Understand what healthcare analytics is.
Identify the 5-stage Analytics Program Lifecycle (APL).
Understand how data analytics can be used in healthcare.
Check it on Experfy: https://www.experfy.com/training/courses/introduction-to-healthcare-analytics.
The role of real world data and evidence in building a sustainable & efficien...Office of Health Economics
This presentation defines RWD and RWE in the context of digital health, and looks at potential uses for RWD and RWE. It briefly sets out the current landscape in Malaysia and looks at the challenges in using RWE. In particular, the issues of access, governance and ensuring good quality are considered.
Predictive Analytics is already being leveraged in several sectors and has helped businesses gain efficiency. In the field of healthcare, Predictive Analytics promises to improve healthcare by forecasting the likelihood of an event enabling healthcare providers to take pre-emptive action where possible.
Predictive Analytics uses statistical analysis and other techniques to search through reams of patient data and analyses it to predict outcomes for individual patients.
Problems such as inaccurate diagnoses and poor drug-adherence pose challenges to individual health and safety. These challenges are now being alleviated with big data analytics using personalized drug regimes, follow-up alerts and real-time diagnosis monitoring.
In this paper, learn how predictive analytics is helping healthcare industry with technologies such as Clinical Decision Support, Medical Text Analysis and Electronic Health Record (EHR).
Understand what healthcare analytics is.
Identify the 5-stage Analytics Program Lifecycle (APL).
Understand how data analytics can be used in healthcare.
Check it on Experfy: https://www.experfy.com/training/courses/introduction-to-healthcare-analytics.
The role of real world data and evidence in building a sustainable & efficien...Office of Health Economics
This presentation defines RWD and RWE in the context of digital health, and looks at potential uses for RWD and RWE. It briefly sets out the current landscape in Malaysia and looks at the challenges in using RWE. In particular, the issues of access, governance and ensuring good quality are considered.
Predictive Analytics is already being leveraged in several sectors and has helped businesses gain efficiency. In the field of healthcare, Predictive Analytics promises to improve healthcare by forecasting the likelihood of an event enabling healthcare providers to take pre-emptive action where possible.
Predictive Analytics uses statistical analysis and other techniques to search through reams of patient data and analyses it to predict outcomes for individual patients.
Problems such as inaccurate diagnoses and poor drug-adherence pose challenges to individual health and safety. These challenges are now being alleviated with big data analytics using personalized drug regimes, follow-up alerts and real-time diagnosis monitoring.
In this paper, learn how predictive analytics is helping healthcare industry with technologies such as Clinical Decision Support, Medical Text Analysis and Electronic Health Record (EHR).
Using real-world evidence to investigate clinical research questionsKarin Verspoor
Adoption of electronic health records to document extensive clinical information brings with it the opportunity to utilise that information to support clinical research, and ultimately to support clinical decision making. In this talk, I discuss both these opportunities and the challenges that we face when working with real-world clinical data, and introduce some of the strategies that we are adopting to make this data more usable, and to extract more value from it. I specifically discuss the use of natural language processing to transform clinical documentation into structured data for this purpose.
Clinicians Satisfaction Before and After Transition from a Basic to a Compreh...Allison McCoy
Healthcare organizations are transitioning from basic to comprehensive electronic health records (EHRs) to meet Meaningful Use requirements and improve patient safety. Yet, full adoption of EHRs is lagging and may be linked to clinician dissatisfaction. In depth assessment of satisfaction before, during, and after EHR transition is rarely done. Using an adapted published tool to assess adoption and satisfaction with EHRs, we surveyed clinicians at a large, non-profit academic medical center before (baseline) and 6-12 months (short-term follow-up) and 12-24 months (long-term follow-up) after transition from a basic, locally-developed to a comprehensive, commercial EHR. Satisfaction with the EHR (overall and by component) was captured at each interval. Overall satisfaction was highest at baseline (85%), lowest at short-term follow-up (66%), and increasing at long-term follow-up (79%). This trend was similar for satisfaction with EHR components designed to improve patient safety including clinical decision support, patient communication, health information exchange, and system reliability. Conversely, at baseline, short-term and long-term follow-up, perceptions of productivity, ability to provide better care with the EHR, and satisfaction with available resources, were lower at both short- and long-term follow-up compared to baseline. Persistent dissatisfaction with productivity and resources was identified. Addressing determinants of dissatisfaction may increase full adoption of EHRs. Further investigation in larger populations is warranted.
Presentation on Predictive modeling in Health-care at San Jose, Ca 2015. This presentation talks about healthcare industry in US, provides stats and forecasts. It then discusses a few use cases in health care and goes into detail on a kaggle example.
Part 1 - Tools for Streamlining and Automating Your Law PracticeGreg McLawsen
Take stock of your law practice. Where should you be devoting your time? What common tasks drag you down? And most importantly, what can you do to make your law practice more efficient and profitable? Greg will teach you how can understand the systems that run your law firm, and help you identify the issues holding you back.
A marketing executive with over 20 years of experience, Eric Lent formerly held a leadership position with The Hershey Company and Hershey International. Eric Lent now serves as vice president of InterContinental Hotel Group's Holiday Inn and Crowne PlazaHotels and Resorts, Americas and serves as an advocate for Compassion International, a Christian charity for children living in poverty. In April 2016, Compassion International ranked in the top one percent with Charity Navigator, a charity-evaluating company.
Using real-world evidence to investigate clinical research questionsKarin Verspoor
Adoption of electronic health records to document extensive clinical information brings with it the opportunity to utilise that information to support clinical research, and ultimately to support clinical decision making. In this talk, I discuss both these opportunities and the challenges that we face when working with real-world clinical data, and introduce some of the strategies that we are adopting to make this data more usable, and to extract more value from it. I specifically discuss the use of natural language processing to transform clinical documentation into structured data for this purpose.
Clinicians Satisfaction Before and After Transition from a Basic to a Compreh...Allison McCoy
Healthcare organizations are transitioning from basic to comprehensive electronic health records (EHRs) to meet Meaningful Use requirements and improve patient safety. Yet, full adoption of EHRs is lagging and may be linked to clinician dissatisfaction. In depth assessment of satisfaction before, during, and after EHR transition is rarely done. Using an adapted published tool to assess adoption and satisfaction with EHRs, we surveyed clinicians at a large, non-profit academic medical center before (baseline) and 6-12 months (short-term follow-up) and 12-24 months (long-term follow-up) after transition from a basic, locally-developed to a comprehensive, commercial EHR. Satisfaction with the EHR (overall and by component) was captured at each interval. Overall satisfaction was highest at baseline (85%), lowest at short-term follow-up (66%), and increasing at long-term follow-up (79%). This trend was similar for satisfaction with EHR components designed to improve patient safety including clinical decision support, patient communication, health information exchange, and system reliability. Conversely, at baseline, short-term and long-term follow-up, perceptions of productivity, ability to provide better care with the EHR, and satisfaction with available resources, were lower at both short- and long-term follow-up compared to baseline. Persistent dissatisfaction with productivity and resources was identified. Addressing determinants of dissatisfaction may increase full adoption of EHRs. Further investigation in larger populations is warranted.
Presentation on Predictive modeling in Health-care at San Jose, Ca 2015. This presentation talks about healthcare industry in US, provides stats and forecasts. It then discusses a few use cases in health care and goes into detail on a kaggle example.
Part 1 - Tools for Streamlining and Automating Your Law PracticeGreg McLawsen
Take stock of your law practice. Where should you be devoting your time? What common tasks drag you down? And most importantly, what can you do to make your law practice more efficient and profitable? Greg will teach you how can understand the systems that run your law firm, and help you identify the issues holding you back.
A marketing executive with over 20 years of experience, Eric Lent formerly held a leadership position with The Hershey Company and Hershey International. Eric Lent now serves as vice president of InterContinental Hotel Group's Holiday Inn and Crowne PlazaHotels and Resorts, Americas and serves as an advocate for Compassion International, a Christian charity for children living in poverty. In April 2016, Compassion International ranked in the top one percent with Charity Navigator, a charity-evaluating company.
Powering the Future of Healthcare in Asia Pacific | Full ReportGalen Growth
How technology will change healthcare delivery
1) The creative destruction of healthcare
2) Data driven healthcare
3) Funding
4) Disruption in Healthcare
5) Opportunity to leapfrog to accelerate change
Big data, RWE and AI in Clinical Trials made simpleHadas Jacoby
Technology is slowly but surely penetrating the healthcare industry in general and the clinical trials sector in particular. New and advanced solutions offer a variety of possibilities aimed to both improving existing processes and creating new and more efficient ones. And on top of all stands the desire to make clinical trials more patient centric.
In all of this, even though some of the technologies have yet to mature enough to meet the high quality standards necessary, it is important to know them and begin imagining the promise they hold for clinical trials.
As the author of “Big Data in Healthcare Hype and Hope,” Dr. Feldman has interviewed over 180 emerging tech and healthcare companies, always asking, “How can your new approach help patients?” Her research shows that data, as an enabling tool, has the power to give us critical new insights into not only what causes disease, but what comprises normal. Despite this promise, few patients have reaped the benefits of personalized medicine. A panel of leading big data innovators will discuss the evolving health data ecosystem and how big data is being leveraged for research, discovery, clinical trials, genomics, and cancer care. Case studies and real-life examples of what’s working, what’s not working, and how we can help speed up progress to get patients the right care at the right time will be explored and debated.
• Bonnie Feldman, DDS, MBA - Chief Growth Officer, @DrBonnie360
• Colin Hill - CEO, GNS Healthcare
• Jonathan Hirsch - Founder & President, Syapse
• Andrew Kasarskis, PhD - Co-Director, Icahn Institute for Genomics & Multiscale Biology; Associate Professor, Genetics & Genomic Studies, Icaahn School of Medicine at Mt. Sinai
• William King - CEO, Zephyr Health
New York eHealth Collaborative Digital Health Conference
November 18, 2014
Advanced Laboratory Analytics — A Disruptive Solution for Health SystemsViewics
As US healthcare systems grapple with the recent upheavals in care payment and delivery, they are turning to advanced analytics as their “central nervous systems” for driving care and financial performance.
Laboratory information — spanning chemistry, pathology, microbiology and molecular testing, for example — is among the best sources of data for these advanced analytics, including clinician decision support, predictive analytics, population health management, and personalized medicine. When strategically harnessed and integrated to create a patient-centric lab data lake, laboratory information can form an affordable yet competitively powerful advanced analytics solution well suited for many health systems — i.e., a disruptive option.
L. Eleanor J. Herriman, MD, MBA, Chief Medical Informatics Officer of Viewics, explains why laboratory data should be a core strategic component for achieving success in value-based healthcare.
TeraCrunch: Transforming Organizations with Machien Learning and Gen-AI Solut...KC Digital Drive
These slides were presented at the February 2024 meeting of the KC Digital Drive Health Innovation Team.
This presentation was given by Tera Crunch. As they describe things: Let's face it – navigating the AI world can be like walking through a maze. You’ve got IT firms moonlighting as AI gurus, in-house teams juggling too much, and bespoke solution shops charging an arm and a leg. That’s where we come in. TeraCrunch is not just another AI & Gen-AI company. We’re the experienced friend you call when you need results without the runaround. We've been around the block for 11 years, building over 150 solutions with a track record of 5-40x ROI.
What makes us different? We cut through the complexities and unnecessary costs with our secret sauce – a blend of proprietary methods and pre-developed tech-stack we've honed for over a decade – getting you the results you need, fast. Plus, our data scientists with roots in places like Harvard and NASA, roll up their sleeves and get to work with your crew. With TeraCrunch, you’re choosing a partner that makes the complex simple and the uncertain sure.
Our presenter will be CEO Tapan Bhatt. With over 19 years of experience in developing cutting-edge technology products and fueling growth in start-up ventures, Tapan's unrivaled insights have been instrumental in driving success for numerous venture capital-backed high-tech startups across both coasts. Prior to establishing TeraCrunch, he held key leadership positions in a series of technology startups that achieved remarkable success. As Head of Business Development at ROAM (acquired by Ingenico), Head of Solution Sales & Sales Engineering at AisleBuyer(acquired by Intuit), Executive Director at Motricity (IPO in 2010, NASDAQ:MOTR), and Executive Director at Amobee Media Systems (acquired by SingTel).
Tapan has an MBA in Marketing from Avila University and a foundation in Electrical Engineering from K.K.Wagh College of Engineering. As part of his many external activities and roles, he is an Innovation Board Member of St. Luke's Health System.
Is mHealth Prescribing: Dead or Thriving?AppScript
App rating is happening everywhere in the ecosystem, but without putting apps in practice, evaluating the prescribing data and patient feedback, we only have half the story. Learn about the prescribing data, rating and scoring methodologies and the evidence of the growing promise of mobile health curation, discovery and distribution.
Healthcare Analytics Adoption Model -- UpdatedHealth Catalyst
The Healthcare Analytics Adoption Model is the result of a collaboration of healthcare industry veterans over the last 15 years. The model borrows lessons learned from the HIMSS EMR Adoption Model, and describes an analogous approach for assessing the adoption of analytics in healthcare.
The Healthcare Analytics Adoption Model provides:
1) A framework for evaluating the industry’s adoption of analytics
2) A roadmap for organizations to measure their own progress toward analytic adoption
3) A framework for evaluating vendor products
This Analytics Adoption Model will enable healthcare organizations to fully understand and leverage the capabilities of analytics and so achieve the ultimate goal that has eluded most provider organizations – that of improving the quality of care while lowering costs and enhancing clinician and patient satisfaction.
A hybrid approach to data management is emerging in healthcare as organizations recognize the value of an enterprise data warehouse in combination with a data lake.
In this SlideShare, we discuss data lakes in healthcare and we:
Provide an overview of a Hadoop-based data lake architecture and integration platform, and its application in machine learning, predictive modeling, and data discovery
Discuss several key use cases driving the adoption of data lakes for both providers and health plans
Discuss available data storage forms and the required tools for a data lake environment
Detail best practices for conducting data lake assessments and review key implementation considerations for healthcare
The healthcare industry has quietly shed the laggards tag and has quickly emerged as frontrunners in digitization. Hospitals are driving technology advancements by creating a digital framework for seamless integration of all aspects of patient care and administration. There are 5 major themes that are seen as critical in the hospital IT ecosystem – Smart Care, Patient Information Management, Remote Care, Medical Devices, and Intelligent Enterprise Systems.
Large enterprises such as Microsoft and Accenture are collaborating with healthcare providers to address a variety of use cases such as chronic disease management, virtual care solutions, risk scoring, patient tracking and monitoring, precision medicine, and patient on/off-boarding. Accenture and Microsoft helped Spain’s Basque Country Health Centre build a remote elderly patient monitoring system. Athenahealth’s cloud-based network system helps Minnie Hamilton Health System identify bottlenecks and streamline the revenue cycle.
Download the report as we provide an overview of the hospital IT landscape, understand digital transformation trends across these 5 major themes and the opportunities available for vendors and service providers.
Case Study “Investment in a Health IT Infrastructure, the Future Quality Imperative”
Steven Anderman
Chief Operating Officer & SVP, Operations
Bronx-Lebanon Hospital Center
Enabling community and patient centred care, pop up uni, 11am, 3 september 2015NHS England
Expo is the most significant annual health and social care event in the calendar, uniting more NHS and care leaders, commissioners, clinicians, voluntary sector partners, innovators and media than any other health and care event.
Expo 15 returned to Manchester and was hosted once again by NHS England. Around 5000 people a day from health and care, the voluntary sector, local government, and industry joined together at Manchester Central Convention Centre for two packed days of speakers, workshops, exhibitions and professional development.
This year, Expo was more relevant and engaging than ever before, happening within the first 100 days of the new Government, and almost 12 months after the publication of the NHS Five Year Forward View. It was also a great opportunity to check on and learn from the progress of Greater Manchester as the area prepares to take over a £6 billion devolved health and social care budget, pledging to integrate hospital, community, primary and social care and vastly improve health and well-being.
More information is available online: www.expo.nhs.uk
CORD Rare Drug Conference, June 8 - 9, 2022
Opportunities and Challenges for Data Management Real-World Data and Real-World Evidence
• Patient support programs: Sandra Anderson, Innomar Strategies
• AI for Data Management and Enhancement: Aaron Leibtag, Pentavere
• Patient Support and RWE: Laurie Lambert, CADTH
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...2023240532
Quantitative data Analysis
Overview
Reliability Analysis (Cronbach Alpha)
Common Method Bias (Harman Single Factor Test)
Frequency Analysis (Demographic)
Descriptive Analysis
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
Explore our comprehensive data analysis project presentation on predicting product ad campaign performance. Learn how data-driven insights can optimize your marketing strategies and enhance campaign effectiveness. Perfect for professionals and students looking to understand the power of data analysis in advertising. for more details visit: https://bostoninstituteofanalytics.org/data-science-and-artificial-intelligence/
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Data and AI
Discussion on Vector Databases, Unstructured Data and AI
https://www.meetup.com/unstructured-data-meetup-new-york/
This meetup is for people working in unstructured data. Speakers will come present about related topics such as vector databases, LLMs, and managing data at scale. The intended audience of this group includes roles like machine learning engineers, data scientists, data engineers, software engineers, and PMs.This meetup was formerly Milvus Meetup, and is sponsored by Zilliz maintainers of Milvus.
2. HEALTHCARE ANALYTICS THEN & NOW
1854 CHOLERA ENDEMIC, LONDON 2014 EBOLA EPIDEMIC
- Rudimentary cluster mapping
- Manual and inaccurate analysis
- Retrospective
- (Biomosaic tool), CDC Emergency
Response Center
- Sophisticated predictive modeling
- data from mobile phones,
historical epidemiological data
- Multiple data sources
- High computing power
3. A BRIEF STORY ON HOW HPE DEPLOYED
ANALYTICS TO IMPROVE PATIENT ENGAGEMENT
AT LUCILE PACKARD CHILDREN’S HOSPITAL
4. DRIVER 1:
HEALTHCARE TODAY HAS BECOME DATA
CENTRIC
200
0
BIOLOGICAL DATABASES IN 10 YEARS
80
Mb
PATIENT DATA GENERATED PER YEAR
600
Bn
SEQUENCED NUCLEOTIDES PER WEEK ON AN ILLUMINA
HISEQ
5. DRIVER 2: MEDICAL ERRORS LEADING TO
INCREASED CASUALITIES AND COST OF CARE
1:300
1:10,00
0
CHANCE OF MEDICAL
CASUALITY
CHANCE OF AIR TRAVEL
CASUALITY
1.4 Mn
PEOPLE SUFFERING FROM
HOSPITAL INFECTIONS
WORLDWIDE
1.3 Mn
DEATHS CAUSED BY INFECTIONS
THROUGH UNSTERILIZED
INSTRUMENTS
6. DRIVER 3:
HEALTHCARE EVOLUTION TOWARDS EVIDENCE
BASED MEDICINE AND ACCOUNTABLE CARE
DELIVERYEcosystemintegration
Today’s
healthcare
Collaborative
healthcare
Evidence Based
Personalized
Healthcare
LowHigh
Integrated
healthcare
Different
providers will
be at different
stages
• Stand-alone
• Best of breed
• Fragmented systems
• Integrated
EMR, EHR,
PMS, CPOE
• Real-time
alerts
• HIE/improve
d access to
data
• Tight linkage
between
physicians &
hospitals
• Care
collaboration
• Regional, state
and national
RHIOS, NHIN
• Patient access
to data
• Personalized/
evidence-based
clinical decision
support
• Patient
engagement
Quality of Care and OutcomesLow High
7. THE FOUR V’S TOGETHER DEFINE THE
IMPORTANCE OF ANALYTICS FOR
HEALTHCARE
VOLUME VARIETY
VALUE VELOCITY
• 500 petabytes to 25,000
Petabytes by 2020
• Key sources :MRI,CT &
PET Scans
• 1hr to sequence
whole genome of
humans
•50% reduction in time
for genome
sequencing for rare
diseases
Behavioural data,
Environmental data
Medical record data
Vital sign data
Nutritional data
Pharmaocological data
• <50% hospital labour
compensation ratio
• $300 Bn cost savings for
hospitals in US.
8. ANALYTICS APPLICATIONS ACROSS THE
CARE DELIVERY SPECTRUM
CLINICAL
ANALYTICS
BUSINESS
ANALYTIC
S
PATIENT
COMPLIAN
CE
CLINICAL HEALTH
OUTCOMES ANALYTICS
1
RESEARCH
&DEVELOPMENT
ANALYTICS
2
DISEASE
MANAGEMEN
T
TREATMENT
EFFECTIVENES
S
SITE
SELECTION
TARGETED
THERAPEUTIC
S
PATIENT
COHORT
IDENTIFICATIO
N
5
OPERATIONAL
ANALYTICS
FACILITY
UTILIZATION
STAFF
UTILIZATION
PROCESS
QUALITY
CONTROL
COMPLIANCE
REPORTING
3
MARKETING
ANALYTICS
CUSTOMER
SEGMENTATI
ON
SOCIAL
NETWORK
ANALYSIS
PRICING
OPTIMIZATIO
N
CUSTOMER
LIFETIME
VALUE
4
FINANCE AND FRAUD
BILLING
QUALITY
FRAUD
DETECTIO
N
RISK
MANAGEMEN
T
9. THE DATA FOR APPLYING ANALYTICS ACROSS
THE HEALTHCARE SPECTRUM COMES FROM
SEVERAL SOURCES
• Video conferences
• Downloads
• Call notes
• SMS
• Web chat
• Blogs
• Social networks
• Mobile apps
• Sensors
• Survey response
• Emails
• Revenue management
• Claims
• EMRs
• ICD 9-10
• Meaningful use
• Lab/radiology notes
• P4P reporting
• Quality reporting
• Clinical quality measures
• Transcription
• Population health mgmt
Billions of
daily interactions
Millions
of daily
transactions
Enterprise information that comes
from line of business systems that
provide structured database
information that is used to run the
business
Global information that comes
from internal and external
unstructured sources that is used
to gain insight on the business
drivers
&
10. SCENARIOS WHERE HEALTHCARE ANALYTICS
CAN BRING COST SAVINGS
Identifying cost effective ways of
treating patient through
comparative analyses
Analyzing disease patterns
Monitoring disease outbreaks
Aid in vaccine development and
Population safety measures
1
2
Analyse patient data from E.H.R
and several unstructured sources,
Financial data, genomic data
determine risk of disease
recurrence., hospitalization
3
Conducting genomic analysis cost
Effectively and integrating
Genomic information into patient
Diagnosis and treatment
4
HEALTHCA
RE
PROCESSES
Clinical Operations
Public Health
Evidence Based
Medicine
Genomic Analysis
11. APPLYING ANALYTICS IN HEALTHCARE SETTINGS
DELIVERS A DATA-DRIVEN ACTIONABLE
APPROACH TO TREATING DISEASES
A USE CASE ON DEVELOPING A TREATMENT APPROACH TO DIABETES
Obtaining generic
population level data on
diabetes
Localizing
context to
diabetes
patients
visiting a
treatment
center
Identify
diabetic
patients with
a high chance
of
hospitalizatio
n
Organize hospital
resources to
effectively deliver
care management
and avoid
hospitalization
• National
Prevalence for
Diabetes is 8.3%
• Hypertension is a
major co-
morbidity for
diabetes
• 35,000
individuals suffer
from diabetes in
our region
1000 diabetes
patients visit our
center every year
Total cost of
treating patients per
year is $7,000
Cost increased by
15% over last year
Assign patient level
risk scores on
hospital sample to
develop an evidence
based prediction
model to determine
potential admits
next year
Prioritize patients by
risk score and
allocate care
management
resources to
address at risk
patients & take
steps to prevent
hospitalization
12. USE CASE : AN APPROACH FOR PREDICTING
HOSPITAL ADMISSION RISK FOR DIABETIC
PATIENTS
• Local patient data
• Regional and
national data sets
• Device data
• Patient engagement
data
• Genomic,
Environmental data
• Activity based
costing data
Data Warehouse
Workload
1
Workload
2
Workload
3
User Defined
Classification
& Association Rules
Regression
Decision Tree
Clustering
Pattern Discovery
Techniques and Tools
Visualization Output
Plasma
glucose
BMI Readmit
risk
<127.5 <26.5 No risk
<157.5 >26.5 High API enabled
transfer of
clinical
workflowE.H.R
Clinical Apps
Ordering, Supply
Refills
Improved Diagnosis
Care Management
Altered treatment
programs
Clinical and Operational
Outcomes
SQL Querying
HIVE
R Studio
13. EVOLUTION OF ANALYTICS IN A HEALTHCARE
PROVIDER SETTING AND CAPABILITY
PRIORITIES IN ANALYTICS
STAGE 1
Rookie
• Monitor
dashboards
• Receive
patient
data reports
• Visualize
patient
data
STAGE 2
Dabbler
Analyze past
patient
behavior
• Perform ad hoc
data analysis
• Develop 360-
degree
view of patients
0
10
20
30
40
50
60
70
80
90
100
• Build models
Incorporate
machine
learning
techniques
• Identify
patient risks
and
opportunities
• Real time
prescriptive
analytics
• Provide point-of-
care
decision support
STAGE 3
Pros
STAGE 4
Gurus
14. EMERGING TRENDS IN HEALTHCARE
ANALYTICS ADOPTION
INTEGRATING CLINICAL,
FINANCIAL AND QUALITY
DATA TO DELIVER VALUE
BASED CARE
1
IMPROVING QUALITY OF
REMOTE CARE DELIVERY
THROUGH ANALYTICS
2
IMPROVING PATIENT
ENGAGEMENT AND STAFF
RESPONSE
3 DEVELOPING PERSONALIZED
TREATMENTS AND
THERAPEUTICS
4
Kaiser Permanente – sepsis risk
Max Hospitals- Deep Venous Thrombosis
Narayana Health Telemedicine e-Health Cen
Remote Care Analytics Dashboard
Lucile Packard Children’s Hospital
Operating Room Scheduling Dashboard
Moffitt Cancer Center Gene Expression Based
Radiosensitivity Index for Cancer
15. PROMINENT CHALLENGES IN DEPLOYING
ANALYTICS IN HEALTHCARE
Effective integration of
data from multiple
sources for sensemaking
Standardization of clinical
ontologies across clinical
management platforms
Mitigating data security
and privacy concerns
around patient data
Need for healthcare
specific analytics solutions
to improve veracity
HEALTHCARE
ANALYTICS
16. A HOST OF TOOLS FOR HEALTHCARE
PROVIDERS TO MAKE SENSE OF DATA AT
ALL TIMES
16
Healthcare
Analytics
Toolkit
Healthcare Data
Programming
Data Mining
File Distribution,
Processing and
configuration
Infrastructure
Databases
BI Tools & Visualization
17. FUTURE DIRECTIONS FOR ANALYTICS IN
HEALTHCARE
PRESCRIPTIVE ANALYTICS WOULD BECOME
INCREASINGLY PROMINENT IN HOSPITAL
OPERATIONS
Provide “in-cotext”, real time interpretation of
scenarios designed through predictive analytics:
Adjusting resource allocation
STARTUPS ENGAGING WITH HEALTHCARE
ORGANIZATIONS TO DESIGN CUSTOM
PREDICTIVE ANALYTICS SOLUTIONS FOR DISEASE
MANAGEMENT
2
Oncora Medical is working with hospitals to improve
real time treatments for radiation oncology
3
INTEGRATION OF HETEROGENOUS DATA
SOURCES
TO DELIVER EVIDENCE BASED MEDICINE
1
Integration of EMR, genomic data, wearable data,
epidemiological data with social and behavioural data
20. HOW CAN HOSPITALS ADOPT AN ANALYTICS APPROACH
Concept
Statement
Proposal Methodology Deployment
Determine the
need by mapping
the situation to the
4 V’s
What is the
problem being
addressed?
Why take an
analytics approach
?
Variable selection
Platform and Tools
Analytical techniques
Association, Results
Expected
Evaluation
Validation Testing
First cut at
establishing the
need for a project
involving analytics
Expand on the
concept note to
highlight the key
questions and
justify the costs
involved in
analytics
implementations
Break down the broad
questions into
actionable objectives
and apply the right
kind of analytical
tools
Break down the broad
questions into
actionable objectives
and map the kind of
tools and platforms to
use
21. EMERGING TRENDS IN ADOPTION OF
HEALTHCARE ANALYTICS
INTEGRATING CLINICAL, FINANCIAL
AND QUALITY DATA TO DELIVER VALUE
BASED CARE
IMPROVING QUALITY OF REMOTE CARE
DELIVERY THROUGH ANALYTICS
DASHBOARDS
EMPLOYING ANALYTICS TO IMPROVE
PATIENT ENGAGEMENT
1 2
Greater than 64% of Hospital Executives
believe that implementing analytics
would improve health outcomes and
support value based care
Best Practice:
• Kaiser Permanente, integrated clinical, E.H.R
data and operational kpis to predict potential
sepsis risk in patients and advance treatment
• Max Hospitals, India deployed analytics to detect
patients with risk for acquired Deep Venous
Thrombosis
Shortage of doctors,particularly in
developing countries is causing hospitals
to depend more on analytics dashboards
to determine availability of paramedical
staff and evaluate treatments
Best Practice :
Narayana Health partnered with Hewlett
Packard to develop the eHealth Center, which used
Analytics dashboards to determine disease spread in
Region and define treatment options based on historical
Data.
3
Analytics is being used to address
chronically ill patients by processing
data streamed from patient wearables to
determine emergency response and
patient alerts/communications
Fact : Critical patients account for 78 percent of
all healthcare spending,81 percent of in-patient
EMPLOYING ANALYTICS TO DEVELOP
PERSONALIZED TREATMENTS AND
THERAPEUTICS
4
Genomic , pharmacological and
conventional diagnostic data are being
integrated to develop personalized
therapeutics and treatment options for
cancerBest Practice :
HPE developed an operating room scheduling
dashboard, that captured data on intensive care
patients from their electronic records and sensors
attached to vital sign monitors at Lucile Packard Hospital
and helped reduce casualities.
Best Practice :
Moffit Cancer Center developed a gene
expression based radio sensitivity Index that
accurately predicts the outcomes of radiation
therapy for various cancers across patient strata.
22. THE FOUR V’S FOR HEALTHCARE TOGETHER
DEFINE THE IMPORTANCE OF ANALYTICS IN
HEALTHCARE
Volume
• The volume of healthcare data is expected to grow 50 fold from 500 petabytes to 25,000
petabytes by 2020
• Primary contributors to the data volume would include high resolution MRI scans, CT
Scans and PET scans
• Data volumes are expected to increase primarily due to government mandates to store
patient data for the longest periods possible
• High resolution healthcare scans are also expected to increase the data volume
Variety
• The variety of data includes text, images, videos
• The primary sources for data are expected to be patient records, patient wearables,
high throughput sequencing data from genomics experiments
Velocity
• Speed at which data is generated from a patient interaction or the rate at which
biomedical data is generated
• Shift from static data like X-Rays, EMRs to real time data from wearable monitoring and
genome sequencers
Value
• Operational efficiencies, to reduce costs, waste, and fraud through more efficient
methods for data integration,
management, analysis, and service delivery.
• Business process enhancements, to find new ways of delivering care while efficiently
allocating services to enable sustainable management of the population health
23. KEY CHALLENGES TO APPLYING ANALYTICS IN
HEALTHCARE
•Analytics solutions
specific to
healthcare will be
necessary to
improve specificity
and veracity of
healthcare
outcomes
•Security threats
challenge the
ability to facilitate
information
exchange and use
open source
software to analyse
proprietary patient
data.
•Currently high
blood pressure can
be expressed in
127 terms.
Integrating data
from genomic
expression studies
with healthcare
records and
standardize
medical ontologies
is a critical
challenge
•Intepreting
structured data and
unstructured data
consistently,as
most of the data
generated is
managed for size
through Electronic
health records and
genomic data
platforms.
Effective
interpretation of
healthcare and
life sciences
data
Standardizing
clinical
ontologies
Lack of
comprehensive
healthcare
specific analytics
solutions .
Threats of data
breaches
and siloed
departmental
data
24. BLOCKCHAIN IN HEALTHCARE TO IMPROVE
EFFECTIVE INTEGRATION OF HEALTHCARE
INFORMATION
Source: Deloitte