SlideShare une entreprise Scribd logo
1  sur  27
Télécharger pour lire hors ligne
Machine Learning in Healthcare – ML for the Rest of Us
Mohinder Dick
Senior Software
UPMC Enterprises
August 18, 2016
Email: dickm@upmc.edu
Twitter: @mobyware
|
Goal
Breakdown the perception that machine learning is too complex.
Address assumptions of what machine learning IS, and what it’s NOT.
Impart the basics of machine learning.
|
©2015 UPMC Enterprises : PROPRIETARY3
Machine Learning can be
perceived as Science Fiction
|
©2015 UPMC Enterprises : PROPRIETARY4
Machine Learning can be
perceived as Complex and Vast
in terms of research, terminology,
and technology
|
©2015 UPMC Enterprises : PROPRIETARY5
|
©2015 UPMC Enterprises : PROPRIETARY6
|
What we’ll accomplish today
• Machine Learning Basics in 8 Slides
• How to get started
• Let’s teach machines (Demo)
• Machine Learning in Healthcare
• Q & A
• References
©2015 UPMC Enterprises : PROPRIETARY7
|
©2015 UPMC Enterprises : PROPRIETARY8
Machine Learning in 8 Slides | Overview
Machine Learning
Supervised Unsupervised
Linear Non Linear Self Organizing
Maps
K Means
Clustering
Linear
Classification
Linear
Regression
NN Decision
Trees
Random
Forces
|
Machine Learning in 8 Slides | Key Terms
Term Description
Machine Learning Algorithms that automatically improve with data
Model Statistical representation of the algorithm’s experience
Supervised Learning Algorithms that improves using labeled examples
Linear Algorithm Predictions are proportional to the feature/input values
Feature Data point that affect the target you are trying to predict.
Target Variable Data point that you are trying to predict
Classification Predicting a categorical target variable
Regression Predicting a continuous target variable
©2015 UPMC Enterprises : PROPRIETARY9
|
Machine Learning in 8 Slides | Supervised Models
©2015 UPMC Enterprises : PROPRIETARY10
Unlabeled Data ML Model Predictions
• ML algorithms process “unseen” data to give predictions
• A model is a statistical representation of the algorithms experiences/training
How do you get a model?
|
Machine Learning in 8 Slides | Supervised Models
©2015 UPMC Enterprises : PROPRIETARY11
Labeled Data Algorithm Trained Model
• Supervised ML algorithms get their name because they learn with help
• You have to provide them experience in labeled examples
• The algorithm translates that data into a representation called a model
• It can be used later to make predictions
• The more data the better
|
Machine Learning in 8 Slides | Linear Models
©2015 UPMC Enterprises : PROPRIETARY12
Linear RegressionLinear Classification
Labeled Data Algorithm Trained Model
ERROR
|
Machine Learning in 8 Slides | Labels & Features
©2015 UPMC Enterprises : PROPRIETARY13
Labeled Data Algorithm Trained Model
Features
Label
+ Good/Bad
+ Real Lame
+ Great Score
• During training features with labels are given to the algorithm to generate the model
• Both features and labels can be categorical or continuous
• The type of your target affects the flavor of algorithm you chose
|
Machine Learning in 8 Slides | Labels & Features
©2015 UPMC Enterprises : PROPRIETARY14
Facial Recognition
Geometric features
called “Haars”
ML Model
Is this a face?
Non-linear model
Predictions
|
Machine Learning in 8 Slides | Recap
Term Description
Machine Learning Algorithms that automatically improve with data
Model Statistical representation of the algorithm’s experience
Supervised Learning Algorithms that improves using labeled examples
Linear Algorithm Predictions are proportional to the feature/input values
Feature Data point that affect the target you are trying to predict.
Target Variable Data point that you are trying to predict
Classification Predicting a categorical target variable
Regression Predicting a continuous target variable
©2015 UPMC Enterprises : PROPRIETARY15
|
How to get started | Training, Data, Tools & Approaches
©2015 UPMC Enterprises : PROPRIETARY16
Training
Books
MOOCs
Instructor Led
Data
Government Agencies
Vendors
Tools
Data Pipeline
Spark
Python
|
How to get started | Tool Details
©2015 UPMC Enterprises : PROPRIETARY17
Apache Spark
Cluster aware execution
MLLib for machine
learning
Python
Loosely typed language
Libraries – scikit, pandas
and numpy
R
Statistical language,
IDE ecosystem
|
How to get started | Tool Details
©2015 UPMC Enterprises : PROPRIETARY18
|
How to get started | Data Driven Approach
©2015 UPMC Enterprises : PROPRIETARY19
Problem
• Hospital bed capacity
Data
• Admitting Hospital
• Patient diagnosis and demographics
Analysis
• Data representation
• Data analysis
• Evaluation
Policy
• Increase capacity at hospitals with average patient age under 40
|
How to get started | Data Driven Approach
©2015 UPMC Enterprises : PROPRIETARY20
|
Machine Learning in Healthcare | Data Driven Approach
Project A
Uses ML and patient Records to predict negative patient outcomes
Project B
• Uses user-feedback to innovatively improve the ML Model
Project C
• Grass roots ML project that yielded insight into factors that affect the length of a patients stay.
©2015 UPMC Enterprises : PROPRIETARY21
|
Machine Learning in Healthcare | Project A
• Hospitals already have digital records, because of the ACA
• Can use public algorithm and software to make predictions
• Predictions save lives and/or money
©2015 UPMC Enterprises : PROPRIETARY22
ModelData in EMR:
Meds
Labs
Visit History
Notes
+ SEPSIS
+ Adverse Drug Reaction
+ % Readmission
Predictions
|
Machine Learning in Healthcare | Project B
• System uses proprietary model to make recommendations to clinicians
• Hospital decided to improve system by developing a way to incorporate feedback
• Hospital improves the model overtime without having to buy a new system
©2015 UPMC Enterprises : PROPRIETARY23
Health Records Model Predictions
ML
Recommendations
User
Feedback
|
Machine Learning in Healthcare | Project C
• Interested individuals built a model using visit data
• Predictions were just OKAY
• BUT inspecting the model allowed the team to learn new factors that were unknown about
the different factors affected the clinical outcomes
©2015 UPMC Enterprises : PROPRIETARY24
Visitor Info Model
+ Length of Stay (LOS)
Predictions
Insight about LOS
|
Let’s teach machines
©2015 UPMC Enterprises : PROPRIETARY25
https://github.com/MobyWare/ml-abstractions-intro-python
|
References
Resource Location
Presentation link [search slideshare]
Demo code (direct) http://mybinder.org/repo/mobyware/ml-abstractions-intro-python
Demo code https://github.com/MobyWare/ml-abstractions-intro-python
EDX Course list (see data) https://www.edx.org/course
Coursera Course list https://www.coursera.org/courses/?domains=data-science
Spark Download Page http://spark.apache.org/downloads.html
Anaconda Python Install Page http://docs.continuum.io/anaconda/install
R install page https://cran.r-project.org/
R Studio install page https://www.rstudio.com/products/rstudio/download/
Ebay Tech Blog on Spark http://www.ebaytechblog.com/2014/05/28/using-spark-to-ignite-data-analytics/
©2015 UPMC Enterprises : PROPRIETARY26
|
Questions

Contenu connexe

Tendances

Inconsistent Outliers
Inconsistent OutliersInconsistent Outliers
Inconsistent OutliersNeil Rubens
 
Cts Overview 070109
Cts   Overview 070109Cts   Overview 070109
Cts Overview 070109Paula Gwyn
 
Hypothesis driven development - Alexander Bertholds, APPRL
Hypothesis driven development - Alexander Bertholds, APPRLHypothesis driven development - Alexander Bertholds, APPRL
Hypothesis driven development - Alexander Bertholds, APPRLUXDXConf
 
2018 ehr challenges
2018 ehr challenges2018 ehr challenges
2018 ehr challengesSapan Patel
 
Build your library a six sigma way
Build your library a six sigma wayBuild your library a six sigma way
Build your library a six sigma wayVrushali Basarkar
 
Wellbeing analytics code of practice
Wellbeing analytics code of practiceWellbeing analytics code of practice
Wellbeing analytics code of practiceJisc
 
Hadoop infrastructure for education
Hadoop infrastructure for educationHadoop infrastructure for education
Hadoop infrastructure for educationDarko Marjanovic
 
Big Data in Education
Big Data in EducationBig Data in Education
Big Data in EducationAlfred Essa
 
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...Edureka!
 
Online Educa Berlin conference: Big Data in Education - theory and practice
Online Educa Berlin conference: Big Data in Education - theory and practiceOnline Educa Berlin conference: Big Data in Education - theory and practice
Online Educa Berlin conference: Big Data in Education - theory and practiceMike Moore
 
Status Quo is No Longer an Option
Status Quo is No Longer an OptionStatus Quo is No Longer an Option
Status Quo is No Longer an OptionIFAH
 
ILRI Research Methods Group (RMG): Unified research computing platform
ILRI Research Methods Group (RMG): Unified research computing platformILRI Research Methods Group (RMG): Unified research computing platform
ILRI Research Methods Group (RMG): Unified research computing platformILRI
 

Tendances (20)

Inconsistent Outliers
Inconsistent OutliersInconsistent Outliers
Inconsistent Outliers
 
Machine Learning and Multi Drug Resistant(MDR) Infections case study
Machine Learning and Multi Drug Resistant(MDR) Infections case studyMachine Learning and Multi Drug Resistant(MDR) Infections case study
Machine Learning and Multi Drug Resistant(MDR) Infections case study
 
Machine Learning in ICU mortality prediction
Machine Learning in ICU mortality predictionMachine Learning in ICU mortality prediction
Machine Learning in ICU mortality prediction
 
Machine Learning For Stock Broking
Machine Learning For Stock BrokingMachine Learning For Stock Broking
Machine Learning For Stock Broking
 
Cts Overview 070109
Cts   Overview 070109Cts   Overview 070109
Cts Overview 070109
 
About Quahog Life Sciences
About Quahog Life SciencesAbout Quahog Life Sciences
About Quahog Life Sciences
 
Hypothesis driven development - Alexander Bertholds, APPRL
Hypothesis driven development - Alexander Bertholds, APPRLHypothesis driven development - Alexander Bertholds, APPRL
Hypothesis driven development - Alexander Bertholds, APPRL
 
2018 ehr challenges
2018 ehr challenges2018 ehr challenges
2018 ehr challenges
 
Build your library a six sigma way
Build your library a six sigma wayBuild your library a six sigma way
Build your library a six sigma way
 
Wellbeing analytics code of practice
Wellbeing analytics code of practiceWellbeing analytics code of practice
Wellbeing analytics code of practice
 
Data analytics course
Data analytics courseData analytics course
Data analytics course
 
Image Analytics for Retail
Image Analytics for RetailImage Analytics for Retail
Image Analytics for Retail
 
Hadoop infrastructure for education
Hadoop infrastructure for educationHadoop infrastructure for education
Hadoop infrastructure for education
 
Image Analytics In Healthcare
Image Analytics In HealthcareImage Analytics In Healthcare
Image Analytics In Healthcare
 
Big Data in Education
Big Data in EducationBig Data in Education
Big Data in Education
 
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...
Data Analytics For Beginners | Introduction To Data Analytics | Data Analytic...
 
Data Science for Retail Broking
Data Science for Retail BrokingData Science for Retail Broking
Data Science for Retail Broking
 
Online Educa Berlin conference: Big Data in Education - theory and practice
Online Educa Berlin conference: Big Data in Education - theory and practiceOnline Educa Berlin conference: Big Data in Education - theory and practice
Online Educa Berlin conference: Big Data in Education - theory and practice
 
Status Quo is No Longer an Option
Status Quo is No Longer an OptionStatus Quo is No Longer an Option
Status Quo is No Longer an Option
 
ILRI Research Methods Group (RMG): Unified research computing platform
ILRI Research Methods Group (RMG): Unified research computing platformILRI Research Methods Group (RMG): Unified research computing platform
ILRI Research Methods Group (RMG): Unified research computing platform
 

En vedette

Hands-on Machine Learning Using Healthcare
Hands-on Machine Learning Using HealthcareHands-on Machine Learning Using Healthcare
Hands-on Machine Learning Using HealthcareHealth Catalyst
 
Predicting the Future of Predictive Analytics in Healthcare
Predicting the Future of Predictive Analytics in HealthcarePredicting the Future of Predictive Analytics in Healthcare
Predicting the Future of Predictive Analytics in HealthcareDale Sanders
 
Machine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionMachine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionPierre Gutierrez
 
New Ways for Predictive Analytics and Machine Learning to Advance Population ...
New Ways for Predictive Analytics and Machine Learning to Advance Population ...New Ways for Predictive Analytics and Machine Learning to Advance Population ...
New Ways for Predictive Analytics and Machine Learning to Advance Population ...Edifecs Inc
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLPaco Nathan
 
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...Health Catalyst
 
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...Amazon Web Services
 
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...Health Catalyst
 
4 Essential Lessons for Adopting Predictive Analytics in Healthcare
4 Essential Lessons for Adopting Predictive Analytics in Healthcare4 Essential Lessons for Adopting Predictive Analytics in Healthcare
4 Essential Lessons for Adopting Predictive Analytics in HealthcareHealth Catalyst
 
Deploying Predictive Analytics in Healthcare
Deploying Predictive Analytics in HealthcareDeploying Predictive Analytics in Healthcare
Deploying Predictive Analytics in HealthcareHealth Catalyst
 
Data Mining in Healthcare: How Health Systems Can Improve Quality and Reduce...
Data Mining in Healthcare:  How Health Systems Can Improve Quality and Reduce...Data Mining in Healthcare:  How Health Systems Can Improve Quality and Reduce...
Data Mining in Healthcare: How Health Systems Can Improve Quality and Reduce...Health Catalyst
 
Transform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningTransform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningSri Ambati
 
4 Best Practices for Analyzing Healthcare Data
4 Best Practices for Analyzing Healthcare Data4 Best Practices for Analyzing Healthcare Data
4 Best Practices for Analyzing Healthcare DataHealth Catalyst
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningRahul Jain
 

En vedette (16)

Hands-on Machine Learning Using Healthcare
Hands-on Machine Learning Using HealthcareHands-on Machine Learning Using Healthcare
Hands-on Machine Learning Using Healthcare
 
Open Machine Learning
Open Machine LearningOpen Machine Learning
Open Machine Learning
 
Predicting the Future of Predictive Analytics in Healthcare
Predicting the Future of Predictive Analytics in HealthcarePredicting the Future of Predictive Analytics in Healthcare
Predicting the Future of Predictive Analytics in Healthcare
 
Machine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionMachine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical prevention
 
New Ways for Predictive Analytics and Machine Learning to Advance Population ...
New Ways for Predictive Analytics and Machine Learning to Advance Population ...New Ways for Predictive Analytics and Machine Learning to Advance Population ...
New Ways for Predictive Analytics and Machine Learning to Advance Population ...
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAML
 
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...
How To Avoid The 3 Most Common Healthcare Analytics Pitfalls And Related Inef...
 
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...
AWS re:Invent 2016| HLC301 | Data Science and Healthcare: Running Large Scale...
 
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...
The MD Anderson / IBM Watson Announcement: What does it mean for machine lear...
 
4 Essential Lessons for Adopting Predictive Analytics in Healthcare
4 Essential Lessons for Adopting Predictive Analytics in Healthcare4 Essential Lessons for Adopting Predictive Analytics in Healthcare
4 Essential Lessons for Adopting Predictive Analytics in Healthcare
 
Deploying Predictive Analytics in Healthcare
Deploying Predictive Analytics in HealthcareDeploying Predictive Analytics in Healthcare
Deploying Predictive Analytics in Healthcare
 
Data Mining in Healthcare: How Health Systems Can Improve Quality and Reduce...
Data Mining in Healthcare:  How Health Systems Can Improve Quality and Reduce...Data Mining in Healthcare:  How Health Systems Can Improve Quality and Reduce...
Data Mining in Healthcare: How Health Systems Can Improve Quality and Reduce...
 
Transform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningTransform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine Learning
 
4 Best Practices for Analyzing Healthcare Data
4 Best Practices for Analyzing Healthcare Data4 Best Practices for Analyzing Healthcare Data
4 Best Practices for Analyzing Healthcare Data
 
Machine Learning for Dummies
Machine Learning for DummiesMachine Learning for Dummies
Machine Learning for Dummies
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 

Similaire à Abstractions Conference 2016 - Machine Learning in Healthcare – ML for the Rest of Us

Bridging the AI Gap: Building Stakeholder Support
Bridging the AI Gap: Building Stakeholder SupportBridging the AI Gap: Building Stakeholder Support
Bridging the AI Gap: Building Stakeholder SupportPeter Skomoroch
 
DutchMLSchool. ML for Energy Trading and Automotive Sector
DutchMLSchool. ML for Energy Trading and Automotive SectorDutchMLSchool. ML for Energy Trading and Automotive Sector
DutchMLSchool. ML for Energy Trading and Automotive SectorBigML, Inc
 
Design Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsDesign Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsInductive Automation
 
L1 Introduction DS.pptx
L1 Introduction DS.pptxL1 Introduction DS.pptx
L1 Introduction DS.pptxShambhavi Vats
 
Industry and academic partnerships july 2015 final
Industry and academic partnerships july 2015 finalIndustry and academic partnerships july 2015 final
Industry and academic partnerships july 2015 finalSteven Miller
 
How to Use Machine Learning in Clinical Research Right Now
How to Use Machine Learning in Clinical Research Right NowHow to Use Machine Learning in Clinical Research Right Now
How to Use Machine Learning in Clinical Research Right NowMMS Holdings Inc.
 
How to Use Machine Learning in Clinical Research Right Now_.pptx
How to Use Machine Learning in Clinical Research Right Now_.pptxHow to Use Machine Learning in Clinical Research Right Now_.pptx
How to Use Machine Learning in Clinical Research Right Now_.pptxMMS Holdings
 
Design Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsDesign Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsInductive Automation
 
Machine Learning in Customer Analytics
Machine Learning in Customer AnalyticsMachine Learning in Customer Analytics
Machine Learning in Customer AnalyticsCourse5i
 
Build Intelligence System with AI. Antimo Musone, Ernst & Young
Build Intelligence System with AI. Antimo Musone, Ernst & YoungBuild Intelligence System with AI. Antimo Musone, Ernst & Young
Build Intelligence System with AI. Antimo Musone, Ernst & YoungData Driven Innovation
 
Machine Learning for Finance Master Class
Machine Learning for Finance Master Class Machine Learning for Finance Master Class
Machine Learning for Finance Master Class QuantUniversity
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...Value Amplify Consulting
 
Transformative Corporate Training with Simulations
Transformative Corporate Training with Simulations Transformative Corporate Training with Simulations
Transformative Corporate Training with Simulations The Blockchain Academy
 
Bryant Nielson - Transformative Corporate Training with Simulations
Bryant Nielson - Transformative Corporate Training with SimulationsBryant Nielson - Transformative Corporate Training with Simulations
Bryant Nielson - Transformative Corporate Training with SimulationsSeriousGamesAssoc
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Succeed in AI projects
Succeed in AI projectsSucceed in AI projects
Succeed in AI projectsSubhendu Dey
 
Practical model management in the age of Data science and ML
Practical model management in the age of Data science and MLPractical model management in the age of Data science and ML
Practical model management in the age of Data science and MLQuantUniversity
 
The Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingThe Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingDecision Management Solutions
 
SIMUL8 Workshop - Process Improvement Innovation: Lean and Simulation
SIMUL8 Workshop - Process Improvement Innovation: Lean and SimulationSIMUL8 Workshop - Process Improvement Innovation: Lean and Simulation
SIMUL8 Workshop - Process Improvement Innovation: Lean and SimulationSIMUL8 Corporation
 
How Will Your ML Project Fail
How Will Your ML Project FailHow Will Your ML Project Fail
How Will Your ML Project FailElena Samuylova
 

Similaire à Abstractions Conference 2016 - Machine Learning in Healthcare – ML for the Rest of Us (20)

Bridging the AI Gap: Building Stakeholder Support
Bridging the AI Gap: Building Stakeholder SupportBridging the AI Gap: Building Stakeholder Support
Bridging the AI Gap: Building Stakeholder Support
 
DutchMLSchool. ML for Energy Trading and Automotive Sector
DutchMLSchool. ML for Energy Trading and Automotive SectorDutchMLSchool. ML for Energy Trading and Automotive Sector
DutchMLSchool. ML for Energy Trading and Automotive Sector
 
Design Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsDesign Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning Basics
 
L1 Introduction DS.pptx
L1 Introduction DS.pptxL1 Introduction DS.pptx
L1 Introduction DS.pptx
 
Industry and academic partnerships july 2015 final
Industry and academic partnerships july 2015 finalIndustry and academic partnerships july 2015 final
Industry and academic partnerships july 2015 final
 
How to Use Machine Learning in Clinical Research Right Now
How to Use Machine Learning in Clinical Research Right NowHow to Use Machine Learning in Clinical Research Right Now
How to Use Machine Learning in Clinical Research Right Now
 
How to Use Machine Learning in Clinical Research Right Now_.pptx
How to Use Machine Learning in Clinical Research Right Now_.pptxHow to Use Machine Learning in Clinical Research Right Now_.pptx
How to Use Machine Learning in Clinical Research Right Now_.pptx
 
Design Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning BasicsDesign Like a Pro: Machine Learning Basics
Design Like a Pro: Machine Learning Basics
 
Machine Learning in Customer Analytics
Machine Learning in Customer AnalyticsMachine Learning in Customer Analytics
Machine Learning in Customer Analytics
 
Build Intelligence System with AI. Antimo Musone, Ernst & Young
Build Intelligence System with AI. Antimo Musone, Ernst & YoungBuild Intelligence System with AI. Antimo Musone, Ernst & Young
Build Intelligence System with AI. Antimo Musone, Ernst & Young
 
Machine Learning for Finance Master Class
Machine Learning for Finance Master Class Machine Learning for Finance Master Class
Machine Learning for Finance Master Class
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
 
Transformative Corporate Training with Simulations
Transformative Corporate Training with Simulations Transformative Corporate Training with Simulations
Transformative Corporate Training with Simulations
 
Bryant Nielson - Transformative Corporate Training with Simulations
Bryant Nielson - Transformative Corporate Training with SimulationsBryant Nielson - Transformative Corporate Training with Simulations
Bryant Nielson - Transformative Corporate Training with Simulations
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Succeed in AI projects
Succeed in AI projectsSucceed in AI projects
Succeed in AI projects
 
Practical model management in the age of Data science and ML
Practical model management in the age of Data science and MLPractical model management in the age of Data science and ML
Practical model management in the age of Data science and ML
 
The Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision ModelingThe Value of Predictive Analytics and Decision Modeling
The Value of Predictive Analytics and Decision Modeling
 
SIMUL8 Workshop - Process Improvement Innovation: Lean and Simulation
SIMUL8 Workshop - Process Improvement Innovation: Lean and SimulationSIMUL8 Workshop - Process Improvement Innovation: Lean and Simulation
SIMUL8 Workshop - Process Improvement Innovation: Lean and Simulation
 
How Will Your ML Project Fail
How Will Your ML Project FailHow Will Your ML Project Fail
How Will Your ML Project Fail
 

Dernier

Mapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxMapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxVenkatasubramani13
 
5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best PracticesDataArchiva
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introductionsanjaymuralee1
 
Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Vladislav Solodkiy
 
SFBA Splunk Usergroup meeting March 13, 2024
SFBA Splunk Usergroup meeting March 13, 2024SFBA Splunk Usergroup meeting March 13, 2024
SFBA Splunk Usergroup meeting March 13, 2024Becky Burwell
 
CI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionCI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionajayrajaganeshkayala
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Guido X Jansen
 
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxTINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxDwiAyuSitiHartinah
 
Master's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationMaster's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationGiorgio Carbone
 
AI for Sustainable Development Goals (SDGs)
AI for Sustainable Development Goals (SDGs)AI for Sustainable Development Goals (SDGs)
AI for Sustainable Development Goals (SDGs)Data & Analytics Magazin
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityAggregage
 
MEASURES OF DISPERSION I BSc Botany .ppt
MEASURES OF DISPERSION I BSc Botany .pptMEASURES OF DISPERSION I BSc Botany .ppt
MEASURES OF DISPERSION I BSc Botany .pptaigil2
 
YourView Panel Book.pptx YourView Panel Book.
YourView Panel Book.pptx YourView Panel Book.YourView Panel Book.pptx YourView Panel Book.
YourView Panel Book.pptx YourView Panel Book.JasonViviers2
 
Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...PrithaVashisht1
 
The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerPavel Šabatka
 
ChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics InfrastructureChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics Infrastructuresonikadigital1
 
How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?sonikadigital1
 

Dernier (17)

Mapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxMapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptx
 
5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introduction
 
Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023
 
SFBA Splunk Usergroup meeting March 13, 2024
SFBA Splunk Usergroup meeting March 13, 2024SFBA Splunk Usergroup meeting March 13, 2024
SFBA Splunk Usergroup meeting March 13, 2024
 
CI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionCI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual intervention
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
 
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxTINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
 
Master's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationMaster's Thesis - Data Science - Presentation
Master's Thesis - Data Science - Presentation
 
AI for Sustainable Development Goals (SDGs)
AI for Sustainable Development Goals (SDGs)AI for Sustainable Development Goals (SDGs)
AI for Sustainable Development Goals (SDGs)
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
 
MEASURES OF DISPERSION I BSc Botany .ppt
MEASURES OF DISPERSION I BSc Botany .pptMEASURES OF DISPERSION I BSc Botany .ppt
MEASURES OF DISPERSION I BSc Botany .ppt
 
YourView Panel Book.pptx YourView Panel Book.
YourView Panel Book.pptx YourView Panel Book.YourView Panel Book.pptx YourView Panel Book.
YourView Panel Book.pptx YourView Panel Book.
 
Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...
 
The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayer
 
ChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics InfrastructureChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics Infrastructure
 
How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?
 

Abstractions Conference 2016 - Machine Learning in Healthcare – ML for the Rest of Us

  • 1. Machine Learning in Healthcare – ML for the Rest of Us Mohinder Dick Senior Software UPMC Enterprises August 18, 2016 Email: dickm@upmc.edu Twitter: @mobyware
  • 2. | Goal Breakdown the perception that machine learning is too complex. Address assumptions of what machine learning IS, and what it’s NOT. Impart the basics of machine learning.
  • 3. | ©2015 UPMC Enterprises : PROPRIETARY3 Machine Learning can be perceived as Science Fiction
  • 4. | ©2015 UPMC Enterprises : PROPRIETARY4 Machine Learning can be perceived as Complex and Vast in terms of research, terminology, and technology
  • 5. | ©2015 UPMC Enterprises : PROPRIETARY5
  • 6. | ©2015 UPMC Enterprises : PROPRIETARY6
  • 7. | What we’ll accomplish today • Machine Learning Basics in 8 Slides • How to get started • Let’s teach machines (Demo) • Machine Learning in Healthcare • Q & A • References ©2015 UPMC Enterprises : PROPRIETARY7
  • 8. | ©2015 UPMC Enterprises : PROPRIETARY8 Machine Learning in 8 Slides | Overview Machine Learning Supervised Unsupervised Linear Non Linear Self Organizing Maps K Means Clustering Linear Classification Linear Regression NN Decision Trees Random Forces
  • 9. | Machine Learning in 8 Slides | Key Terms Term Description Machine Learning Algorithms that automatically improve with data Model Statistical representation of the algorithm’s experience Supervised Learning Algorithms that improves using labeled examples Linear Algorithm Predictions are proportional to the feature/input values Feature Data point that affect the target you are trying to predict. Target Variable Data point that you are trying to predict Classification Predicting a categorical target variable Regression Predicting a continuous target variable ©2015 UPMC Enterprises : PROPRIETARY9
  • 10. | Machine Learning in 8 Slides | Supervised Models ©2015 UPMC Enterprises : PROPRIETARY10 Unlabeled Data ML Model Predictions • ML algorithms process “unseen” data to give predictions • A model is a statistical representation of the algorithms experiences/training How do you get a model?
  • 11. | Machine Learning in 8 Slides | Supervised Models ©2015 UPMC Enterprises : PROPRIETARY11 Labeled Data Algorithm Trained Model • Supervised ML algorithms get their name because they learn with help • You have to provide them experience in labeled examples • The algorithm translates that data into a representation called a model • It can be used later to make predictions • The more data the better
  • 12. | Machine Learning in 8 Slides | Linear Models ©2015 UPMC Enterprises : PROPRIETARY12 Linear RegressionLinear Classification Labeled Data Algorithm Trained Model ERROR
  • 13. | Machine Learning in 8 Slides | Labels & Features ©2015 UPMC Enterprises : PROPRIETARY13 Labeled Data Algorithm Trained Model Features Label + Good/Bad + Real Lame + Great Score • During training features with labels are given to the algorithm to generate the model • Both features and labels can be categorical or continuous • The type of your target affects the flavor of algorithm you chose
  • 14. | Machine Learning in 8 Slides | Labels & Features ©2015 UPMC Enterprises : PROPRIETARY14 Facial Recognition Geometric features called “Haars” ML Model Is this a face? Non-linear model Predictions
  • 15. | Machine Learning in 8 Slides | Recap Term Description Machine Learning Algorithms that automatically improve with data Model Statistical representation of the algorithm’s experience Supervised Learning Algorithms that improves using labeled examples Linear Algorithm Predictions are proportional to the feature/input values Feature Data point that affect the target you are trying to predict. Target Variable Data point that you are trying to predict Classification Predicting a categorical target variable Regression Predicting a continuous target variable ©2015 UPMC Enterprises : PROPRIETARY15
  • 16. | How to get started | Training, Data, Tools & Approaches ©2015 UPMC Enterprises : PROPRIETARY16 Training Books MOOCs Instructor Led Data Government Agencies Vendors Tools Data Pipeline Spark Python
  • 17. | How to get started | Tool Details ©2015 UPMC Enterprises : PROPRIETARY17 Apache Spark Cluster aware execution MLLib for machine learning Python Loosely typed language Libraries – scikit, pandas and numpy R Statistical language, IDE ecosystem
  • 18. | How to get started | Tool Details ©2015 UPMC Enterprises : PROPRIETARY18
  • 19. | How to get started | Data Driven Approach ©2015 UPMC Enterprises : PROPRIETARY19 Problem • Hospital bed capacity Data • Admitting Hospital • Patient diagnosis and demographics Analysis • Data representation • Data analysis • Evaluation Policy • Increase capacity at hospitals with average patient age under 40
  • 20. | How to get started | Data Driven Approach ©2015 UPMC Enterprises : PROPRIETARY20
  • 21. | Machine Learning in Healthcare | Data Driven Approach Project A Uses ML and patient Records to predict negative patient outcomes Project B • Uses user-feedback to innovatively improve the ML Model Project C • Grass roots ML project that yielded insight into factors that affect the length of a patients stay. ©2015 UPMC Enterprises : PROPRIETARY21
  • 22. | Machine Learning in Healthcare | Project A • Hospitals already have digital records, because of the ACA • Can use public algorithm and software to make predictions • Predictions save lives and/or money ©2015 UPMC Enterprises : PROPRIETARY22 ModelData in EMR: Meds Labs Visit History Notes + SEPSIS + Adverse Drug Reaction + % Readmission Predictions
  • 23. | Machine Learning in Healthcare | Project B • System uses proprietary model to make recommendations to clinicians • Hospital decided to improve system by developing a way to incorporate feedback • Hospital improves the model overtime without having to buy a new system ©2015 UPMC Enterprises : PROPRIETARY23 Health Records Model Predictions ML Recommendations User Feedback
  • 24. | Machine Learning in Healthcare | Project C • Interested individuals built a model using visit data • Predictions were just OKAY • BUT inspecting the model allowed the team to learn new factors that were unknown about the different factors affected the clinical outcomes ©2015 UPMC Enterprises : PROPRIETARY24 Visitor Info Model + Length of Stay (LOS) Predictions Insight about LOS
  • 25. | Let’s teach machines ©2015 UPMC Enterprises : PROPRIETARY25 https://github.com/MobyWare/ml-abstractions-intro-python
  • 26. | References Resource Location Presentation link [search slideshare] Demo code (direct) http://mybinder.org/repo/mobyware/ml-abstractions-intro-python Demo code https://github.com/MobyWare/ml-abstractions-intro-python EDX Course list (see data) https://www.edx.org/course Coursera Course list https://www.coursera.org/courses/?domains=data-science Spark Download Page http://spark.apache.org/downloads.html Anaconda Python Install Page http://docs.continuum.io/anaconda/install R install page https://cran.r-project.org/ R Studio install page https://www.rstudio.com/products/rstudio/download/ Ebay Tech Blog on Spark http://www.ebaytechblog.com/2014/05/28/using-spark-to-ignite-data-analytics/ ©2015 UPMC Enterprises : PROPRIETARY26

Notes de l'éditeur

  1. Goal is to provide a soft landing for a topic that can be the stuff of science fiction Re demonstrate, illustration in healthcare If time permits we will do so with a quick demo.
  2. Machine learning is complex and vast: Research Terms Technologies
  3. Consider two visions of ML, one is way to complex. This is good to aspire to: ANN Threat modelling Advance image recognition Arrow anecdote
  4. Vision 2: Approachable for most of us here. Use simpler types of machine learning to serve clinical context: Facial recognition: OpenCV to find face. Glasses Estimate length of stay in hospital Determine which drugs are likely to be prescribed
  5. Both features and targets can be categorical or continuous.
  6. Prediction is the value of the target variable the machine comes up with. Label is the value you give it during training.
  7. Linear models use weights for each feature. Classification is based on regions. Evaluate by percentage of TP, FP, TN, FN Linear regression is based on the delta in the predicted value. Use measures like the RMSE
  8. Haars are rectangular regions Models for facial detection are typically non-linear. Trees or Net (neural nets) Haar cascades – Viola & Jones (real-time image detection)
  9. Both features and targets can be categorical or continuous.
  10. All free and/or open source
  11. eBay’s tech blog. Spark application used to cluster sellers on eBay and store in HDFS