Machine Learning in Healthcare (no coding required!)
3.8 (2 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
24 students enrolled

Machine Learning in Healthcare (no coding required!)

Learn how to apply machine learning techniques in healthcare
New
3.8 (2 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
24 students enrolled
Created by Eddie Jay
Last updated 5/2020
English
English [Auto-generated]
Current price: $62.99 Original price: $89.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 2.5 hours on-demand video
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Assignments
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Health data 101
  • How to plan the analysis and to get buy in
  • What you should know about health data for predictive modeling purposes
  • What predictive model features are, and how to create them
  • Statistical model primer
  • How to build predictive models: step by step guide: using case study
  • How to assess model performance
Requirements
  • Basic knowledge of health care data
  • Knowledge of basic statistical concepts
Description

This course will teach you how to work with health data, using machine learning models to find actionable insights.

Through a step-by-step guided case study, you will learn practical skills that you can apply immediately!


We will use a case study: Opioid Abuse Prediction for a clinic


Topics we will cover:

  1. Health Data (sources, types, features, error handling)

  2. Logistics of machine learning

  3. What predictive model features are, and how to create them

  4. A statistical primer, highlighting key machine learning models and concepts

  5. Build a decision tree, logistic regression and random forest through

    1. Opioid abuse prediction case study

    2. KNIME (a free machine learning software, no coding required!)

  6. Assess model performance

  7. Output presentation and implementation

Who this course is for:
  • Beginner to Intermediate analysts of health data
  • Public health/Epidemiology/Bioinformatics analysts
  • Actuarial/Statistical analysts
Course content
Expand all 39 lectures 02:37:31
+ Introduction
2 lectures 02:49

To make what you learn here concrete and actionable, we will use a case study - opioid dependency prediction at a clinic.

Please download the excel spreadsheet that contains elements needed for this case study.

Preview 01:17
+ Health data 101
13 lectures 39:50
Electronic health records
02:19
Research reports
02:57
Public health
02:17
Wearables
02:40

What are strengths of insurance claims?

Insurance Claims
1 question
What are strengths of EHR data?
1 question
Key takeaways from sources of health data session
1 question
Structured data
03:11
Data structure
1 question
Unstructured data
02:15
Features of data - Hierarchical Drugs
02:36
Features of data - Hierarchical Procedures
03:51
Features of data - Hierarchical LOINCs and other
02:23
Disease Etiology, Chronology, Supply vs Demand
04:33
Why understanding of medicine and medical practices enhance analyses?
1 question
Errors and error handling
04:22
Correcting errors in health data
1 question
+ Logistics of machine learning
4 lectures 14:32

7 steps to predictive modeling/Machine learning

Steps to Predictive Modeling
01:06

A solid analytic plan ensures you ask the important questions upfront and keeps you on the right track, improving the efficiency and effectiveness of your analysis.

Planning the analysis
03:57

Your ability to convince others to work with you, on a project, is a key skill as an analyst. Remember, without end users, what you analyze is theoretical, pointless. Market yourself and your projects like a pro!

Getting Buy in for the analysis
07:31
Data use considerations
01:58
Why plan?
1 question
Why do we need buy in for the project?
1 question
+ Data preparation and Feature engineering
4 lectures 26:27
Initial exploration of the data
02:07
Data preparation
03:44
Feature engineering
12:49
On features
1 question

Going from raw data to training data set with machine learning features.

From raw data to training dataset
07:47
+ Statistical Primer
7 lectures 28:41
Logistic regression - intro
04:29
Logistic regression Pros and Cons
05:46
Bias Variance trade off
05:38
Bias Variance
1 question
Decision tree
03:20
When to use which?
1 question
Random forest
04:20
Neural net
04:10
+ Machine learning in Healthcare - case study
2 lectures 18:08
Intro to KNIME
05:44
Model training in KNIME
12:24
Try to build the decision tree and logistic regression models in KNIME.
Build your own
1 question
+ Model assessment and Output
7 lectures 21:20
Sensitivity vs Specificity
03:28
On sensitivity and specificity
1 question
Cross validation in KNIME
04:38
Sensitivity/Scenario testing
04:40
Presenting the results
04:04
Implementation and Future improvements
02:09
Practice practice practice!
01:04