2. Tele communication in India ( July 2012)
• Late nineties, India invested in Cellular instead of wired phone lines
• India's mobile phone subscribers' base touches 929 million
• Wireline: 33 million
• Wireless: 929 million (~ 28 time of wire line)
• Overall teledensity in India reached 79.28 per cent
Benefit of Emerging Technology Adoption
7. Emerging Technologies
1. Smartphone
Information wherever you are
2. Virtual Reality/3D gaming
Simulation of real world scenario
3. Wearable Devices
Unobtrusive continuous health monitoring
4. Ontology
Knowledge as a set of concepts within a domain, and the relationships
among those concepts.
5. Machine Learning
Data to Information
6. Big Data
Unlimited storage and compute
7. Cloud Computing
Deliver Infrastructure, Platform and/or Application as Service
8. Crowd Sourcing
Leverage the crowd
9. Smartphone
Information wherever you are
Smartphone are becoming rich in personalized information center due
their following abilities:
Portable personal device with phone, camera, music, internet and
apps
PIM: Personal Information Management
Profiles tracker – likes and dislike profiling
Location information: GPS
Information Guide: Search, directions, deals etc.
Sensors
Three-axis gyro
Accelerometer
Proximity sensor
Ambient light sensor
Notifications
Apps for almost everything
About 5,800 health care smartphone applications
Perfect device for collecting personal information through direct data
entry or indirect through sensors and preferences that can be useful for
personal healthcare and wellness management.
10. Smartphone
Applications in healthcare
Medical Content and First Aid
Boost Health and Fitness
Health Monitoring and Treatment
Training on the Go
System Monitoring
Collaboration
11. Medical Content and First Aid
iTriage
Created by two ER docs, iTriage helps you answer the questions: “What medical condition could I have?” and “Where
should I go for treatment?”
12. Medical Content and First Aid
WebMD
WebMD helps you with your decision-making and health improvement efforts by providing mobile access 24/7 to
mobile-optimized health information and decision-support tools including WebMD’s Symptom Checker, Drugs &
Treatments, First Aid Information and Local Health Listings.
14. Health Monitoring and Treatment
iHealth
iHealth's Blood Pressure Dock lets you take more control of your personal healthcare using iPhone 4, iPad and
iPod touch (4th Gen.).
15. Training on the Go
RNotes: Nurse’s Clinician Pocket Guide
RNotes® helps nurses provide premium patient care by putting the latest quick-reference, clinically-focused nursing
information at their fingertips.
16. Payers related use cases
Provider Support
Apps for Members, e.g. health4me from
Unitedhealthcare.
Visibility on the Go
Tracking information
Dashboards
Business Process
Exception Management
Monitoring
Notifications
18. Virtual Reality(VR)
Surgery
Surgical navigation, IGS, CAS, AR surgery, and
robot-assisted surgery
Medical Data Visualization
Multi-modality image fusion, advanced 2D/3D/4D
image reconstruction, and pre-operative planning
and other advanced analytical software tools
Education and Training
Virtual surgical simulators and other simulators for
medical patient procedures
Rehabilitation and Therapy
Immersive VR systems for pain
management, behavioral therapy, psychological
therapy, physical rehabilitation, and motor skills
training
19. 3D Gaming
Pulse !!: Virtual Clinical Learning Lab for Health Care
Training
Pulse!! is the first ever, immersive virtual learning space
for training health care professionals in clinical skills.
Cutting-edge graphics recreate a lifelike, interactive,
virtual environment in which civilian and military heath
care professionals practice clinical skills in order to better
respond to injuries sustained during catastrophic
incidents, such as combat or bioterrorism.
It is developed in partnership with Texas A & M University
- Corpus Christi and is funded from a federal grant from
the Department of the Navy's Office of Naval Research.
21. Wearable Devices
Wearable devices equipped with sensors, Web
connections, or both, help consumers and healthcare
providers track health and fitness.
ABI Research last year estimated that the market for
wearable health-related devices, ranging from heart
monitors to biosensors that read body temperature and
motion, will reach more than 100 million device sales
annually by 2016.
22.
23. Basic B1
The consumer-oriented Basis B1 wrist band incorporates five
sensors to provide a precise view of a person's health immediately
and over extended periods of time.
an optical blood flow sensor that detects heart rate, through
pulse or blood flow;
a 3D accelerometer, a highly sensitive sensor that detects the
smallest movements, regardless of whether users are alert and
active or sleeping;
a body temperature sensor to measure exertion during activity;
an ambient temperature sensor to detect the outside
temperature and compare it to body temperature to boost the
accuracy of caloric burn calculations;
and a galvanic skin response sensor to measure the intensity of
sweat output.
24. Health Monitoring and Treatment
Raisin: A raisin that can save your
life
The FDA recently approved the marketing of a
new medical device, Raisin Personal Monitor,
worn like a band-aid that receives data from a
sensor you swallow in a pill and then sends out
a wireless health report.
The device manufacturer, Proteus Biomedical,
developed ingestible sensors made out of food
products that serve as markers in the body.
Then it transmits an ultra-low-power signal to
the Raisin, recording everything from
date/time, type of drug, dose, place of
manufacture and physical reactions.
It was designed primarily for heart failure
patients, but the applications may extend to
other conditions.
Image by Proteus Biomedical
25. Ontology
Knowledge as a set of concepts within a domain, and
the relationships among those concepts.
26. Ontology
Ontology models knowledge as a set of concepts within a domain, and the
relationships among those concepts.
An ontology renders shared vocabulary and taxonomy which models a domain
with the definition of objects and/or concepts and their properties and relations.
Ontology helps in taking a data and converts into information using common set
of concepts or terminology so that the information can be:
Categorized
Uniform meaning so that it can be compared with other set of data
Used in Artificial Intelligence, the Semantic Web, biomedical informatics, library
science, enterprise bookmarking, Knowledge Management.
Healthcare Usages:
EHR
HIE
Translation: ICD10 ICD9
Unstructured data processing
Analytics
28. Machine Learning
Machine Learning is the study of computer algorithms that
improve automatically through experience.
Main Algorithm Types
Supervised Learning
Classification
Regression
Unsupervised Learning
Clustering
Density Estimation
Applications
Natural Language Process, useful for EHR
Fraud Detection
Predictive Analytics
Forecasting
30. Big Data
Data Characteristics
Volume
Variety
Velocity
Variability
Complexity
Desired Properties of a Big Data System
Robust and fault-tolerant
Low latency reads and updates
Scalable
General System
Extensible
Allows ad hoc queries
Minimal maintenance
Debuggable
Big Data is data sets that exceeds the boundaries and size of the normal processing capabilities forcing
you to take non traditional approach.
Big data is a popular overloaded term used to describe the exponential growth, availability and use of
information, both structured and unstructured.
31. Big Data Technical Approach
NoSQL Storage
Distributed Storage
Parallel Processing
MapReduce
Lambda Architecture
The Lambda Architecture solves the problem of computing arbitrary functions on arbitrary data in realtime by
decomposing the problem into three layers
1. Speed Layer
Compensate the high latency of update to serving layer
Fast incremental algorithm
Batch layer eventually override speed layer
2. Serving layer
Random access to batch view
Updated by batch layer
3. Batch Layer
Store master dataset
Compute arbitrary view
32. Hadoop
Hadoop is a platform that provides both distributed storage and computational capabilities.
Hadoop was first conceived to fix a scalability issue that existed in Nutch, an open source crawler and search
engine.
It is based on Google papers on Google File System (GFS), and MapReduce, a computational frameworks for
parallel processing.
Figure 1.1 The Hadoop environment
Because you’re coming to this book with an interest in getting some practical
3
This section will look at Hadoop from an architectural perspective, examine
how industry uses it and consider some of its weaknesses. Once we get through the
background we’ll look at how we can install Hadoop and run a MapReduce job.
Hadoop proper, as shown in the following figure 1.2, is a distributed
master-slave architecture that consists of the Hadoop Distributed File System3
(HDFS) for storage, and MapReduce for computational capabilities. Traits intrinsic
to Hadoop are data partitioning and parallel computation of large data sets. Its
storage and computational capabilities scale with the addition of hosts to a Hadoop
cluster, and can reach volume sizes in the petabytes on clusters with thousands of
hosts.
Footnote 3m A model of communication where one process called the master has control over one or more
other processes, called slaves.
Figure 1.2 High-level Hadoop architecture
4
34. Hadoop: Related Technology
The Hadoop ecosystem is diverse and grows by the day. It’s impossible to keep
track of all the various projects that interact with Hadoop in some form. In this
book the focus is on the tools that are currently receiving the highest adoption from
users, as shown in the following figure 1.9 .
Figure 1.9 Hadoop and related technologies
35. Big Data
Use cases
Batch Transaction Processing
Analytics
Test Data selection based on
rules/scenarios
Search
EHR & HIE
37. Cloud Computing
Cloud computing is the delivery of computing
and storage capacity as a service.
The name comes from the use of a cloud-
shaped symbol as an abstraction for the
complex infrastructure it contains in system
diagrams.
Cloud computing entrusts services with a user's
data, software and computation over a network.
There are three types of cloud computing:
Infrastructure as a Service (IaaS)
Platform as a Service (PaaS)
Software as a Service (SaaS)
38. eMix
Electronic Medical Information Exchange
A cloud-based virtualized radiological image and information report service, provides secure
access for physicians, hospitals and patients to view images and information.
In the past, this was done by setting up a special network connection to transmit the
file, express-mailing a CD, or printing and mailing the image (film).
http://www.emix.com/
40. Crowd Sourcing
Crowd sourcing is a process that involves outsourcing tasks to a distributed
group of people. This process can occur both online and offline.
The difference between crowdsourcing and ordinary outsourcing is that a task
or problem is outsourced to an undefined public rather than a specific
body, such as paid employees.
Crowd sourcing delivers the elasticity of cloud by leveraging peer-to-peer
technologies.
It also mitigates concerns about loss of privacy, since a single cloud provider
does not have a global view of anyone’s data.
Also, it presents a more economical solution compared to cloud computing:
instead of paying a cloud provider for services, the contribution is made in-
kind by becoming part of the computing system that offers computing
power, storage capacity, data or knowledge. As a consequence, the concept
of “cloud owner” is removed from the equation.
Human brain guided computation is able to perform task that computers can
not do. Example, quality or accuracy of a content on Wikipedia.
41. Crowd Sourcing: Challenges
Will we be able to crowd-source CPU hours in the future?
Will the crowd carry sensors on their mobile devices to make the
network more aware of environmental situations?
Do new security questions arise?
How should we deal with performance issues?
How can we extract high-quality answers from data created by the
crowd, which implies many small contributions from well-
intentioned providers that may not be correct?
42. Crowd Sourcing: Examples
SETI@home
Search for Extraterrestrial Intelligence (SETI)
(http://setiathome.berkeley.edu/)
An early example of crowd computing was the discovery of
a gold deposit location at the Moribund Red Lake Mine in
Northern Ontario. Using all available data, the company,
Goldcorp, Inc. had been unable to identify the location of
new deposits on their land. In desperation, the CEO put all
relevant geological data on the web and created a contest,
open to anyone in the world. An obscure firm in Australia
used their software and algorithms to crack the puzzle. As
a result, the company found an additional 8 million ounces
of gold at the mine. The only cost was the nominal prize
money awarded.
Real Time Traffic information including jams, speed,
construction etc.
43. Crowd Sourcing: Use Cases
Enterprise Use Cases
Managing business processes for their customers
Moderating images and user-generated content
Analyzing sentiment for brands in Social Media
Improving search relevance
Processing data (business listings, points-of-
interest, contacts, etc…)
Structuring and normalizing digital content
An electronic health record is defined by the National Alliance for Health Information Technology as an electronic record of health-related information on an individual that conforms to nationally recognized interoperability standards and that can be created, managed, and consulted by authorized clinicians and staff across more than one health care organization.In layman’s terms EHRs are computerized versions of patients’ clinical, demographic and administrative data. The records may include treatment histories, medical test reports and images stored in an electronic format.Health information exchange (HIE) is the electronic movement of health-related information among organizations according to nationally recognized standards. HIE also sometimes is referred to as a health information network (HIN).
Patients, doctors, insurers, government and researchers will all make better decisions in healthcare with better information, which we will get from the grand healthcare platform. We need to turn our islands of healthcare data into a network of networks that is ultimately global..
Volume. Many factors contribute to the increase in data volume transaction-based data stored through the yearstext data constantly streaming in from social mediaincreasing amounts of sensor data being collected, etc. VarietyData today comes in all types of formats, traditional structured data, text documents, email, meter-collected data, video, audio, stock ticker data and financial transactions. By some estimates, 80 percent of an organization's data is not numeric! But it still must be included in analyses and decision making.VelocityHow fast data is being produced and how fast the data must be processed to meet demand. VariabilityIn addition to the increasing velocities and varieties of data, data flows can be highly inconsistent with periodic peaks. Fro example:Is something big trending in the social media? Perhaps there is a high-profile IPO looming. ComplexityWhen you deal with huge volumes of data, it comes from multiple sources. It is quite an undertaking to link, match, cleanse and transform data across systems. However, it is necessary to connect and correlate relationships, hierarchies and multiple data linkages or your data can quickly spiral out of control. Data governance can help you determine how disparate data relates to common definitions and how to systematically integrate structured and unstructured data assets to produce high-quality information that is useful, appropriate and up-to-date.
No single approach or standard. This field is still evolving.
Thedefacthaddo
Volume. Many factors contribute to the increase in data volume transaction-based data stored through the yearstext data constantly streaming in from social mediaincreasing amounts of sensor data being collected, etc. VarietyData today comes in all types of formats, traditional structured data, text documents, email, meter-collected data, video, audio, stock ticker data and financial transactions. By some estimates, 80 percent of an organization's data is not numeric! But it still must be included in analyses and decision making.VelocityHow fast data is being produced and how fast the data must be processed to meet demand. VariabilityIn addition to the increasing velocities and varieties of data, data flows can be highly inconsistent with periodic peaks. Fro example:Is something big trending in the social media? Perhaps there is a high-profile IPO looming. ComplexityWhen you deal with huge volumes of data, it comes from multiple sources. It is quite an undertaking to link, match, cleanse and transform data across systems. However, it is necessary to connect and correlate relationships, hierarchies and multiple data linkages or your data can quickly spiral out of control. Data governance can help you determine how disparate data relates to common definitions and how to systematically integrate structured and unstructured data assets to produce high-quality information that is useful, appropriate and up-to-date.
Apache Sqoopis a tool designed for efficiently transferring bulk data between Apache Hadoop and structured datastores such as relational databases.Apache Flume is a distributed, reliable, and available service for efficiently collecting, aggregating, and moving large amounts of log data.Apache Oozie is a workflow/coordination system to manage Apache Hadoop(TM) jobs.HBase is an open-source, distributed, versioned, column-oriented store modeled after Google's Bigtable: A Distributed Storage System for Structured Data. Use HBase when you need random, realtime read/write access to your Big Data.Hive: A data warehouse infrastructure that provides data summarization and ad hoc querying.Mahout: A Scalable machine learning and data mining library.Pig: A high-level data-flow language and execution framework for parallel computation.Cascading is an application framework for Java developers to quickly and easily develop robust Data Analytics and Data Management applications on Apache Hadoop.Crunch, a Java library that aims to make writing, testing, and running MapReduce pipelines easy, efficient, and even fun. Crunch’s design is modeled after Google’s FlumeJava, focusing on a small set of simple primitive operations and lightweight user-defined functions that can be combined to create complex, multi-stage pipelines.