discussion
Chapter 1 defines the origin of healthcare informatics.
Chapters 1 and 2 review basic information on HC Informatics, data and knowledge. But not all informatics use in healthcare is easy. What makes Informatics in HC difficult?
Chapter 1: Overview of Health Informatics
Robert Hoyt MD
Elmer V Bernstam MD
William R Hersh MD
After reviewing these slides, the viewer should be able to:
State the definition and origin of health informatics
Identify the drivers behind health informatics
Describe the key players involved in health informatics
State the impact of the HITECH Act and Affordable Care Act on health informatics in the United States
List the barriers to health information technology (HIT) adoption
Describe educational and career opportunities in health informatics
Learning Objectives
With the advent of the internet, high speed computers, voice recognition, mobile technology, etc. healthcare professionals today have many more tools at their disposal
But, technology is advancing faster than healthcare professionals can assimilate it into practice
Therefore, there is a new need for education and translation of emerging technologies and the data/information they generate into healthcare
Introduction
There are lots of data but less information, knowledge and wisdom. Information is data with meaning, e.g., the number 10 could be anything but a prostate specific antigen (PSA) of 10 is important information. Humans provide knowledge and wisdom
Information Hierarchy
The advent of electronic health records (EHRs) and multiple other healthcare information systems provided the ability and the need to collate and analyze large amounts of data to improve health and financial decisions.
As genetic information collection grows, datasets are huge (big data) and part of EHRs
Sources of Healthcare Data
All large healthcare organizations will collect and analyze a variety of clinical, financial and administrative data to make wise clinical and business decisions
Therefore, data analytics is very important
Mining the Data
Health informatics is the field of information science concerned with management of healthcare data and information through the application of computers and other technologies
In reality, it is more about applying information in the healthcare field than it is about technology
Technology can generate, transport and analyze useful healthcare data
“Technology is the transportation, not the destination”
Dr. Safran
Definitions
Health informatics is also known as clinical informatics, medical informatics and biomedical informatics leading to confusion
The most inclusive term is biomedical informatics because it encompasses bioinformatics as well as medical, dental, nursing, public health, pharmacy, medical imaging and veterinary informatics
Bioinformatics is concerned with biological data, particularly DNA and genomic information
Definitions
American Medical Informatics Association Perspective
www.amia.org
©AMIA 2013
Health information technology (HIT or health IT) is defined as the application of computers and technology in healthcare settings
Health information management (HIM) traditionally focused on the paper medical record and coding. With the advent of the electronic health record HIM specialists now have to deal with a new set of issues, such as privacy (HIPAA) and legal implications of electronic data
Other Definitions
Healthcare has been slow to adopt technology, compared to other industries such as banking
Health informatics emphasizes information brokerage; the sharing of a variety of information back and forth between people and healthcare entities
Informaticians (or informaticists) harness the power of information technology to expedite the transfer and analysis of data, leading to improved efficiencies and knowledge
Background
Informatics training must be expansive to include IT knowledge about networks and systems, usability, process re-engineering, workflow analysis and redesign, quality improvement, project management, leadership, teamwork, implementation and training
Many of the newest technologies are interrelated such as EHRs, patient portals, mobile technology, telemedicine, etc.
Background
Increase healthcare efficiency and productivity
Improve healthcare quality (patient outcomes) resulting in improved patient safety
Reduce healthcare costs
Improve healthcare access with technologies such as telemedicine and online scheduling
Improve coordination and continuity of care
Improve medical education of clinicians and patients
Standardize medical care
Driving Forces Behind Health Informatics
Technological innovations appear at a startling pace as stated by Moore’s Law:
“the number of transistors on a chip will double approximately every two years.” Gordon Moore, co-founder Intel Corporation 1965
The healthcare field is also subject to “disruptive innovations (technologies)” which are innovations that just appear and soon take over mainstream technologies, e.g., smartphones, LED lights & solid state hard drives
Technology Freight Train
HealthData.gov makes federal datasets available to healthcare organizations, developers and researchers
Datasets are available in categories: health, state, national, Medicare, hospital, quality, community and inpatient
Users can use filters: data type, subject, agency, date updated, coverage period, collection frequency, geographic area, release date and output format
Avalanche of Healthcare Data
Healthdata.gov
Community Health Status Indicators
Child Growth Charts
Health Data Interactive
Behavioral Risk Factor Surveillance System (CDC)
Births (CDC)
Mortality (CDC)
Fourth National Survey of Older Americans
Health Indicators Warehouse
Population (census) (CDC)
Cancer Profiles
Archimedes data modeling and analytics tool
Computers: the first general purpose computer (ENIAC)(1946) required 1,000 sq. ft. of floor space
Term “medical informatics” appeared in the 1960s
Computer technologies and early EHRs appeared in 1970s at the VA and Massachusetts General Hospital
MEDLINE reorganized medical literature searches (1960s)
Artificial intelligence in medicine appeared in 1970s
Internet appeared in 1969 as Defense project; World Wide Web in about 1990
Historical Highlights
Mobile technology. The PalmPilot PDA appeared in 1996 as the first truly popular handheld computing device, but rapidly evolved to the smartphone
Human Genome Project. Complete human genome sequencing was finished in 2003. Now comes the hard part, making sense of the huge datasets
Data from large databases will likely change the way we practice medicine in the future
Historical Highlights
Key Players Involved with HIT
Physicians and nurses
Patients
Hospitals and healthcare organizations
Support staff
Medical educators
Public health
HIT vendors
Insurance companies
Federal and state governments
Medical research
Organizations Involved with HIT
Institute of Medicine
Department of Health and Human Services (HHS)
Office of the National Coordinator (ONC)
Agency for Healthcare Research and Quality (AHRQ)
HHS (cont.)
Centers for Medicare and Medicaid (CMS)
Centers for Disease Control and Prevention (CDC)
Health Resources and Services Administration (HRSA)
National Institute of Standards and Technology (NIST)
* Academic
* Federal government
Evaluates policy relevant to healthcare and provides feedback to the Federal Government and the public
In their two pioneering books To Err is Human (1999) and Crossing the Quality Chasm (2001), they reported approximately 98,000 deaths occur yearly in the US due to medical errors. It is their belief that adopting health information technology will help promote “safe, effective, patient centered, timely, efficient and equitable medical care”
They recommended 12 types of HIT that would help move healthcare into the 21st Century
Institute of Medicine (IOM)
American Recovery and Reinvestment Act (ARRA) 2009
ARRA had five broad goals: (a) improve medical quality, patient safety, healthcare efficiency and reduce health disparities; (b) engage patients and families; (c) improve care coordination; (d) ensure adequate privacy and security of personal health information; (e) improve population and public health
From ARRA came the Health Information Technology for Economic and Clinical Health Act (HITECH)
US Federal Government
The HITECH Act included financial support for:
Reimbursement for use of certified EHRs
State health information exchange
Comparative effectiveness research
62 Regional Extension Centers to support HIT
Health Informatics curricula at the community college and university level
Beacon Communities to highlight and share “best HIT practices”
Other less well-known programs
US Federal Government
The Patient Protection and Affordable Care Act of 2010
Expanded Medicaid coverage for the uninsured
Created the Patient Centered Outcomes Research Initiative (PCORI)
Created the CMS Innovation Center that will evaluate new healthcare delivery models
Created a Readmission Reduction Program that will penalize hospitals with too many readmissions
Other less well-publicized programs
US Federal Government
Reports directly to Secretary of HHS. Strategic Plan (2015-2020):
Goal 1: Advance person-centered and self-managed health
Goal 2: Transform healthcare delivery and community health
Goal 3: Foster research, scientific knowledge and innovation
Goal 4: Enhance nation’s health IT and infrastructure
ONC established in 2015 the Health Information Technology Advisory Committee (HITAC)
Office of the National Coordinator for Health Information Technology (ONC)
Charged with improving the quality, safety, efficiency, and effectiveness of health care for all Americans
Supports medical research to include health IT
They support and maintain:
HIT Knowledge Library
National Resource Center for HIT
HIT Portfolio Program to study HIT impact
Multiple other related programs at http://healthit.ahrq.gov/health-it-tools-and-resources
Agency for Healthcare Research and Quality
An insurer for about 100 million Americans
CMS reimburses for “meaningful use” of certified EHRs by clinicians and hospitals under Medicare or Medicaid
As of April 2014 they have paid out about $22 billion to clinicians and hospitals as part of the HITECH Act meaningful use program
They have a CMS Data Navigator that provides healthcare data from over 300 federal sources
Centers for Medicare and Medicaid Services (CMS)
They support the Public Health Information Network
They use HIT to improve and maintain public health using a variety of surveillance programs
They have a Data and Statistics section and a Health Data Interactive program
They have a variety of HIT-related projects, such as text messaging health education to patients
Centers for Disease Control and Prevention (CDC)
The United States is not unique. Other developed and developing countries share the same concern about the rise in chronic diseases, such as diabetes, and the high price tag generated
Most countries have implemented electronic health records and other technologies in a hope to better track chronic diseases. Paper charts are grossly inadequate for public or population health
Most countries are teaching Health Informatics
International Health Informatics
Not enough time
Not enough expertise, as few have formal training in informatics
Not enough financial resources
Lack of interoperability between technologies
Inadequate cost and return on investment data
Privacy concerns
New legal concerns: who owns the electronic data?
Need for behavioral changes: about 50% of staff will be slow to adopt any new changes
Barriers to HIT Adoption
Hype versus Fact: there have been many overly optimistic predictions by vendors, academicians, the government and early adopters that HIT will revolutionize healthcare
While we are still early in the game, the reviews are mixed whether adoption today has improved quality, safety or reduced medical costs
The most recent review by the RAND Corp. in 2014 was positive about HIT, but was funded by ONC
Barriers to HIT Adoption
Sharp rise in Health Informatics courses offered over the past 5-10 years; assisted by the HITECH Act
Most common degree is a Masters level but PhD, associate, undergraduate and certificate programs are widely available
Many programs are completely online
The AMIA.org web site hosts a majority of the available HI programs with a search engine and filters
Health Informatics Programs
Founded in 1989 and now has about 5000 members
Largely represents physicians and researchers involved with the biomedical sciences
They have about 20 working groups that focus of all aspects of Health Informatics
Membership includes subscription to the Journal of the American Medical Informatics Association (JAMIA) and Applied Clinical Informatics (ACI)
American Medical Informatics Association (AMIA)
They have 50,000 individual and 570 corporate members
Provides multimedia educational material
Maintains a Health IT Body of Knowledge resource site
Annual meeting attracts over 40,000 attendees and 1,000 vendors in exhibition hall
The have a separate HIMSS Analytics section
Health Information and Management Systems Society (HIMSS)
Founded in 1928 primarily for paper-based medical record librarians
In 2016 they had 103,000 members
They focus on coding, health information management, privacy and analysis
With the advent of electronic health records, their role has been expanded
They maintain an HIT resource library
American Health Information Management Association (AHIMA)
Job postings have tripled since 2009 largely due to widespread adoption of EHRs and the necessary skill set for implementation, project management, workflow redesign, training, etc.
In reality what most HIT vendors and healthcare organizations are looking for individuals with good IT and clinical skills and involvement in IT projects. In other words, someone ready to hit the ground running
Job sites can be found on the AMIA, HIMSS, AHIMA and the HealthInformaticsForum.org web sites
Health Informatics Careers
There are about 3 million nurses in the US (2016 Bureau of Labor) so a large labor pool for an informatics education
Multiple nursing programs in the US offer a nursing informatics program with certification
There has been a certification program for nurse informaticians available since 1995 and in 2016 there were 2040 certified nurse informaticians (ANCC 2016 data)
Nurses are extremely valuable given their clinical experience and exposure to quality and project management as part of the nursing experience
Nurse Informaticians
Usually a physician or nurse who reports to the CIO, or CEO
CMIOs are less technology oriented and more tasked to help implement newer technologies and gain staff acceptance
The are therefore involved with training and adoption strategies, as well as the development of a variety of policies to include privacy/security
Most have a Master’s degree in an information science and often are Certified Professional in Health Information Management Systems (CPHIMS)
Chief Medical Informatics Officer
Smaller organizations may have a “go to” nurse or physician who is an early adopter and has much more IT experience; a clinician informatician
In 2013 physicians could become board certified in Clinical Informatics for the first time. Details are on the AMIA web site
AMIA is working on an Advanced Interprofessional Informatics Certification that non-physicians can attain and be similar to board certification in Clinical Informatics
Clinician Informatician
Resources Listed in the Textbook:
Books
Journals
E-journals
E-newsletters
Blogs
Health Informatics Resources
Health Informatics is a relatively new and exciting field with many new educational and job opportunities
Research in health informatics is being published at an increasing rate so hopefully new approaches and tools will be evaluated more often and more objectively.
Although technology holds great promise, it is not the solution for every problem facing medicine today. We must continue to focus on improved patient care as the single most important goal of this new field.
Conclusions
Chapter 2: Healthcare Data, Information and Knowledge
Elmer Bernstam MD
Todd Johnson PhD
Trevor Cohen MD PhD
After reviewing these slides the viewer should be able to:
Define data, information, and knowledge
Understand how vocabularies convert data to information
Describe methods that convert information to knowledge
Distinguish informatics from other computational disciplines, particularly computer science
Describe the differences between data-centric and information-centric technology
Learning Objectives
Data are symbols or observations reflecting differences in the world. Example = 250.00 (Note: data is the plural of datum)
Information is data with meaning. Example = ICD-9 code of 250.00 means type 2 diabetes
Knowledge is information that is justifiably believed to be true. Example = obese patients are more likely to develop type 2 diabetes
Introduction
Computers generate and analyze binary information: zero (off) and one (on). Each zero or one is a bit; a series of 8 bits is a byte. Note that these bits and bytes have no meaning per se
Bits can occur as various data types
Integers such as 345 or 669988
Floating point numbers such as 14.1 or -1.23
Characters such as a or z
Character strings such as “hello” or “goodbye”
Introduction
Data can be aggregated into a variety of formats such as image files (JPG, GIG, PNG), text files, sound files (WAV, MP3) or video files (WMV, MP4)
Recognize that these formats do not define what information is available, just the category format
Data are the domain of computer scientists, but information is the domain of informatics and informaticians
Introduction
Information retrieval involves both computer science (data) and informatics (information). See image below
Introduction
Computer data not only lacks meaning, but must includes dates and other qualifiers to gain significance. For example, blood glucose = 127. Was that mg/dl, was the sample drawn fasting, etc.
Everything must be standardized, otherwise computer B will not understand data transmitted from computer A (i.e. data won’t be interoperable)
Data and Information
A modern way to convert medical information to knowledge is to use a clinical data warehouse (CDW)
EHRs are now a huge source of healthcare data and information. They contain both structured (coded e.g. ICD-9 codes) and unstructured text (free text or natural language)
Interpreting free text requires natural language processing (NLP)
Information to Knowledge
Data from EHRs, Radiology, Pathology, etc. are copied into a staging database where they are cleaned and loaded into another common database and associated with meta data (data that describes data). ICD-type data is an example of meta data
Tools can be applied to the data in the CDW, such as simple descriptive analytics that reports the number of patients with breast cancer, their age, menopausal status, etc. More about this in chapter 3
CDWs do a better job of analyzing and reporting aggregate healthcare data than the average EHR, which tends to focus on the individual
Clinical Data Warehouse
CDWs can be used to evaluate a critical clinical process, cost estimates and they can analyze potential solutions
CDWs are highly valuable for informatics and evidence based medical research
CDWs can help track infections and report trends to public health
Next slide shows a typical CDW schema
Clinical Data Warehouse
Clinical Data Warehouse
ETL = extract, transfer and load
Informatics for Integrating Biology and the Bedside (i2b2) is a Harvard project used by many other academic institutions in the US
The program is open source and modular and incorporates genomic and clinical information for research purposes
Data base consists of facts (diagnoses, lab results, etc.) queried by users and dimensions that describe the facts
With this model data can be aggregated from multiple hospitals
i2b2 platform
https://www.i2b2.org
i2b2 star schema
In order to extract concepts from free text in EHRs or CDWs several systems have been developed. See below
Concept Extraction
Concept Extractor Gold Standard Precision Recall F-score (F1)
cTAKES17 Mayo clinic 0.80 0.65 0.72
MetaMap20 NLM 500 articles 0.32 0.53 0.40
MEDLEE21 Proprietary 0.86 0.77 0.81
With other industries such as banking, data and information are much closer (smaller semantic gap).
For example, banking data such as $100.50 is close to an account balance of $100.50. It leaves little leeway for a different interpretation
In healthcare, there are subjective factors (“I feel sick”) that are difficult to measure and vary from patient to patient and physician to physician. Lab results are more objective and easier to interpret
What Makes Informatics Difficult?
What Makes Informatics Difficult?
It is difficult to model all of healthcare. View the HL7 RIM model on next slide
Biomedical information is difficult due to incomplete, imprecise, vague, inconsistent and uncertain information
Humans can adapt to this dynamic and vague information but computers can not. Clinical decision support in EHRs is precise, when in reality it might need to be flexible over time
HL7 version 3 RIM model
Health IT is an attractive solution to our troubled healthcare system, but is it realistic?
Other IT fields have experienced serious “ups and downs” such as artificial intelligence
There is a large gap between healthcare data generated and information (semantic gap)
Is it too early to expect EHRs and computerization to change healthcare?
Why Health IT Fails Sometimes
Computer scientists focus on data, while informaticists focus on information
There is a gap between healthcare data and information (semantic gap)
The transformation of information into knowledge is a primary goal of informaticists
Clinical data warehouses are increasing used to research clinical questions and generate knowledge from information
Conclusions
19