Skip to content
View bamideleadedeji's full-sized avatar

Block or report bamideleadedeji

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bamideleadedeji/README.md

Hi, I'm Bamidele Adedeji

Data Scientist | Healthcare Analytics | Machine Learning Engineer

SQL & Data Engineering: Architected a relational SQLite database for hospital operations, using complex JOINs and date functions to reduce appointment no-shows

Project Portfolio

Breast Cancer Diagnostic Classification

  • Problem: Early detection of malignant tumors using cellular measurements.
  • Key Skill: SVM with high-recall optimization (98%) and Multicollinearity handling.
  • Tech: Python, Scikit-Learn, Seaborn.

Heart Disease Risk Prediction

  • Problem: Predicting patient cardiac risk based on clinical indicators.
  • Key Skill: Logistic Regression and Feature Importance analysis.
  • Tech: Pandas, Matplotlib.

Hospital No-Show: Operational Intelligence

  • Problem: Reducing revenue loss by predicting appointment attendance.
  • Key Skill: Random Forest and custom Data Simulation Engine to overcome technical blocks.
  • Tech: Random Forest, Data Simulation.

I specialize in transforming complex healthcare and operational data into actionable insights. My work focuses on high-stakes predictive modeling, ranging from clinical cancer diagnostics to optimizing hospital efficiency.

Technical Toolbox

  • Languages: Python (Pandas, NumPy, Scikit-Learn)
  • Modeling: Logistic Regression, SVM, Random Forest, Feature Engineering
  • Tools: Jupyter, Matplotlib, Seaborn, Git/GitHub
  • Specialties: Multicollinearity Analysis, Clinical Recall Optimization, Data Simulation

Featured Portfolio Projects

1. Breast Cancer Diagnostic Classification

  • The Goal: Classify cell nuclei as Malignant or Benign with 98% Recall.
  • The Tech: Implemented SVM and handled Multicollinearity by removing redundant 90%+ correlated features.
  • Impact: Prioritizes clinical safety by minimizing false negatives in cancer detection.

2. Heart Disease Risk Prediction

  • The Goal: Identify high-risk cardiac patients using clinical indicators.
  • The Tech: Used Logistic Regression and Feature Importance to rank risk factors like age and cholesterol.
  • Impact: Provides a baseline for preventative medical screening tools.

3. [Hospital No-Show: Operational Intelligence]((bamideleadedeji)

  • The Goal: Predict patient attendance to improve clinic efficiency.
  • The Tech: Utilized Random Forest and engineered a WaitDays feature.
  • The Solve: Successfully bypassed network connectivity blockers (WinError 10060) by building a custom Data Simulation Engine.

Let's Connect!

Pinned Loading

  1. Cookie-Review-Transformation Cookie-Review-Transformation Public

    Jupyter Notebook

  2. Health-Insurance-Regression Health-Insurance-Regression Public

    Predictive modeling of medical insurance costs using Linear Regression, feature encoding, and correlation analysis

    Jupyter Notebook