mznaturl1/heart-disease-prediction

Heart-disease-prediction

Identifying Heart Disease Indicators

Group Members:

• Jacob Darmofal
• Vincent Elequin
• Tamica Grant
• Isidore Lozano

Project Description:

• Using CDC survey data from 2000 to 2020 of 400,000 adults.
• We intend to collect and analyze the data to build machine learning models to understand which characteristics (gender, age, race/ethnicity, etc.) to predict heart disease risk factors.
• Using Pandas, Matplotlib, and PostgreSQL to visualize mortality predictions.
• Determine if there are high risk populations geographically

Questions to ask:

• What health factors will have a higher chance of heart disease?
• Do smokers have a higher risk of having heart disease?
• What age category is more expected?
• Which feature(s) in our dataset impact the possibility of heart disease?

Parameters to consider:

• heart_disease
• bmi
• smoking
• alcohol consumption
• history of stroke
• physical health
• mental health
• gender
• age
• race
• diabetic
• physical activity
• general health
• hours of sleep
• asthma
• kidney disease
• skin cancer

Resources:

• Personal Key Indicators of Heart Disease | Kaggle
• Heart Disease Stroke Prevention Vital Statistics from CDC (https://chronicdata.cdc.gov/
• Heart-Disease-Stroke-Prevention/National-Vital-Statistics-System-NVSS-National-Car/kztq-p2jf)
  • The above databases are made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/. Any rights in individual contents of the database are licensed under the Database Contents License: http://opendatacommons.org/licenses/dbcl/1.0/
• Microsoft Bing for pics https://www.bing.com/images/create
• ChatGPT (www.openai.com)
• Neural Networks https://scikit-learn.org/
• Imbalanced Learn https://imbalanced-learn.org/stable/references/generated/imblearn.over_sampling.-
• SMOTE https://imbalanced-learn.org/stable/references/generated/imblearn.over_sampling.SMOTE.html
• Tableau https://www.tableau.com
• Tableau story published to: https://public.tableau.com/app/profile/tamica.grant/viz/HeartDiseaseMap/DiseasesoftheHeartAnalysis?publish=yes

Scope of Work:

• Research data sources
• Create a front-end interface to JSON or csv file to “smarten” the algorithm.
• Perform a deep dive with existing data using machine learning.
• To predict mortality rates from data available - Predicting and diagnosing illnesses
• Create a visualization that continues to learn where clusters lie based on ML (use Leaflet or - Plotly to change the visualization).
• Identify population areas that have the highest mortality rates - Developing stronger prevention strategies.
• Create an idea using mock data and simulate how machine learning might be used.
• Create an analysis of existing data to make a prediction, classification, or regression.
• Initial GitHub repository and set-up of Google slides.