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
Previous PDF | Next PDF |
[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 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
1What 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.
2What 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
4Slide 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.
6Slide 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 Evaluation7Slide 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
InputML in a Nutshell
Every machine learning algorithm has three components:Representation
Evaluation
Optimization
9Representation
Decision trees
Sets of rules / Logic programs
Graphical models (Bayes/Markov nets)
Neural networks
Support vector machines
10Evaluation
Accuracy
Precision and recall
Squared error
Likelihood
Posterior probability
Cost / Utility
Margin
Entropy
K-L divergence
11Optimization
Combinatorial optimization
E.g.: Greedy search
Convex optimization
E.g.: Gradient descent
Constrained optimization
E.g.: Linear programming
12Machine 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 13Supervised Learning
14Slide 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 LiuUnsupervised Learning
Learning patterns from unlabeled data
Tasks understanding and visualization anomaly detection information retrieval data compression 16Unsupervised Learning (Cont.)
17Slide 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 regressionNon-metric(Symbolic functions)
Classification and regression tree (CART), decision treeAggregation
Bagging (bootstrap + aggregation), Adaboost, Random forest 18Unsupervised 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
19Supervised 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
21Supervised Learning: Decision Trees
22Should 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 partitioning23Slide credit: SRI International
Decision Tree Induction: Decision Boundary
24Slide credit: SRI International
Supervised Learning:Neural Networks
25Motivation: 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 outputSlide credit: SRI International
Neural Networks (continued)
26Neural 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 backpropagation27Slide credit: SRI International
Neural Network Learning: Decision Boundary
28single-layer perceptronmulti-layer network