Brochure
Enquire
- Welcome to the course
- Claims Data Defined
- Why analyze healthcare claims data
- Who this course is for
Quick Facts
| particular | details | |||
|---|---|---|---|---|
|
Medium of instructions
English
|
Mode of learning
Self study
|
Mode of Delivery
Video and Text Based
|
Course and certificate fees
Fees information
₹ 499 ₹3,299
certificate availability
Yes
certificate providing authority
Udemy
The syllabus
Introduction
Theory of Healthcare systems
- The four functions of any healthcare system
- The three key actors in claims data
- Vertical integration of healthcare system functions
- Healthcare systems quiz
Healthcare provider payment systems
- Introduction to healthcare provider payment systems
- Fee-for-service
- Capitation
- Bundled payments
- Global budgets
- Summary of healthcare provider payment systems
- Healthcare provider payment systems
Theory of claims data
- The two core challenges for healthcare payers
- Fact tables and dimension tables
- Authorisation signals
- Theory of claims data quiz
Merging healthcare claims data
- Introduction to merging data
- Merging data from a data warehouse
- Merging an episode of care
Higher level categorization
- Introduction to Higher level categorization
- Consult the data dictionary
- Consult the Dimensions Tables
- (Re)Discover the underlying logic of codes
- Use existing hierarchies of (inter)national coding systems
- Ask a domain expert
- Summary of higher level categorization
- Higher level categorization quiz
Relevant resources for this course
- Get all relevant resources here
Basic exploration of Healthcare claims data
- Getting started with the practice dataset
- Basic filtering of data in Excel
- Introduction to pivot tables
- Working with a pivot table in Excel
- Selecting aggregations in a pivot table
- Grouping by date in a pivot table
- Using a pivot table to create and control a chart
- Introduction to vertical lookup
- Vertical look-up part 1: Exploring the look-up table in Excel
- Vertical look-up part 2: Applying the function
- Vertical look-up part 3: Filling down the results
- A note on filling down in Excel
- Vertical look-up part 4: Finalizing the dataset
- Benefit of introducing categories in claims data
Extract Transform and Load (ETL) from the Data warehouse using SQL
- Background information about the practice data warehouse
- Relational data schema
- Getting started with Google Big Query
- Alternative method to get to the Google Big Query Medicare dataset
- Introduction to SQL in Google Big Query interface
- Writing a simple SQL script to extract healthcare claims data
- Merging data using SQL
- Visualizing the data in Big Query
- Calculating the age of the patient at the time of knee replacement
- Confirming the correct code using the where clause and a regular expression
- Inspecting the compatibility between the tables
- Concatenate and cast data to allow compatibility
- Create a subquery
- Date difference function to calculate age
Absolute and relative comparisons
- Absolute and relative comparisons
- Using a 100% Stacked column chart for relative comparisons
- Using percentages for relative numbers
- Per capita calculations using distinct count
- Using distinct count for relative comparisons in Excel
Process mining with healthcare claims data
- Benefits of process mining with healthcare claims data
- Process mining tools
- Warning! Please read this word of caution before using Celonis Snap
- Getting started with Celonis Snap
- Configure the dataset for process mining
- Introduction to process mining with Celonis Snap part 1
- Introduction to process mining with Celonis Snap part 2
- Discover patient pathways using process mining (part 1)
- Discover patient pathways using process mining (part 2)
- Isolate a sub process by focussing on the sub process spider activity
- Introduction to specifying a sequence order
- Theory of sequence order when dealing with identical timestamps
- A note about specifying a sequence order
- Manipulating the raw data to specify a sequence order (part 1)
- Manipulating the raw data to specify a sequence order (part 2)
- A note about concatenation
- Confirm the correct sequence in a new process map
- Detect anomalies by comparing the processes of different providers
- Moving from process mining to statistics and machine learning
- Process mining quiz
- Process mining assignment
Proxy diagnosis and cohort analysis
- A note about proxy diagnosis and cohort analysis
- Proxy diagnosis
- Method for obtaining a proxy diagnosis
- Why use a subquery for proxy diagnosis
- Querying healthcare consumption of diabetics using a proxy diagnosis
- Identify insuline users (diabetics)
- Use identified diabetics to capture their full episode of care
- Capture the episode of care for patients undergoing a total knee replacement
Tidying healthcare claims data
- Introduction to tidy data
- Tidying healthcare claims data with Excel
- Converting the target variable to a binary field with Excel
- Getting started with Google Colab
- Tidying healthcare claims data with Python
- Converting the target variable to a binary field with Python
- A note about metric selection
Predicting Consumption Events
- Introduction to this section
- Preparing the data for logistic regression with Python
- Performing logistic regression
- Evaluating the performance with a confusion matrix
- Using a different categorization logic as input for logistic regression (part 1)
- Using a different categorization logic as input for logistic regression (part 2)
- Using a different categorization logic as input for logistic regression (part 3)
- Considerations for advanced machine learning practitioners
- Applying logistic regression with different metrics
Detecting Irregularities and Possible Fraud
- Introduction to this section
- Preparing the data for unsupervised machine learning
- Applying Principal Component Analysis
- A note about the Python code
- Applying K-means Clustering
- Calculating the distance from the nearest cluster
- Combining the machine learning outputs with the original claims data
- Exporting the machine learning output to a csv file
- Prepare for case by case analysis guided by the machine learning output
- Explore the different clusters (part 1)
- Interpret and rename the different clusters
- Compare the healthcare providers by patient clusters (part 1)
- Compare the healthcare providers by patient clusters (part 2)
- Example of absolute versus relative data
- Analyzing the distance from nearest cluster (part 1)
- Analyzing the distance from nearest cluster (part 2)
- Analyzing the distance from nearest cluster (part 3)
- Identifying red flags (part 1)
- Identifying red flags (part 2)
- Inspecting the red flag indivual patients on a case-by-case basis (part 1)
- Inspecting the red flag indivual patients on a case-by-case basis (part 2)
Performance Tracking (Compare defined targets with actual performance)
- Introduction to performance tracking with healthcare claims data
- Method part 1: Harmonizing the actual data with the targets
- Method part 2: Merging the two tables
- Method part 3: Feed the data into a business intelligence dashboard
- Trivia: Using compound/composite keys rather than multiple join keys
- Practice performance tracking with claims data
- Exploration of the business intelligence dashboard
- Visually inspecting the targets table
- Uploading the target table in the data warehouse
- Preparing the raw claims data for aggregation using SQL (part 1)
- Preparing the raw claims data for aggregation using SQL (part 2)
- Aggregating the raw claims data using SQL
- Creating a subquery containing the actual performance
- Joining the subquery with the uploaded table
- Calculating the percentage realized
- Saving the output as a new table in the data warehouse
- Feeding the output into the business intelligence dashboard
- Creating the business intelligence dashboard
Value based healthcare and health outcome indicators
- Introduction to value-based healthcare and health outcomes
- Introduction to types of health outcome indicators
- Patient reported health outcomes
- Biological health outcome indicators
- Adverse health episodes as outcome indicators
- Aftercare signals as a health outcome indicator
- Mortality as a health outcome indicator
- Merging different types of health outcome indicators
- Challenges with value-based healthcare and health outcomes
Conclusion
- Final Words
Articles
Popular Articles
prev
next
Similar Courses
Introduction to Health Technology Assessment
University of Glasgow, Glasgow via Futurelearn
Traditional Herbal Medicine in Supportive Cancer C...
Technion - Israel Institute of Technology via Coursera
prev
next
Courses of your Interest
C++ Foundation
PW Skills
Advanced CFD Meshing using ANSA
Skill Lync
Data Science Foundations to Core Bootcamp
Springboard
User Experience Design And Research
UM–Ann Arbor via Futurelearn
Fundamentals of Agile Project Management
UCI Irvine via Futurelearn
Artificial intelligence Design and Engineering wit...
CloudSwyft Global Systems, Inc via Futurelearn
prev
next
More Courses by Udemy
prev
next
