Electronic medical records hold great promise to facilitate efficient healthcare. No longer will nurses squint to decipher doctors’ chicken scratch on paper forms, and patients can have their medical records transferred between healthcare providers with ease. But interpreting all the data in the system can present a challenge.

A simple keyword search in a database pulls up far too many results, including many irrelevant ones. For example, if you searched ‘pneumonia’ in the medical records, you would retrieve the cases of pneumonia you desired — but also every single time pneumonia was mentioned in passing.

“In an ideal world, all clinical data should be structured and coded, mapped with a standard terminology,” says Stéphane Meystre, a biomedical informaticist at the University of Utah Medical School who was not involved with the research. “But clinicians like to tell things their way, so we need a way to extract data from narrative text.”

One solution to help computers decode the context of all the medical terms in a system might be natural language processing, an artificial intelligence tool that goes beyond a basic keyword search, according to a study out today in the Journal of the American Medical Association. This analytical tool incorporates sentence structure “to take into account the context of what you’re trying to say,” says Harvey Murff, associate professor of medicine at Vanderbilt University and lead author.

Murff and his colleagues used natural language processing to search the medical records of nearly 3,000 patients at six Veterans Health Administration medical centers for adverse effects following surgery, including renal failure, sepsis, heart attack and pneumonia. They compared their results to patient reviews done by reading straight from the paper charts— considered the gold standard, he says. Pooling the data from all complications, natural processing language identified 77% of all adverse events found in the paper-based undertaking. By comparison, a traditional keyword search only identified 42% of post-surgical complications.

The unfortunate reality is that the system still cannot decipher mis-entered information. Clinicians sometimes rush the process of entering notes into the computer, leading to typos and misspellings, or use non-standard abbreviations. Additionally, “the meanings [of terms] changes from specialty to specialty, hospital to hospital, even in the same documents,” Meystre says.

Murff says that even though his language analysis tool can help sort through the information in a system, it is not perfect. “It’s unlikely that you’d have a tool like this that would ever be 100% accurate,” says Murff. “After all, it’s people; we take shortcuts.”

Natural language processing is one tool, but it’s likely not the final word.

Image: flickr user southerntabitha via Creative Commons

Reports of multidrug resistant tuberculosis in every region of the world have raised red flags over the past few years, but clinicians have a far more basic problem on their hands: diagnosing the disease. The World Health Organization (WHO) reported last year that one-third of tuberculosis infections go undetected or are poorly treated, leading to disease spread and evolution of drug resistance.

The most accurate diagnosis is made by culturing the bacteria that causes the disease, Mycobacterium tuberculosis. However, this process takes around two months — far too long for clinicians to respond quickly in the field. Serological tests that detect anti-tuberculosis antibodies in the blood take less than an hour. But last month, the WHO, in its first-ever explicit ‘negative’ policy recommendation, cautioned against using these tests after researchers showed that they are neither accurate nor cost-effective.

The apparent need for a fast and cheap diagnostic test has pushed researchers to develop novel methods. One such approach was published online today in the Journal of Applied Microbiology. The researchers measured the heat cast off by growing bacteria — a technique known as isothermal microcalorimetry — to diagnose tuberculosis and related infections. Policy makers and doctors have historically ignored this method because the required equipment is too expensive. But this study provides evidence that a low-cost version of the instrumentation can diagnose the disease in less than two weeks.

Continue reading →

In August 2007, billionaire Carl Icahn took hold of 2.7 million of Biogen Idec’s shares, making him one of the company’s largest investors. Over the next few years, he grew his ownership in the Weston, Massachusetts-based biotech, holding 8.2 million shares valued at nearly $750 million as recently as June of this year. But yesterday, after four years of attempted control of the company’s direction and management, Icahn disclosed that he has dumped all of his stock in the company, according to the Wall Street Journal.

Ever since he first invested in Biogen Idec, Icahn has tried to wrench control of the drugmaker best known for its drugs for treating multiple sclerosis. He insisted that the board sell Biogen Idec at the end of 2007, and when they failed to find a buyer, Icahn accused them of lying about their effort. In 2009, the board elected two of his four nominated directors at his urging — and two months later, two other board members resigned (although former director Cecil Pickett told Nature that early resignation was “the plan all along”).

Continue reading →