Using Aggregate Data to Help Public Health

“Public health is different than our personal health. Most people take for granted the role public health agencies play in our lives, but its primary emphasis is tracking disease data across the country in order to prevent a nationwide epidemic or pandemic. Nobody wants another bubonic plague, right?”
Article
John Grohol, e-patients.net, 13 November 2008

HIM and Health IT

“Health information management and health information technology are disciplines with completely different functions; however, the two disciplines are striving to find common ground with the emergence of increasing volumes of electronic data. HIM and health IT are finding that the scope and responsibilities of individual job functions are increasingly crossing department domains.
This convergence is occurring at different rates in different healthcare facilities, based on a variety of factors such as organizational size, culture, infrastructure, and degree of electronic health record (EHR) adoption. However, there is a universal need for alignment between the two disciplines to ensure that both business processes and technology are in place to advance successfully toward a fully functional EHR. This practice brief outlines how HIM and health IT can find common ground in an electronic healthcare environment.”
Article
AHIMA, Journal of AHIMA 79, no.11 (November–December 2008): 69-74

DOD grant explores mining health records data

“The Defense Department awarded a $100,000 grant to Teksouth Corp. to study ways that data in electronic health records could be structured to improve the analysis of disease and population health trends in the military.”
Article
Paul McCloskey, Government Health IT, 27 October 2008

Finding a Needle in a Haystack

“Some might call it “data mining on steroids.” But the organizer of an ambitious research project at Montefiore Medical Center in New York describes it as “asking clinically cogent questions of ragged data while respecting the need for user flexibility.”
No matter what you call it, the Clinical Looking Glass project, headed by Eran Bellin, M.D., is taking data mining to the next level. The application, 10 years in the making, is enabling some 250 physicians to conduct their own ad hoc research studies. Some are as simple as identifying all patients taking a drug that has been recalled. Others are far more complex, such as assessing whether a certain type of filter is beneficial to patients with blood clots.”
Article
Howard J. Anderson, Health Data Management, 1 October 2008

Prescription Data Used To Assess Consumers - No Privacy Unless You Pay Cash…

“This brings up one big issue, something I have been aware of for a while, collecting data for one purpose and being used for another, think this doesn’t happen, think again.  When you sign up for health insurance, you sign you life away for all this data to be collected and reviewed for the process of qualifying for health insurance. Ingenix is a division of United Healthcare and one company who does this with profits of over 1 billion last year.”
Article
The Medical Quack, 4 August 2008

Prescription Data Used To Assess Consumers

“Health and life insurance companies have access to a powerful new tool for evaluating whether to cover individual consumers: a health “credit report” drawn from databases containing prescription drug records on more than 200 million Americans.”
Article
Ellen Nakashima, Washington Post, 4 august 2008

Fingertip Health Care Histories

“That’s why Kerecz set up an electronic personal health record for each of her five children with Aetna, the family’s health insurer. The service lets her use her personal computer to access and update their medical records, giving her greater insight into ways to improve their care.”
Article
Greg Bordonaro, Hartford Business, 7 July 2008

E-Health 3.0: How Can The Semantic Web Change The World Of Internet Health Information?

“Access to online health information is something most individuals take for granted these days. Whether sifting through a million Google hits or a laborious visit to WebMD, most people with access to a computer have utilized the current online health tools. Just ten years ago, few would give credence to reputable health information posted on the Web. Even fewer of us would rely on it as a primary or secondary source of medical information. Yet, recent Pew research suggests that 8 in 10 Internet users go online for health information totaling eight million health searches on a typical day. While the depth of information on the Web has increased dramatically, the ability to access the right information has floundered in comparison. Contextual data retrieval is particularly critical with health information and by most accounts the Internet is a mess in this regard. The ground breaking idea of a new search paradigm known as Semantic Web may hold the promise of a cure.”
Article
Alex Trzebucki, Medical News Today, 13 June 2008

Online medical records offer convenience, may limit privacy

“When Mary Adams had a mammogram in October, she didn’t have to wait for a call from her doctor — or even a note in the mail — to get her results.
Instead, she got a message from her Cleveland Clinic doctor that her online health record had been updated. She logged onto MyChart, one of the nation’s first online sites for personal health records, and voilà, there were the results: Everything was normal.”
Article
Janet Kornblum, USA Today, 12 June 2008

Medicare prescription data will be scanned for harmful drug effects

“The Food and Drug Administration now has access to another major ingredient of its Sentinel project, intended to detect adverse drug effects by mining medical data.
The Centers for Medicare and Medicaid Services will make claims data from its Medicare Part D prescription drug program available to the FDA, researchers and others. Although the data will be anonymized, it can be linked to Medicare inpatient and outpatient claims records, enabling researchers to associate drugs and medical devices with their effects on health.”
Article
Nancy Ferris, Government Health IT, 22 May 2008

Privacy advocates seek to protect prescription information

“The Coalition for Patient Privacy and 25 of its member organizations are asking Congress not to pass an e-prescribing mandate unless it includes provisions for protecting the privacy of prescription information.
In a letter to lawmakers, the coalition said the sale of prescription information for data-mining purposes has been a reality for more than a decade. “Mandating e-prescribing without privacy provisions endorses and encourages the current practices,” the letter states. “It sets Americans up for even greater violations of their private health records in the future.”
Article
Nancy Ferris, Government Health IT, 13 May 2008

Swedish centre mines drug reaction data

“A Swedish monitoring centre is using data mining techniques to help identify adverse drug reactions based on Yellow Card patient records.
The Yellow Card is the UK’s Medicines and Healthcare products Regulatory Agency (MHRA) scheme, which has been used for over 40 years to collect information on suspected side effects from all types of medicines.”
Article
eHealth Europe, 23 April 2008

Realising the Knowledge Spiral in Healthcare: the role of Data Mining and Knowledge Management

Abstract:
Knowledge Management (KM) is an emerging business approach aimed at solving current problems such as competitiveness and the need to innovate which are faced by businesses today. The premise for the need for KM is based on a paradigm shift in the business environment where knowledge is central to organizational performance. Organizations trying to embrace KM have many tools, techniques and strategies at their disposal. A vital technique in KM is data mining which enables critical knowledge to be gained from the analysis of large amounts of data and information. The healthcare industry is a very information rich industry. The collecting of data and information permeate most, if not all areas of this industry; however, the healthcare industry has yet to fully embrace KM, let alone the new evolving techniques of data mining. In this paper, we demonstrate the ubiquitous benefits of data mining and KM to healthcare by highlighting their potential to enable and facilitate superior clinical practice and administrative management to ensue.
Specifically, we show how data mining can realize the knowledge spiral by effecting the four key transformations identified by Nonaka of turning: (1) existing explicit knowledge to new explicit knowledge, (2) existing explicit knowledge to new tacit knowledge, (3) existing tacit knowledge to new explicit knowledge and (4) existing tacit knowledge to new tacit knowledge. This is done through the establishment of theoretical models that respectively identify the function of the knowledge spiral and the powers of data mining, both exploratory and predictive, in the knowledge discovery process. Our models are then applied to a healthcare data set to demonstrate the potential of this approach as well as the implications of such an approach to the clinical and administrative aspects of healthcare. Further, we demonstrate how these techniques can facilitate hospitals to address the six healthcare quality dimensions identified by the Committee for Quality Healthcare.

Nilmini WICKRAMASINGHE^a, Rajeev K BALI^b,c, M Chris GIBBONS^d, Jonathan Schaffer^e
a Center for the Management of Medical Technology, Stuart Graduate School of Business, Illinois Institute of Technology, Chicago, USA
^b Knowledge Management for Healthcare (KARMAH) research subgroup,
^c Biomedical Computing and Engineering Technologies Applied Research Group (BIOCORE), Coventry University, UK
^d Johns Hopkins Urban Health Institute, Johns Hopkins Medical Institutions, Baltimore, USA
^e The Cleveland Clinic, Cleveland, USA

To be published in “Medical and Care Compunetics 5″, IOSPress, 2008.
To be presented at the ICMCC Event 2008.

Perlegen strikes back on privacy

“Last week, patient privacy advocate Deborah Peel, MD, wrote a letter to Healthcare IT News attacking Perlegen Sciences’ plans to work with an EMR vendor to use patient data for genetics research. In a new letter, Perlegen strikes back at Peel.”
Article
Bryan L. Walser, Perlegen Sciences, Inc., Healthcare IT News, 27 March 2008

Patient privacy rights advocate attacks plans to mine medical records

“Deborah Peel, founder and chairman of Patient Privacy Rights, takes exception to a plan by Mountain View, Calif. -based Perlegen Sciences, Inc. to collaborate with an undisclosed electronic medical records vendor to identify and develop genetic markers that predict how patients are likely to respond to specific medical treatments.”
Article
Deborah Peel, Healthcare IT News 21 March 2008

Google includes San Diego medical software company’s program

“Internet giant Google has tapped a medical software developer in San Diego to provide a key element of its test project that lets people create comprehensive medical records on the Web.
SafeMed’s application sifts through vast medical databases and personal health records in the blink of an eye to detect potentially harmful drug interactions and recommend treatments for specific conditions.”
Article
Keith Darcé, SignOnSanDiego, 20 March 2008

EMR vendor to share patient data with genetics research firm

“Perlegen Sciences, Inc., a company exploring the clinical application of genetic research, plans to collaborate with an undisclosed electronic medical records vendor to identify and develop genetic markers that predict how patients are likely to respond to specific medical treatments.”
Article
Richard Pizzi, Healthcare IT News, 20 March 2008

Peel: Congress should stop pandering to health data miners

“The story last week on e-prescribing [“$3 billion annual savings estimated for Medicare e-prescribing,” GovHealthITcom, March 4] does not mention the elephant in the room: that every prescription in the nation has been data-mined and sold for over a decade to drug companies and employers without the legal consent of Americans.”
Article
Government Health IT, 6 March 2008

Introduction to Data Mining for Medical Informatics

“Data mining consists of a series of techniques for the discovery of patterns in large databases. This article provides an introduction to common data mining techniques with a view toward their use. The article begins by describing methods for discovering and exploring associations in observations and variables. The discussion then turns to methods for prediction. These techniques discover relationships between sets of variables. The article concludes with a description of evaluative techniques that are useful for assessing the results from data mining.”
Abstract
Donald E. Brown PhD, Clinics in Laboratory Medicine, Volume 28, Issue 1, March 2008, Pages 9-35, doi:10.1016/j.cll.2007.10.008

Back Page: Limiting access to providers’ prescribing data

“Last year, New Hampshire became the first state to pass legislation curtailing the practice of mining pharmaceutical records. Data-mining companies buy data from pharmacies and benefits managers to track which drugs physicians are prescribing. The companies then sell that information to pharmaceutical companies, which use it to fine-tune their marketing efforts.”
Article
Jonathan Lax, Government Health IT, 10 September 2007

Improving the Quality of Care at the End of Life: An Information Systems Approach

Tamang S., Kopec D., Shagas G., Levy K.
Brooklyn College; Albert Einstein Coll. of Medicine, USA

Abstract:

Chronic and terminally ill patients are disproportionately affected by medical errors. In addition, the elderly suffer more preventable adverse events than younger patients. Targeting system wide “error-reducing” reforms for vulnerable populations can significantly reduce the incidence and prevalence of human error in medical practice. Recent developments in medical informatics, particularly the application of artificial intelligence (AI) techniques such as data mining, neural networks, and case-based reasoning (CBR), presents tremendous opportunities for mitigating error in disease diagnosis and patient management. Additionally, the ubiquity of the Internet creates the possibility of an almost ideal network for the dissemination of medical information. We explore the capacity and limitations of web-based palliative information systems (IS). These can be used to transform the delivery of care, streamline processes and improve the efficiency and validate the correctness of treatments. As a result, medical error(s) that occur when patients with severe, chronic illnesses and/or the frail elderly are treated, can be reduced.

The palliative care model grew out of the need for pain relief and comfort measures for patients diagnosed with cancer. Applied definitions of palliative care extend commonly used conventions, but there is no widely accepted definition. This research will discuss the development life cycle of the CONFER management information systems (MIS), currently used by a community-based palliative care program in Brooklyn, New York, and the CAREN CBR. CONFER is based on the idea of “eCare”, a process based application for care management. CONFER uses XML (extensible mark-up language), a W3C-endorced standard mark-up to define systems data. The CAREN system is a CBR prototype designed for palliative care patients in the cancer trajectory, which was developed by the first author in her research. CBR is a technique, which tries to exploit the similarities of two situations and match decision-making to the best-known precedent cases. The system uses the opensource CASPIAN shell developed by the University of Aberystwyth, Wales and is available by anonymous FTP. Our preliminary results suggest that these systems can be used to improve the quality of care and disseminate expert level ‘know how’ to palliative care clinicians.