Researcher shows data mining EMRs can detect bad drug reactions

June 5, 2013

NJIT Assistant Professor Mei Liu, PhD, a computer scientist, has recently shown in a new study that electronic medical records can validate previously reported adverse drug reactions and report new ones.

"Comparative Analysis of Pharmacovigilance Methods in Detection of from Electronic Medical Records" (Journal of American Medical Informatics Association, May 2013) examined the use of retrospective medication orders and inpatient laboratory results documented in the medical records to identify adverse reactions. Twelve years of data from Vanderbilt University Medical Center were studied by Liu and a research team. The researchers correlated abnormal laboratory results with specific administrations by comparing the outcomes of a drug-exposed group and a matched unexposed group.

" requires that each drug be monitored throughout its market life as early detection of adverse drug reactions can lead to alerts that prevent patient harm," Liu said. "Recently, (EMRs) have emerged as a valuable resource for detecting bad ."

Liu, a computer scientist, recently joined NJIT. She uses advanced informatics approaches to improve health care, with the long-term research goal of developing data-mining methodologies to uncover from EMRs to improve the quality, safety, efficiency and effectiveness of health care.

"EMRs have created an unprecedented resource for observational studies since they contain not only detailed patient information, but also large amounts of longitudinal clinical data," she said. Despite the promise of EMR as a research tool, challenges exist for large-scale observational studies. Much relevant clinical information is embedded in narrative text and multiple factors conspire to make drawing specific conclusions from EMR data more challenging than data collected specifically to answer research hypotheses. Thus, it is desirable to develop effective and efficient computational methods to mine EMR data for conducting large-scale observational research.

Adverse drug reaction (ADR) for instance, is one of the major causes for failure in drug development. And severe ADRs that go undetected until the post-marketing phase of a drug often lead to patient morbidity, as exemplified by numerous drug withdrawals. Currently, she is leading three projects to simultaneously examine ADRs from different angles. First, she aims to predict ADRs from the chemical, biological and phenotypic properties of drugs. Second, she uses laboratory and retrospective medication order data from EMR to ascertain ADRs. Third, she is exploring the use of natural language processing techniques to extract adverse events from the narrative notes in EMR and correlate those events with medications through association mining. She is also interested in other data mining tasks for clinical informatics, such as drug repurposing (i.e. application of known drugs to new diseases). She is also interested in using patient to build predictive models for diseases such as diabetes and cancer.

Liu has published numerous papers in Bioinformatics, PLOS ONE, and the Journal of American Medical Informatics Association. She received her doctorate in computer science with a research focus in bioinformatics from the University of Kansas in 2009.

Explore further: Mining information contained in clinical notes could yield early signs of harmful drug reactions

Related Stories

Mining information contained in clinical notes could yield early signs of harmful drug reactions

April 10, 2013
Mining the records of routine interactions between patients and their care providers can detect drug side effects a couple of years before an official alert from the U.S. Food and Drug Administration, a Stanford University ...

Using internet search logs can help identify drug interactions

March 28, 2013
(HealthDay)—Search logs can be used to inexpensively mine for anonymized signals that may alert authorities to potential drug interactions and add new Web-scale pharmacovigilance capabilities, according to research published ...

Study examines the role adverse reactions play in statin discontinuation

April 1, 2013
Despite their well-documented benefits, statins, drugs used to lower cholesterol, are commonly discontinued in routine care. Statin discontinuation has been linked to increased risk for cardiovascular events and death in ...

Recommended for you

Mind-body therapies immediately reduce unmanageable pain in hospital patients

July 25, 2017
Mindfulness training and hypnotic suggestion significantly reduced acute pain experienced by hospital patients, according to a new study published in the Journal of General Internal Medicine.

Study suggests ending opioid epidemic will take years

July 20, 2017
The question of how to stem the nation's opioid epidemic now has a major detailed response. A new study chaired by University of Virginia School of Law Professor Richard Bonnie provides extensive recommendations for curbing ...

Team-based model reduces prescription opioid use among patients with chronic pain by 40 percent

July 17, 2017
A new, team-based, primary care model is decreasing prescription opioid use among patients with chronic pain by 40 percent, according to a new study out of Boston Medical Center's Grayken Center for Addiction Medicine, which ...

Private clinics' peddling of unproven stem cell treatments is unsafe and unethical

July 7, 2017
Stem cell science is an area of medical research that continues to offer great promise. But as this week's paper in Science Translational Medicine highlights, a growing number of clinics around the globe, including in Australia, ...

Popular heartburn drugs linked to higher death risk

July 4, 2017
Popular heartburn drugs called proton pump inhibitors (PPIs) have been linked to a variety of health problems, including serious kidney damage, bone fractures and dementia. Now, a new study from Washington University School ...

Most reproductive-age women using opioids also use another substance

June 30, 2017
The majority of reproductive-age and pregnant women who use opioids for non-medical purposes also use at least one other substance, ranging from nicotine or alcohol to cocaine, according to a University of Pittsburgh Graduate ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.