16
Lessons
50h
Duration
English
Language
Share This Class:
OBJECTIVEs:
- In this course, you will learn how clinical data are generated and the format of this data. You will learn Statistics, SQL, Python, Machine Learning methods with clinical cases.
- Completing a clinical data science course can help students enhance their proficiency in analyzing complex clinical data sets. This includes learning advanced statistical techniques, data visualization, and machine learning algorithms.
- With a solid foundation in clinical data science, professionals can make more informed decisions based on evidence and data-driven insights. By completing these projects, students can develop their research skills and contribute new knowledge to the field.
Course features:
- Practical hands on
- Lab sessions
- Training by experienced faculty
PRE-REQUISITES:
- Basic statistics and knowledge of Excel
Learning Path
- Data Science with Python
- Data Types
- Variables And Other Basic Elements Control Statements
- Date and Time in Python
- Arrays and Strings
- Lists and Tuples
- Dictionaries
- Series
- DataFrame
- Panel
- Basic Functionality
- NumPy
- Pandas
- SciPy
- Visualization with Matplotlib
- Data Wrangling
- Web Scrapping
- Exploratory Data Analysis
- Feature
Engineering - Feature Selection
- Project Case Studies: Patient Demographic Analysis
- Healthcare Analysis
- Machine Learning with Python
- Function Application
- Reindexing Python
- Iteration
- Sorting
- Working with Text Data Options & Customization
- Indexing & Selecting Data Statistical Functions
- Window Functions
- Date Functionality
- Time delta
- Categorical Data
- Visualization Python Pandas – IO Tools
- Supervised and UnSupervised Learning
- Types of Supervised Algorithms
- Semi-supervised
- Reinforcement Train
- Test
- Validation Split
- Semi-supervised
- Reinforcement Train
- Test
- Validation Split
- R square
- Introduction to Scikit learn
- Training methodology
- Hands on linear regression
- Ridge Regression
- Logistics regression
- Precision Recall ROC curve
- F-Score
- Classification: Decision Tree
- Cross Validation Bias vs Variance
- Ensemble approach Bagging
- Boosting Random Forest Variable Importance
- K-Means clustering
- Hierarchical Clustering
- Recommender System and Association
- Project case studies: Classification of drugs, prediction of heart disease, Association of Ingredients in Drug, Liver Disease Prediction
- SQL