Electronic medical record text search tool shows promise for identifying postoperative complications

August 23, 2011

Use of natural language processing, such as in the form of free-text searches of electronic medical records (EMRs) of clinical and progress notes of patients performed better at identifying postoperative surgical complications than the commonly used administrative data codes in EMRs, according to a study in the August 24/31 issue of JAMA.

To improve on identifying concerns, the Agency for Healthcare Research and Quality developed a set of 20 measures, known as the patient safety indicators, which use administrative data to screen for potential adverse events that occur during hospitalization, according to background information in the article. "Currently most automated methods to identify patient safety occurrences rely on administrative data codes; however, free-text searches of could represent an additional surveillance approach," the authors write. "The development of automated approaches, such as natural , that extract specific medical concepts from textual medical documents that do not rely on discharge codes offers a powerful alternative to either unreliable administrative data or labor-intensive, expensive manual chart reviews. Nevertheless, there have been few studies investigating natural language processing tools for the detection of adverse events. It is not known whether a surveillance approach based on language processing searches of free-text documents will perform better than currently used tools based on administrative data."

Harvey J. Murff, M.D., M.P.H., of the Veterans Affairs Medical Center and Vanderbilt University, Nashville, Tenn., and colleagues conducted a study to evaluate a language processing-based approach to identify within a multi-hospital health care network using the same EMR. The study included 2,974 patients (median [midpoint] age, 64.5 years; 95 percent men) undergoing inpatient surgical procedures at 6 Veterans Health Administration (VHA) medical centers from 1999 to 2006. Among the outcomes measured were postoperative occurrences of acute renal failure requiring dialysis, deep vein thrombosis, pulmonary embolism, sepsis, pneumonia, or heart attack identified through medical record review as part of the VA Surgical Quality Improvement Program. The researchers determined the sensitivity and specificity of the natural language processing approach to identify these complications and compared its performance with patient safety indicators that use discharge coding information.

Within each analytic sample the percentage of postoperative acute renal failure requiring dialysis was 2 percent (39 of 1,924); for pulmonary embolism, 0.7 percent (18 of 2,327); for deep vein thrombosis, 1 percent (29 of 2,327); for sepsis, 7 percent (61 of 866); for pneumonia, 16 percent (222 of 1,405), and for heart attack, 2 percent (35 of 1,822). The researchers found that in general, using a natural language processing-based approach had higher sensitivities and lower specificities than did the patient safety indicator. "The increase in sensitivity of the natural language processing-based approach compared with the patient safety indicator was more than 2-fold for acute renal failure and sepsis and over 12-fold for pneumonia. Specificities were 4 percent to 7 percent higher with the patient safety indicator method than the natural language processing approach."

"Natural language processing correctly identified 82 percent of acute renal failure cases compared with 38 percent for patient safety indicators. Similar results were obtained for venous thromboembolism (59 percent vs. 46 percent), pneumonia (64 percent vs. 5 percent), sepsis (89 percent vs. 34 percent), and postoperative myocardial infarction (91 percent vs. 89 percent). Both and patient safety indicators were highly specific for these diagnoses."

The authors suggest that a natural language processing-based approach offers several potential advantages over administrative-code based strategies to identify health care quality concerns. "First is the flexibility of the approach to meet the individual institutional needs. Once documents have been processed, different approaches and query strategies to identify a specific outcome can be implemented at a relatively low programming effort using standard database query applications. Second, as opposed to administrative codes, search strategies using daily progress notes, microbiology reports, or imaging reports could be monitored on a prospective basis. Thus, this approach could potentially identify complications while a patient is still in the hospital, which could greatly facilitate real-time quality assurance processes. … Finally, in systems with highly integrated EMRs, prospective surveillance could be extended to the outpatient setting for individuals remaining with the health care system."

More information: JAMA. 2011;306[8]:848-855.

Related Stories

Recommended for you

Exploring the potential of human echolocation

June 25, 2017
People who are visually impaired will often use a cane to feel out their surroundings. With training and practice, people can learn to use the pitch, loudness and timbre of echoes from the cane or other sounds to navigate ...

Team eradicates hepatitis C in 10 patients following lifesaving transplants from infected donors

April 30, 2017
Ten patients at Penn Medicine have been cured of the Hepatitis C virus (HCV) following lifesaving kidney transplants from deceased donors who were infected with the disease. The findings point to new strategies for increasing ...

'bench to bedside to bench': Scientists call for closer basic-clinical collaborations

March 24, 2017
In the era of genome sequencing, it's time to update the old "bench-to-bedside" shorthand for how basic research discoveries inform clinical practice, researchers from The Jackson Laboratory (JAX), National Human Genome Research ...

The ethics of tracking athletes' biometric data

January 18, 2017
(Medical Xpress)—Whether it is a FitBit or a heart rate monitor, biometric technologies have become household devices. Professional sports leagues use some of the most technologically advanced biodata tracking systems to ...

Financial ties between researchers and drug industry linked to positive trial results

January 18, 2017
Financial ties between researchers and companies that make the drugs they are studying are independently associated with positive trial results, suggesting bias in the evidence base, concludes a study published by The BMJ ...

Best of Last Year – The top Medical Xpress articles of 2016

December 23, 2016
(Medical Xpress)—It was a big year for research involving overall health issues, starting with a team led by researchers at the UNC School of Medicine and the National Institutes of Health who unearthed more evidence that ...

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.