzes COVID-19 mortality trends across U.S. states using data analytics and machine learning to uncover healthcare disparities and improve public health strategies. The study utilizes a dataset of over 16,000 records and implements various predictive models, achieving high accuracy in forecasting deaths. Key findings highlight the importance of equitable healthcare access and suggest future enhancements, including additional datasets and global model expansions.

Uploaded by

Pavan Chilukuri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
You are on page 1/ 8

Project

Assignment
Analyzing COVID-19 Mortality Trends Using
Data Analytics and Machine Learning

Surya Pavan Kumar Chilukuri || INFS 580 || Final


Project
Agen
da

Dataset Methods & Key Results Machine Conclusion


Overview Tools Learning
Insights
Introducti
on
Research Questions:
COVID-19 revealed healthcare disparities across U.S. states, with significant
differences in mortality rates and public health responses.
How did
Why It COVID-19-related
Matters: deaths vary across U.S. states throughout the
pandemic?
What is the correlation between COVID-19, pneumonia, and influenza deaths?
Studying mortality trends and co-morbidities offers insights to improve
How future
accurately did weekly
healthcare death counts
strategies align with expected mortality levels?
and preparedness.
This study analyzesanalytics
Predictive COVID-19can
mortality trends, using
help forecast advanced
surges analytics
and optimize and
resource
machineallocation.
learning to provide actionable insights for public health planning.
Dataset
Overview
Source: Provisional COVID-19 Death Counts by Week and State (CDC).
Key Features:
16,632 records spanning multiple years of the pandemic.

Contains weekly death counts for COVID-19, pneumonia, and influenza from
2020–2024.
Covers 54 U.S. states and territories.
Methods &
Tools

Data Data Cleaning Explorator Advanced Interactive


Collection and y Data Modeling and Dashboards
and Storage Preprocessing Analysis Prediction
Dataset hosted on Amazon (EDA)
Tools Used: Python Models Implemented:
S3 for scalability and easy Tools: R and SQL in Platform: Python Dash.
PostgreSQL. (Pandas, Matplotlib, Linear Regression:
accessibility. Seaborn). Baseline predictive Key Features:
Missing values imputed, Interactive visualization of
Benefits of AWS S3: duplicates removed, and Key Tasks: modeling.
Ensures secure storage Random Forest: trends by state and wave.
schema validation Geospatial analysis for Real-time insights into
and centralized access for performed. state-level trends. Captures complex non-
the analysis team. linear relationships with mortality distributions.
Outcome: Clean and Seasonal trend analysis of
Facilitates seamless COVID-19 deaths. improved accuracy (R² =
integration with R and structured dataset, ready for
statistical analysis and Correlation matrix 0.96).
Python scripts for data creation to understand Outcome: Accurate
retrieval. visualization.
relationships between predictions of weekly COVID-
illnesses. 19 deaths.
Interpretations &
Visualization Highlights

AIT 580_COVID-19 Visualiza


tions Loading.
……
Conclusi
on:
Summary:
COVID-19 mortality trends revealed critical healthcare disparities.
Machine learning models provided accurate predictions and actionable insights.
Findings emphasized the need for equitable access to healthcare and timely policy interventions.
Future Enhancements:

Incorporating additional datasets on vaccinations and resource utilization.


Expanding interactive models for global datasets.
Role of AWS S3:
Facilitated centralized storage of a large dataset, simplifying data preprocessing and analysis.
Enabled seamless collaboration among multiple tools, such as R, Python, and PostgreSQL.
THANK YOU!

You might also like