Objectives

 At the end of this session the learner should be able to :

• Define health analytics

• List benefits of health analytics
• Mention types of data analytics
• Discuss sources of health care data

1
Chapter 1:Overview of health analytics
Definition

• Health analytics is rapidly emerging as a key and distinct

application of health information technology.
• The key objective of health analytics is to gain insight for
making informed healthcare decisions.

2
Chapter1: Overview of health analytics
• Definition cont…

 Health analytics is systematic use of data and related clinical

and business (C&B) insights developed through applied
analytical disciplines such as statistical, contextual,
quantitative, predictive, and cognitive spectrums to drive fact-
based decision making for planning, management,

measurement and learning for health care. 

3
 Health analytics
Definition cont…
• Health analytics is the use of data, information technology,
statistical analysis, quantitative methods, and mathematical
computer-based models to help health care providers gain
improved insight about patients and make better, fact-based
decisions.
• Health analytics as a “way of transforming data into actions
through analysis and insights in the context of the health care
decision making and problem solving

4
 Health analytics
• Health analytics can assist administrators, case managers,
clinicians, and even patients in better understanding
healthcare processes and outcomes across multiple facilities,
providers, stakeholders, and regulatory agencies.

5
Why do we need health analytics?
• Data analytics is an essential resource for decision-making.

• Involves the use of data, analysis, and modeling to arrive at a

solution to a problem or to identify a new opportunities.

• Analytics plays a more essential role for healthcare than it

might in financial and business markets.

– Effective use of analytics in the healthcare industry can improve

current care but more importantly can facilitate preventive care

6
Why do we need health analytics?
• HA can answer the following questions:
– What happened in the past and why?

– What could happen in the future and with what certainty?

– What actions can be taken now to control events in the

future?

7
Why do we need health analytics?
• Is there a cancer presence in this X-ray image?

• How many nurses do we need during the upcoming

month given the patients admission pattern we had last
year and the number of patients admitted at the Out
Patient Department (OPD) in the last month?

• How can we optimize the OPD processes to reduce

waiting times?

8
 Benefits of HA
• Interpret data to inform future interactions with patients,
consumers, and populations.

• Uncover the root cause of an epidemic.

• Aid in predictive modeling by interpreting patient data

from previous interactions.

• Improve quality of clinical care by increasing healthcare

organizations’ access to patient data.
9
 Benefits of HA
• Improve/optimize clinical workflow across healthcare
organizations.

• Gain market share by improving patient care and reputation.

10
 Types of Health Analytics
• Descriptive analytics: is the easiest level to understand and
use.

– Works by categorizing, characterizing, aggregating and

classifying data to be converted to useful information to help
healthcare professionals understand and analyze decisions.

– Answer: What happened?

11
 Types of Health Analytics
• Common statistics are used: the number of laboratory tests,
the average age of patients, or the average length of stay in
the hospital for patients with a particular diagnosis.

• Descriptive analytics are often presented as pie charts, bar or

column charts, tables, or written narratives.

12
 Types of Health Analytics
• Diagnostics analytics:

– Needs extensive exploration and directed analysis of the

existing healthcare data.

– Use tools such as visualization techniques to discover the

root causes of a problem.

– Answer: the question “Why did it happen?”.

13
 Types of Health Analytics
• Predictive analytics: works in a more complex way than simple
descriptive analytics.

– Focuses on the use of information rather than simple data by

examining existing past readings and indicators to predict future
performance.

– Advanced techniques such as machine learning and data mining

allow predictive analytics to detect hidden patterns in large
quantities of data.

14
 Types of Health Analytics
• Predictive analytics help health professional to answer
question such as:
– Which drugs should I use for treatment?
– Which of my patients are most likely to get well (based on a protocol)?
– When one drug fails, which others are most likely to fail too?

• Answer: What could happen?

15
 Types of Health Analytics
• Prescriptive analytics: optimize clinical, financial, and other
outcomes.
– Comes into action when decisions have to be made regarding a
wide range of feasible alternatives.
– Enables executives not only to look into consequences and/or
expected results of their decisions and see the opportunities or
problems
– Answer: What should we do?

16
 Types of Health Analytics
• Discovery (Wisdom) analytics: utilizes knowledge about
knowledge, or wisdom:

– To discover new medications or alternative treatments or

– To detect new symptoms, signs or diseases.

• The Data–Information–Knowledge–Wisdom hierarchy

17
 Practical Application of HDA
– Data Analytics for Pharmaceutical Discoveries

– Clinical Decision Support Systems: design to assist

clinicians at the point of care… uses data analytics to
reduce errors and assist in the diagnostic process.

– Improve patient Wellness: can be used by healthcare

organization to direct their patients to maintain
healthy habits and identify changes in life --- improve
health based on physical condition.
18
 Administrative data

• It is the data that organizations collect about their operations.

• It includes data for routine operations,
• It is frequently used to assess how well an organization is
achieving its intended goals.

19
 Administrative data

•  It is often used only for program operations, such as service

delivery
• It helps to improve the design of future polices .

20
 Clinical Data
• Clinical data is a staple resource for most health and
medical research.
• Clinical data is either collected during the course of ongoing
patient care or as part of a formal clinical trial program. 
 Clinical data falls into six major types:
• Electronic health records
• Administrative data
• Claims data
• Patient / Disease registries
• Health surveys
• Clinical trials data

21
Clinical Data
Electronic Health Record
• The purest type of electronic clinical data which is
obtained at the point of care at a medical facility,
hospital, clinic or practice.
• The data collected includes administrative and
demographic information, diagnosis, treatment,
prescription drugs, laboratory tests, physiologic
monitoring data, hospitalization, patient insurance, etc.

22
 Administrative data

• Often associated with electronic health records, these are

primarily hospital discharge data reported to a government
agency like AHRQ(Agency for Healthcare Research & Quality).

 Healthcare Cost & Utilization Project (H-CUP) HCUP net is a

free, on-line query system based on data from the Healthcare
Cost and Utilization Project (HCUP).
 It provides access to health statistics and information on
hospital inpatient and emergency department utilization.

23
 Claims data
• Claims data describe the billable interactions (insurance
claims) between insured patients and the healthcare delivery
system.
• Claims data falls into four general categories: inpatient,
outpatient, pharmacy, and enrollment.
• The sources of claims data can be obtained from the
government (e.g., Medicare) and/or commercial health firms
(e.g., United HealthCare).

24
 Patient / Disease Registries

• Disease registries are clinical information systems that track a

narrow range of key data for certain chronic conditions such
as Alzheimer's Disease, cancer, diabetes, heart disease, and
asthma.
• Registries often provide critical information for managing
patient conditions.

25
 Patient / Disease Registries
• National Program of Cancer Registries

• CDC provides support for states and countries to maintain

registries that provide high-quality data.
• Data collected by local cancer registries enable public health
professionals to understand and address the cancer burden
more effectively.

26
 Patient / Disease Registries
• National Trauma Data Bank The National Trauma Data Bank®
(NTDB) is the largest aggregation of trauma registry data ever
assembled.
• The goal of the NTDB is to inform the medical community, the
public, and decision makers about a wide variety of issues
that characterize the current state of care for injured persons.

27
 Health Surveys

• National surveys of the most common chronic conditions are

generally conducted to provide prevalence estimates.
• National surveys are one of the few types of data collected
specifically for research purposes, thus making it more widely
accessible.  
• Medicare Current Beneficiary Survey

• The Medicare Current Beneficiary Survey (MCBS) is a continuous,

multipurpose survey of a nationally representative sample of the
Medicare population.

28
 Clinical Trials Registries and Databases

• ClinicalTrials.gov
o Information on publicly and privately supported
clinical studies from around the world.
• Cochrane Library
o Trials database, CENTRAL, is component of
Cochrane Library
o Reports of randomized and quasi-randomized
clinical trials taken from Medline, Embase, and
elsewhere.
29
Clinical Trials Registries and Databases

• European Union Clinical Trials Database

o Protocol and results information on
interventional clinical trials conducted in the
EU.
o Good source of pediatric drug development
trials.
• CenterWatch
o Portal for actively recruiting pharmaceutical
industry-sponsored clinical trials..
30
 Clinical Research Datasets

• Clinical research data may be available through national or

discipline-specific organizations.  Level of access is likely
restricted but available through proper channels.

• Proprietary research data may also be available through

individual agreements with private companies.

31
 External data

• External data is data that is stored outside the current

database.

• External data sources include benchmarks, publicly available

data sets, as well as data from government agencies and the

WHO.

32
 Data Analysis Tools

• Commonly used software for data analysis include:

• ArcGIS Desktop   
http://www.esri.com/software/arcgis/arcview
geospatial data analysis tool
• SPSS*    http://www-01.ibm.com/software/analytics/spss/
predictive analytics software

33
Data Analysis Tools

• Stata    http://www.stata.com
data analysis and statistical software
• R*     http://cran.r-project.org/
a freely available language and environment for statistical
computing and graphics which provides a wide variety of
statistical and graphical techniques: linear and nonlinear
modelling, statistical tests, time series analysis, classification,
clustering, etc.
• Epi Info  http://wwwn.cdc.gov/epiinfo/

34
 Common Representations of data in HISs
• Understanding the common clinical representations (data
standards) of data in healthcare systems include:

– ICD-10,
– SNOMED,
– LOINC,
– drug vocabularies (e.g., RxNorm),
– clinical data standards and other common representations

• Principal informatics component necessary for information

flow through the HS infrastructure.

35
 Common Representations of data in HISs
• Data must be collected and maintained in a standardized
format, using uniform definitions, in order to use it in health
analytics.

• Lack of common representation of data is a great challenging

in the integration of clinical data for further health analysis.

36
 Common Representations of data in HISs
• Health care data standardization involves the following:

– Definition of data elements: determination of the data content

to be collected and exchanged.

– Data interchange formats: standard formats for electronically

encoding the data elements

37
Common Representations of data in HISs
– Terminologies:
• The medical terms and concepts used to describe, classify, and
code the data elements and data expression languages
• Syntax that describe the relationships among the
terms/concepts.

– Knowledge Representation: standard methods for

electronically representing:
• Medical literature
• Clinical guidelines, and the like for decision support.

38
 Common Representations of data in HISs
• Common standards:
– International Classification of Diseases, 10th Edition, Clinical Modified
(ICD-10-CM):

– Current Procedure Terminology (CPT) : this code includes more than

8,000 five-character alphanumeric codes describing services provided
to patients by physicians, paraprofessionals, therapists, and others.

– International Classification of Diseases, 10th Edition, Procedural

Coding System (ICD-10-PCS) : is a 130,000 alphanumeric code set used
by hospitals to describe surgical procedures

39
 Common Representations of data in HISs
• Common standards:
– Health Care Procedural Coding System, Level II (HCPCS Level II) :
developed originally for use to report procedures and bill for supplies.

– Code on Dental Procedures and Nomenclature (CDT): the five-

character codes start with the letter D and used to be the dental
section of HCPCS Level II.

– National Drug Codes (NDC) : the Federal Drug Administration's (FDA)

code set is used to track and report all packages of drugs

40
 Strategies for Optimizing Data Quality
Dimensions of data quality
• Validity : data measure what they are supposed to measure
• Reliability :Every one defines , measures, and collects data
the same way
• Completeness: data include all of the values needed to
calculate indicators
• Timeliness: Data are up to date .information is available on
time.
• Integrity :Data are true .the values are safe from deliberate
bias and have not been changed for political or personal
reasons
• Precision: The data have sufficient detail; in this case the
“accuracy” of the data refers to the fineness of measurement
units.
41
 Strategies for Optimizing Data Quality
• The issue of data quality (DQ) has become more complex and
controversial as a consequence of big data.
• Improving and maintaining high data quality is a central goal
of healthcare analytics, composed of three phases:
1. State reconstruction: aimed at collecting contextual information on
healthcare processes and services, ,quality issues and corresponding
costs.
2. Assessment/measurement: measures the quality of data collections
along relevant quality dimensions.
3. Improvement: concerns the selection of the steps, strategies, and
techniques for reaching new data quality targets

42
 Strategies for Optimizing Data Quality
• In the improvement steps, there are two general types of
strategies:
– Data-driven: strategies improve the quality of data by directly
modifying the value of data.

– Process-driven: improve quality by redesigning the processes that

create or modify data.

43
 Strategies for Optimizing Data Quality
• The following improvement techniques can be applied in data-
driven strategies:
• Acquisition of new data: improves data by acquiring higher-
quality data to replace the values that raise quality problems.

• Standardization (or normalization): replaces or complements

nonstandard data values with corresponding values that
comply with the standard.

• Record linkage: identifies that data representations in two (or

multiple) tables that might refer to the same real-world object.

44
 Strategies for Optimizing Data Quality

• Data and schema integration: define a unified view of the

data provided by heterogeneous data sources.

• Source trustworthiness: selects data sources on the basis

of the quality of their data;

• Error localization and correction: which identify and

eliminate data quality errors by detecting the records
that do not satisfy a given set of quality rules.

45
 Quiz
• List and explain at least three dimension of
data quality?
• List two strategies in data quality
improvement step?

46