Meet Your Instructor: Ahmed Shaheen, MD
Ahmed Shaheen, MD
Computational Neuroscience Post-Doctorate Researcher, UAI, Chile
- Extensive experience in clinical and computational neuroscience research and data science
- Expert in integrating traditional statistical methods with innovative AI techniques in biomedical research
- Peer Reviewer for prestigious journals including Frontiers Neurology, Clinical Case Reports, Neuroscience, Neuroscience Informatics etc.
- Editorial Board Member of PLOS ONE
- H-index: 12
- Over 50 publications and more than 20 peer reviews (see research profiles for last updates)
- Specializes in applying advanced statistical and AI methods in primary and secondary clinical research, and neuroscience
Shaheen, MD's research focuses on leveraging machine learning and AI to advance biomedical sciences, with a particular emphasis on neurology and clinical applications.
Embrace the AI Revolution
This comprehensive course equips postgraduate researchers, PhD students, and advanced undergraduates with essential skills in statistical analysis and cutting-edge machine-learning techniques. While focusing on applications in biomedical, clinical, and neuroscience research, the foundational knowledge and practical skills you gain are transferable to diverse fields.
This course is a must for anyone working in the research field either as post-doctorate, research fellow, university staff, graduate or undergraduate students, or as research aspirants.
What sets this course apart?
Bridging Statistics and AI
Master fundamental statistical methods alongside the latest advancements in machine learning and deep learning, including large language models (LLMs).
Hands-on Learning
Gain practical experience with R and Python programming languages, applying your knowledge to real-world research problems through engaging examples and case studies.
Future-proof Skillset
This course is designed to evolve with the rapidly advancing field of AI, ensuring you stay ahead of the curve in your research career.
Useful Applications
You will learn to apply advanced statistical and AI methods in primary and secondary clinical research, neuroscience, imaging, radiology, time series, and more.
Courses
Course 1: R Programming and Data Analysis Fundamentals
-
R Basics: Exploring COVID-19 Data
- R fundamentals and data types
- Basic operations and functions
- Control structures and vectorization
-
Data Visualization with ggplot2
- Understanding ggplot2 layers
- Creating various plot types
- Customizing visualizations
-
Data Engineering with Tidyverse
- Tidy data principles
- Data manipulation with dplyr
- Advanced tidyverse operations
-
Handling Missing Data and Pre-processing
- Types of missing data
- Imputation techniques
- Data transformation and encoding
- Balancing data: upsampling/downsampling/bootstraping
-
Descriptive Statistics and Normality Testing
- Summary statistics and tables
- Measures of central tendency and dispersion
- Assessing normality
-
P-values and Statistical Tests
- Hypothesis testing fundamentals
- Parametric and non-parametric tests
- Permutation z-statistics
- Bootstraping t-statistics
-
Matching Analysis Techniques
- Propensity Score Weighting (PSW)
- Propensity Score Matching (PSM)
- Assessing balance and analyzing outcomes
-
Introduction to Large Language Models
- Using Gemini for data extraction
- BioMistral for disease prognosis prediction
-
Bonus: Clinical Databases
- Overview of NSQIP, SEER, and NIS
- Data extraction techniques
Course 2: Regression Analysis And Mathematical Modeling
-
Statistical Learning Framework
- Regression vs Classification
- Parametric, Non-Parametric, and Semi-Parametric Models
- Bias-Variance Tradeoff & Fitting (over fitting, under fitting)
- Curse of Dimensionality
-
Linear Regression
- Simple Linear Regression
- Multiple Linear Regression
- Assumptions and Diagnostics
- Model Evaluation: R-squared, Adjusted R-squared
- Loss Functions
- Confidence Intervals and Hypothesis Testing and Bootstraping
- The F-Statistic and Model Comparison
-
Logistic Regression
- The Logistic Function and Probability Transformation
- Odds Ratios and Interpretation
- Maximum Likelihood Estimation
- Model Evaluation: AIC and BIC
-
Regularization Techniques
- Lasso Regression (L1)
- Ridge Regression (L2)
- Elastic Net
-
Non-linearity in Regression
- Polynomial Regression
- Spline Functions
- Generalized Additive Models (GAMs)
-
Survival Analysis
- Kaplan-Meier Curves
- Cox Proportional Hazards Model
- IPD from KM Meta-analysis
-
Advanced Modeling Techniques
- Nomograms
- Fixed vs Random Effects Models
-
Model Evaluation and Diagnostics
- Diagnostic Test Analysis
- Model Calibration
-
Bonus: Meta-analysis
- Fixed and Random Effects Meta-analysis
- Forest Plots
- Publication Bias Assessment
Course 3: Machine Learning
-
Machine Learning Model Architectures
- Overview of model types and their applications
- Support Vector Machines, Decision Trees, and Ensemble Methods
- Hyperparameter tuning and optimization
-
Training, Testing, and Cross-validation
- Data splitting strategies
- Validation techniques and metrics
- Avoiding overfitting and underfitting
-
Feature Selection
- Importance of feature selection
- Techniques for selecting and engineering features
- Dimensionality reduction methods
-
Model Selection
- Choosing the right model for your problem
- Comparison of model performance
- Ensemble methods and stacking
-
Model Interpretation and Feature Importance
- Understanding model predictions
- Techniques for interpreting complex models
- Visualizing feature importance
-
Unsupervised Learning
- Principal Component Analysis (PCA)
- t-Distributed Stochastic Neighbor Embedding (t-SNE)
- Uniform Manifold Approximation and Projection (UMAP)
-
Bonus: Shiny Application and Model Deployment
- Creating interactive web applications with Shiny
- Deploying models for real-time use
- Best practices for maintaining deployed models
Course 4: Deep Learning and Artificial Intelligence
-
Deep Learning Basics: Gradient Descent Algorithm
- Introduction to gradient descent
- Types of gradient descent algorithms
- Optimizers and their roles
-
Introduction to Python and PyTorch
- Python basics for deep learning
- Setting up and using PyTorch
- Building and training neural networks with PyTorch
-
Neural Network Architectures
- Feedforward Neural Networks
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs) and Transformers
-
Pre-trained Models
- Using pre-trained models for transfer learning
- Fine-tuning models for specific tasks
- Popular pre-trained models and their applications
-
Large Language Models and Natural Language Processing
- Introduction to large language models
- Applications in NLP
- Fine-tuning and using language models
-
Medical Imaging and Computer Vision
- Basics of medical imaging techniques
- Computer vision models and applications
- Image pre-processing and augmentation
-
Neural Signal Decoding
- Techniques for decoding neural signals
- Applications in neuroscience and brain-computer interfaces
- Challenges and solutions in signal processing
-
Deep Learning Model Interpretation
- Understanding model decisions and predictions
- Techniques for interpreting deep learning models
- Visualization tools and methods
-
Bonus: Python Programming
- Advanced Python programming techniques
- Libraries and tools for deep learning
- Best practices for Python coding in AI
Course 5: EEG And Time Series Analysis for Medical Research
- Coming soon
Course 6: EEG Preprocessing
- Coming soon
Course 7: Medical Image Analysis
- Coming soon
Course 8: Medical Image Preprocessing
- Coming soon
Course 9: Medical Research Methodology
- Coming soon
Course 10: Scientific Writing in Medical Research
- Coming soon
Course 11: Study Protocol And Fund Proposal Writing And Registration
- Coming soon
Course 12: Meta-Analysis
- Coming soon
Course 13: Computational Neuroscience
- Coming soon
Course 14: Computational Biomedical Research
- Coming soon
Course 15: Bayesian Statistics
- Coming soon
Course 16: Deep Learning Embedding and Unsupervised Machine Learning Analysis for Unstructured Medical Data
- Coming soon
Course 17: Mathematical Basics for Medical Researchers
- Coming soon
Course 18: Medical Dynamic Systems
- Coming soon
Latest Research and Tools
Preprint: Novel Machine Learning Approach in Biomedical Research
Explore our latest preprint paper introducing a novel machine learning approach for biomedical research.
Read the PreprintCOVID-19 Machine Learning Application
Explore our Shiny application for COVID-19 data analysis using machine learning techniques.
COVID-19 ML ApplicationReady to Transform Your Research Skills?
Join us for an immersive learning experience that will revolutionize your approach to data analysis in research.
What Our Students Say
Share Your Experience
Connect with Dr. Ahmed Shaheen
For inquiries: ahmeds1999haheen@gmail.com
Follow for updates, ask questions, or get in touch!