[PDF] [PDF] Introduction to Machine Learning & Its Application in Healthcare

[PDF] Where Artificial Intelligence meets Predictive Analytics - Michigan

Understand the impact AI and Predictive Medicine can have on healthcare • Understand that present systems cannot manage the variables of data that must be 

[PDF] Healthcare AI

Exponential growth in data to analyze using AI in many fields In healthcare: – Medical Imaging – Electronic health records – Genomic data – Patient 

[PDF] Machine Learning for Healthcare 6S897, HSTS53 Lecture 1: What

Brief history of AI and ML in healthcare 2 Examples of machine learning in healthcare 4 Table 1 9 25 Neural Network Studies in Medical Decision Making*

[PDF] Role of artificial intelligence in healthcare ppt - Weebly

Role of artificial intelligence in healthcare ppt Medical imaging: Machine learning algorithms can process unimaginable amounts of information in a blink of an 

[PDF] Rise of the Intelligent Machines in Healthcare - HIMSS Global

29 fév 2016 · networks, and machine learning, and the types of problems they can address Source: http://www slideshare net/0xdata/paypal-fraud-detection-with-deep- learning-in-h2o- Medical speech recognition for specialties – at the

[PDF] Introduction to Machine Learning & Its Application in Healthcare

3 oct 2018 · Healthcare Lecture 4 A branch of artificial intelligence, concerned with the design and development of Machine Learning: Field of study that gives Identify patient subgroups for personalized and precision medicine

[PDF] Machine Learning for Big Data in Healthcare - NYU

Then we present IoT-assisted healthcare monitoring systems In data analytics for medical applications, we focus on cloud-based detection of chronic diseases

[PDF] Artificial Intelligence in Health Care - Stat News

Investment in AI health startups Page 6 Page 7 ○ mainly used in the back ○ Clinical use is increasing ○ Drug makers are using AI 

[PDF] Presentation I-Com

Source: PWC, Sherlock in Health How artificial intelligence may improve quality Training AI applications in healthcare Reduce medical errors Process large

[PDF] artificial intelligence in human resource management

[PDF] artificial intelligence in human resources management

[PDF] artificial intelligence in medical diagnosis pdf

[PDF] artificial intelligence in today's society

[PDF] artificial intelligence recruitment process

[PDF] artificial intelligence research paper 2019 pdf

[PDF] artigo 76 cpc

[PDF] artigo 76 do cpc comentado

[PDF] artigo 76 do cpc planalto

[PDF] artigo 76 novo cpc comentado

[PDF] artistas francesas mujeres

[PDF] artistas franceses famosos actuales

[PDF] artnaturals alcohol based hand sanitizer gel 1 gallon

[PDF] as as grammar exercises pdf

[PDF] as cited in apa 7th

Introduction to Machine

Learning & Its Application in

Healthcare

Lecture 4

Oct 3, 2018

Presentation by: Leila Karimi

1

What Is Machine Learning?

A branch of artificial intelligence, concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data.

Arthur Samuel (1959). Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed.

Tom Mitchell (1998) Well-posed Learning Problem: A computer program is said to learn from experience Ewith respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

2

What Is Machine Learning? Example

͞A computer program is said to learn from edžperience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E." Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. Classifying emails as spam or not spam ---> Task T Watching you label emails as spam or not spam ---> Experience E The number (or fraction) of emails correctly classified as spam/not spam --->

Performance measure P

Slide credit: Andrew Ng3

ML Applications

4

Slide credit: LiorRokach

The Learning Setting

Imagine learning algorithm is trying to decide which loan applicants are bad credit risks. Might represent each person by n features. (e.g., income range, debt load, employment history, etc.) Take sample S of data, labeled according to whether they wereͬweren't good risks. Goal of algorithm is to use data seen so far produce good prediction rule (a ͞hypothesis") h(x)for future data.

5Slide credit: AvrimBlum

The learning setting example

Given this data, some reasonable rules might be:

ͻPredict YES iff(!recent delinq) AND (%down > 5).

ͻPredict YES iff100*[mmp/inc] -1*[%down] < 25.

6

Slide credit: AvrimBlum

Big Questions

(A)How might we automatically generate rules that do well on observed data? ---> Algorithms (B)What kind of confidence do we have that they will do well in the future? ---> Performance Evaluation

7Slide credit: AvrimBlum

The machine learning framework

y = f(x) estimate the prediction functionfby minimizing the prediction error on the training set Testing:applyfto a never before seentest example xand output the predicted valuey = f(x)

OutputPrediction

Function

Input

ML in a Nutshell

Every machine learning algorithm has three components:

Representation

Evaluation

Optimization

9

Representation

Decision trees

Sets of rules / Logic programs

Graphical models (Bayes/Markov nets)

Neural networks

Support vector machines

10

Evaluation

Accuracy

Precision and recall

Squared error

Likelihood

Posterior probability

Cost / Utility

Margin

Entropy

K-L divergence

11

Optimization

Combinatorial optimization

E.g.: Greedy search

Convex optimization

E.g.: Gradient descent

Constrained optimization

E.g.: Linear programming

12

Machine Learning Algorithms

Supervised Learning

Training data includes desired outputs

Unsupervised Learning

Training data does not include desired outputs

Semi-supervised learning

Training data includes a few desired outputs

Others: Reinforcement learning, recommender systems 13

Supervised Learning

14

Slide credit: Yi-Fan Chang

Supervised learning process: two steps

Learning (training): Learn a model using the training data Testing: Test the model using unseen test data to assess the model accuracy 15 ,cases test ofnumber Total tionsclassificacorrect ofNumber AccuracySlide credit: Bing Liu

Unsupervised Learning

Learning patterns from unlabeled data

Tasks understanding and visualization anomaly detection information retrieval data compression 16

Unsupervised Learning (Cont.)

17

Slide credit: Yi-Fan Chang

Supervised Learning (Cont.)

Supervised learning categories and techniques

Linear classifier(numerical functions)

Parametric(Probabilistic functions)

Naïve Bayes, Gaussian discriminant analysis (GDA), Hidden Markov models (HMM),

Probabilistic graphical models

Non-parametric(Instance-based functions)

K-nearest neighbors, Kernel regression, Kernel density estimation, Local regression

Non-metric(Symbolic functions)

Classification and regression tree (CART), decision tree

Aggregation

Bagging (bootstrap + aggregation), Adaboost, Random forest 18

Unsupervised Learning (Cont.)

Unsupervised learning categories and techniques

Clustering

K-means clustering

Spectral clustering

Density Estimation

Gaussian mixture model (GMM)

Graphical models

Dimensionality reduction

Principal component analysis (PCA)

Factor analysis

19

Supervised Learning: Linear Classifier

Find a linear function to separate the classes

Techniques:

Perceptron

Logistic regression

Support vector machine (SVM)

Ada-line

Multi-layer perceptron (MLP)

20 , where wis an d-dim vector (learned)

Supervised Learning: Non-Linear Classification

Techniques:

Support vector machine (SVM)

Neural Networks

21

Supervised Learning: Decision Trees

22

Should I wait at this restaurant?

Slide credit: SRI International

Decision Tree Induction

(Recursively) partition examples according to the most importantattribute.

Key Concepts

entropy impurity of a set of examples (entropy = 0 if perfectly homogeneous) (#bits needed to encode class of an arbitrary example) information gain expected reduction in entropy caused by partitioning

23Slide credit: SRI International

Decision Tree Induction: Decision Boundary

24Slide credit: SRI International

Supervised Learning:Neural Networks

25

Motivation: human brain

massively parallel (1011neurons, ~20 types) small computational units with simple low-bandwidth communication (1014 synapses, 1-10ms cycle time)

Realization: neural network

units(neurons) connected by directed weighted links activation functionfrom inputs to output

Slide credit: SRI International

Neural Networks (continued)

26
Neural Network = parameterized family of nonlinear functions types

Slide credit: SRI International

Neural Network Learning

Key Idea: Adjusting the weights changes the function represented by the neural network (learning = optimization in weight space). Iteratively adjust weightsto reduce error(difference between network output and target output).

Weight Update

perceptron training rule linear programming delta rule backpropagation

27Slide credit: SRI International

Neural Network Learning: Decision Boundary

28
single-layer perceptronmulti-layer network

Slide credit: SRI International

Supervised Learning:Support Vector

Machines

Kernel Trick: Map data to higher-dimensional spacewhere they will be linearly separable. Learning a Classifier : optimal linear separator is one that has the largest marginbetween positive examples on one side and negative examples on the other

29Slide credit: SRI International & Andrew Moore

ĭ: xĺij(x)

Support Vector Machines: Decision Boundary

30

Supervised Learning:Nearest Neighbor

Models

Key Idea: Properties of an input xare likely to be similarto those of points in the neighborhoodof x. Basic Idea: Find (k) nearest neighbor(s) of xand infer target attribute value(s) of xbased on corresponding attribute value(s).

31Slide credit: SRI International

Nearest Neighbor Model: Decision Boundary

32Slide credit: SRI International

Evaluating classification methods

Predictive accuracy

Efficiency

time to construct the model time to use the model

Robustness: handling noise and missing values

Scalability: efficiency in disk-resident databases

Interpretability:

understandable and insight provided by the model

Compactness of the model

33,cases test ofnumber Total

tionsclassificacorrect ofNumber AccuracySlide credit: Bing Liu

Performance Evaluation

Randomly split examples into training set Uand test set V.

Use training set to learn a hypothesis H.

Measure % of Vcorrectly classified by H.

Repeat for different random splits and average results.

34Slide credit: SRI International

Generalization

Components of generalization error

Bias:how much the average model over all training sets differ from the true model? Error due to inaccurate assumptions/simplifications made by the model Variance:how much models estimated from different training sets differ from each other Underfitting:model is too ͞simple" to represent all the releǀant class characteristics

High bias and low variance

High training error and high test error

Overfitting:model is too ͞compledž" and fits irreleǀant characteristics (noise) in the data

Low bias and high variance

Low training error and high test error

35

Bias-Variance Trade-off

Models with too few parameters are

inaccurate because of a large bias (notquotesdbs_dbs19.pdfusesText_25