Project
Kaggle
Learn how to create a heart attack prediction model using real medical data and ChatGPT-4 features - from downloading datasets to a finished machine learning-based solution!


Practice on a real project ChatGPT-4 integration Detailed analysis of Kaggle
Start now Read more
About the Course
In this course, you will learn how to work effectively with the Kaggle platform and use ChatGPT-4 to automate data analysis and code generation. We'll walk you through all stages of an ML project, from preprocessing data and creating models such as logistic regression and Random Forest to interpreting results and improving performance. This course will help you confidently apply what you've learned in practice!
Who this course is suitable for
Beginners in Data Science
Master ML on a real project with ChatGPT-4 support, even if you're just starting your data analysis journey.
Data Analysts
Take your data analysis to the next level by learning how to build and optimize ML models for medical predictions.
Developers
Add in-demand Kaggle and generative AI skills to your arsenal.
Healthcare Professionals
Learn how to apply Data Science to medical analytics and predictive analytics.
Course Experts
Mikhail Kovalev
Lead Data Scientist at MedAnalytics Inc.
10+ years of experience in machine learning and medical data analysis. Specializes in predictive analytics and computational diagnostics. Winner of 5 Kaggle competitions in the HealthTech category.
Anna Smirnova
Senior ML Engineer at NeuroByte
Expert in generative AI and data analytics automation. Developed 15+ industrial ML models.
Dmitry Somov
Kaggle Grandmaster | Ex-Google
Top 1% of Kaggle members with 12+ years of experience. Specializing in feature engineering and optimization of ML algorithms. Trained 1000+ students on Kaggle.
Sergey Bastilashvili
Kaggle Grandmaster | Senior AI Researcher at MedData Labs
5+ years experience in medical AI solutions and competitive data science
What you will learn in the course:
  • Working professionally with Kaggle - From registration to publishing finished solutions, including navigating datasets and competitions.
  • Medical Data Processing - Cleaning, analyzing, and visualizing real-world medical datasets (EDA).
  • ML model building - From classical algorithms (logistic regression, Random Forest) to neural networks.
  • Model optimization - Hyperparameter selection, evaluation of metrics (AUC-ROC, accuracy, F1-score) and improvement of results.
  • Automation with ChatGPT-4 - Using AI to generate code, analyze data, and accelerate workflow.
  • Interpreting Results - Explaining model findings to clinicians and businesses (Explainable AI).
  • Decision Deployment - Basics of implementing models in production (using medical cases as an example).
  • Preparing for real-world challenges - From project presentation to Kaggle competitions.
Course Project:
Predicting Heart Attacks from Real Medical Data
In this course, you will develop an ML model capable of predicting heart attack risk from clinical data. You will work with a real dataset with Kaggle that reflects cardiac diagnostic tasks.

This project will give you hands-on experience of the full cycle of Data Science, from processing raw data to creating a working model that you can demonstrate to potential employers.
Course Program
Module 1. First Contact with Kaggle
  • What is Kaggle?
  • FAQ about Kaggle
  • Registering on Kaggle and Member Login Procedures
  • Project Link File - Hearth Attack Prediction Project, Machine Learning
  • Getting to Know the Kaggle Homepage
  • Quiz
Module 2. Competition Section on Kaggle
  • Lesson 1
  • Lesson 2
  • Quiz
Module 3. Dataset Section on Kaggle
  • Datasets on Kaggle
Module 4. Code Section on Kaggle
  • Examining the Code Section in Kaggle: Lesson 1
  • Examining the Code Section in Kaggle Lesson 2
  • Examining the Code Section in Kaggle Lesson 3
  • Quiz
Module 5. Discussion Section on Kaggle
  • What is Discussion on Kaggle?
  • Quiz
Module 6. Other Most Used Options on Kaggle
  • Courses in Kaggle
  • Ranking Among Users on Kaggle
  • Blog and Documentation Sections
  • Quiz
Module 7. Details on Kaggle
  • User Page Review on Kaggle
  • Treasure in The Kaggle
  • Publishing Notebooks on Kaggle
  • What Should Be Done to Achieve Success in Kaggle?
  • Quiz
Module 8. Introduction to Machine Learning with Real Hearth Attack Prediction Project
  • First Step to the Project
  • FAQ about Machine Learning, Data Science
  • Notebook Design to be Used in the Project
  • Project Link File - Hearth Attack Prediction Project, Machine Learning
  • Examining the Project Topic
  • Recognizing Variables In Dataset
  • Quiz
Module 9. First Organization
  • Required Python Libraries
  • Loading the Dataset
  • Initial analysis on the dataset
  • Quiz
Module 10. Preparation for Exploratory Data Analysis (EDA)
  • Examining Missing Values
  • Examining Unique Values
  • Separating variables (Numeric or Categorical)
  • Examining Statistics of Variables
  • Quiz
Module 11. Exploratory Data Analysis (EDA) - Uni-variate Analysis
  • Numeric Variables (Analysis with Distplot): Lesson 1
  • Numeric Variables (Analysis with Distplot): Lesson 2
  • Categoric Variables (Analysis with Pie Chart): Lesson 1
  • Categoric Variables (Analysis with Pie Chart): Lesson 2
  • Examining the Missing Data According to the Analysis Result
  • Quiz
Module 12. Exploratory Data Analysis (EDA) - Bi-variate Analysis
  • Numeric Variables – Target Variable (Analysis with FacetGrid): Lesson 1
  • Numeric Variables – Target Variable (Analysis with FacetGrid): Lesson 2
  • Categoric Variables – Target Variable (Analysis with Count Plot): Lesson 1
  • Categoric Variables – Target Variable (Analysis with Count Plot): Lesson 2
  • Examining Numeric Variables Among Themselves (Analysis with Pair Plot) Lesson 1
  • Examining Numeric Variables Among Themselves (Analysis with Pair Plot) Lesson 2
  • Feature Scaling with the Robust Scaler Method
  • Creating a New DataFrame with the Melt() Function
  • Numerical - Categorical Variables (Analysis with Swarm Plot): Lesson 1
  • Numerical - Categorical Variables (Analysis with Swarm Plot): Lesson 2
  • Numerical - Categorical Variables (Analysis with Box Plot): Lesson 1
  • Numerical - Categorical Variables (Analysis with Box Plot): Lesson 2
  • Relationships between variables (Analysis with Heatmap): Lesson 1
  • Relationships between variables (Analysis with Heatmap): Lesson 2
  • Quiz
Module 13. Preparing for Modeling in Machine Learning
  • Dropping Columns with Low Correlation
  • Visualizing Outliers
  • Dealing with Outliers – Trtbps Variable: Lesson 1
  • Dealing with Outliers – Trtbps Variable: Lesson 2
  • Dealing with Outliers – Thalach Variable
  • Dealing with Outliers – Oldpeak Variable
  • Determining Distributions of Numeric Variables
  • Transformation Operations on Unsymmetrical Data
  • Applying One Hot Encoding Method to Categorical Variables
  • Feature Scaling with the Robust Scaler Method for Machine Learning Algorithms
  • Separating Data into Test and Training Set
  • Quiz
Module 14. Modeling for Machine Learning
  • Logistic Regression
  • Cross Validation
  • Roc Curve and Area Under Curve (AUC)
  • Hyperparameter Optimization (with GridSearchCV)
  • Decision Tree Algorithm
  • Support Vector Machine Algorithm
  • Random Forest Algorithm
  • Hyperparameter Optimization (with GridSearchCV)
  • Quiz
Module 15. Conclusion
  • Project Conclusion and Sharing
  • Quiz
Module 16. Project Files and Sources
  • Source
  • Prompts
  • Github Link
  • Kaggle Link
Module 17. ChatGPT-4 Unleashed: Innovations in Communication and Learning
  • Big News: Introducing ChatGPT-4
  • How to Use ChatGPT-4?
  • Chronological Development of ChatGPT-4
  • What are capabilities of ChatGPT-4?
  • As an App: ChatGPT
  • Voice Communication with ChatGPT-4
  • Instant Translation in 50+ Languages
  • Interview Preparation with ChatGPT-4
  • Visual Commentary with ChatGPT-4: Lesson 1
  • Lesson 2
Module 18. Dataset Exploration and Field Knowledge
  • ChatGPT for Generative AI Introduction
  • Accessing the Dataset
  • First Task: Field Knowledge
  • Continuing with Field Knowledge
  • Loading the Dataset and Understanding Variables
  • Delving into the Details of Variables
Module 19. Variable Analysis: Missing Date, Unique Values and Statistics
  • Let's Perform the First Analysis
  • Updating Variable Names
  • Examining Missing Values
  • Examining Unique Values
  • Examining Statistics of Variables Lesson 1
  • Lesson 2
  • Lesson 3
Module 20. Exploratory Data Analysis (EDA) 1
  • Exploratory Data Analysis (EDA)
  • Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
Module 21. (EDA) 2
  • Importance of Bivariate Analysis in Data Science
  • Numerical Variables vs Target Variable Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Categoric Variables vs Target Variable Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
Module 22. (EDA) 3
  • Correlation Between Numerical and Categorical Variables and the Target Variable Lesson 1
  • Lesson 2
  • Examining Numeric Variables Among Themselves Lesson 1
  • Lesson 2
  • Numerical Variables - Categorical Variables Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
  • Categorical Variables with Swarm Plot Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
  • Lesson 6
  • Relationships between variables (Analysis with Heatmap) Lesson 1
  • Lesson 2
Module 23. Preparation for Modeling
  • Preparation for Modeling
  • Dropping Columns with Low Correlation
  • Struggling Outliers
  • Visualizing Outliers Lesson 1
  • Lesson 2
  • Lesson 3
  • Dealing with Outliers Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
  • Determining Distributions
  • Determining Distributions of Numeric Variables Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
  • Lesson 5
  • Applying One Hot Encoding Method to Categorical Variables Lesson - 1
  • Lesson - 2
  • Feature Scaling with the RobustScaler Method for Machine Learning Algorithms
  • Separating Data into Test and Training Set
Module 24. Machine Learning Algorithm - Logistic Regression
  • Logistic Regression Algorithm Lesson 1
  • Lesson 2
  • Cross Validation
  • ROC Curve and Area Under Curve (AUC) Lesson 1
  • Lesson 2
  • Hyperparameter Optimization (with GridSearchCV)
  • Hyperparameter Tuning for Logistic Regression Model
Module 25. Decision Tree & SVM
  • Decision Tree Algorithm Lesson 1
  • Lesson 2
  • Support Vector Machine Algorithm Lesson 1
  • Lesson 2
Module 26. Random Forest
  • Random Forest Algorithm Lesson 1
  • Lesson 2
  • Lesson 3
  • Lesson 4
Module 27. Conclusion
  • Project Conclusion
  • Suggestions and Closing
Module 28. Extra
  • Generative AI with Heart Attack Prediction Kaggle Project
What's in store for you in the course
Video lessons
Watch the lessons at your own pace.
Step-by-step instructions
Complete practice assignments and submit them for review.
Community
Ask questions, exchange experiences and share your impressions.
Experts
All mentors are practicing professionals with years of experience in IT.
Certificate
Get a document that proves your qualification.
Certificate of Professional Development
Get an official document confirming your new skills. It will become a strong argument for career growth and professional development.
Choose a tariff
Introductory
$200
Training program 7 modules Video lessons Practical assignments Questions to test your knowledge Assignment check and feedback from tutors Chat for students and tutors Access to the course - 1 month Without certificate
Start Now
Basic
$300
Training program - 15 modules Video lessons Practical assignments Questions to test your knowledge Assignment check and feedback from tutors Student chat Access to the course - 3 months Without certificate
Start Now
Standard
$400
Training program - 28 modules Video lessons Practical tasks Questions to test knowledge Assignment checking and feedback from tutors Student chat Access to the course - 8 months Certificate
Start Now
Standard Plus
$500
Individual mentor support Training program - 28 modules Video lessons Practical assignments Questions to test your knowledge Error analysis and recommendations Student chat Access to the course - 18 months Certificate
Start Now
Corporate
$900
For corporate training for employees Groups of 5-10 people Training program - 28 modules Video lessons Practical tasks Questions to test knowledge Checking of assignments and feedback from supervisors Student chat Access to the course - 18 months Certificate
Start Now
Over 4,000 people have been trained by us
One in four of our students came to us by recommendation
Anna
Data Analyst → Junior ML Engineer
Thanks to the heart attack prediction project, I was able to show my employer not a training dataset, but a solution to a real medical problem for the first time. Already at the interview at HealthTech-startup I was asked to solve this case and was hired!
Olga
bioinformatics student
Kaggle seemed too complicated for me, but the cardiac diagnostics project laid everything out step by step. I won my first contest with 89% model accuracy! This is now my case study for applying to a master's program in ML.
Ivan
Python developer
The transition into Data Science seemed vague until I did this project. In 2 months I learned not just how to write code, but how to solve applied problems. Already got an offer as a Junior DS - the employer liked that I had a medical case.
Ekaterina
Product Manager in pharma
The course gave me a language for communicating with data scientists. Now I can give them specific tasks to analyze clinical data. Our pilot project on risk prediction even received an internal grant!
FAQ
Do I need Data Science experience for this course?
No! The course is designed for different levels of experience. We will start with the basics of data analysis and gradually move on to advanced topics. Even if you are new to Python and ML, the lessons and practice will help you understand.
How much time should I devote to the course?
We recommend 8-10 hours per week (lectures + practice). This pace will allow you to comfortably master the material in 1.5-2 months. But you can study at your own pace - access to the course will remain forever.
Can I combine the course with work/study?
Yes! All lessons are recorded and assignments can be completed at your convenience. Many students take the course alongside their main activity, taking time out in the evenings or weekends.
What if the course is not suitable?
You can get your money back within 14 days of purchase** - no questions asked. If you take more than 3 lessons, the refund will be prorated.
What result will I get?
At the end of the course you will create a working ML model for predicting heart attacks, master professional analysis of medical data and work with Kaggle, as well as receive a finished project and a certificate for your portfolio. This will set you apart from other candidates when applying for jobs.