�������ýҕ�l

PALO ALTO, Calif  –When Dr. Sarah Russell sees patients at the Veterans Administration hospital here, she sometimes turns to a trusted adviser:  the supercharged software on her desktop.

Whether a patient needs a blood transfusion, a different medication or a more refined diagnosis, the artificially intelligent program can give her options in seconds.

Say a patient is anemic. With input from the patient’s electronic medical record and a vast store of information from what has worked for other patients, the computer can determine quickly whether a transfusion is likely to be worthwhile.

The program also warns her whether patients might react poorly to a given medication and flags patients who may have a greater risk of getting re-admitted to the hospital after being sent home.

“I’’m not asking [the program] to say, ‘This is where a patient is headed’,” says Russell, the VA’s chief medical informatics officer for the Palo Alto health system.  Instead, for similar patients, “just tell me what’s happened in the past, and I’ll make the call.”

The system is one of a growing number of similar tools around the country allowing doctors to tap into  databanks of patient records and research to improve and streamline care.

Supercomputers and homegrown systems can help identify patients who might be at risk for kidney failure, cardiac disease or postoperative infections and to prevent hospital readmissions. In addition, patients’ individual health data—including genetic information—can be combined with the wealth of material available in public databases, textbooks and journals to help come up with more personalized treatments.

Driving the increased reliance on artificial intelligence is health reform law, which seeks to leverage technology to improve outcomes and reduce costs, and the availability of cheaper and more powerful computers. In addition, doctors are embracing “population management” —  the practice of using large reservoirs of information about  patients with similar medical histories to help draw inferences about individual cases.

To be sure, computers can’t replace doctors at the bedside, but they can be a tool to take full advantage of electronic medical records, transforming them from mere e-filing cabinets into full-fledged doctors’ aides that can deliver clinically relevant, high-quality data in real time.

So far, computers have gotten really good at parsing so-called structured data—information that can easily fit in buckets, or categories. In health care, this data is often stored as billing codes or lab test values.

But this data doesn’t capture patients’ full-range of symptoms or even their treatments.  Images, radiology reports and the notes doctors write about each patient can be more useful. That’s unstructured data, and computers are less savvy at handling it because it requires making inferences and a certain understanding of context and intent.

That’s the stuff humans are really good at doing — and it’s what scientists are trying to teach machines to do better.

In recent years, universities, tech companies and venture capital firms have invested millions into making computers better at analyzing images and words. Companies are popping up to capitalize on findings in studies suggesting that artificial intelligence can be used to improve care.

But many challenges remain, experts say. Among them is the tremendous expense and difficulty of gaining access to high-quality data and of developing smart models and training them to pick up patterns.

Most electronic medical record-keeping systems aren’t compatible with each other. The data is often stored in servers at individual clinics or hospitals, making it difficult to build a comprehensive reservoir of medical information.

Moreover, the systems often aren’t hooked up to the Internet and therefore can’t be widely distributed or accessed like other information in the cloud. So, unlike the vast amount of data on Google and Facebook, the information can’t be mined from anywhere by those interested in analyzing it.

From the perspective of privacy advocates, this makes some good sense: A researcher’s treasure trove is a hacker’s playground.

“It’s not the greatest time to talk about” health records on the web, given security scandals such as the Edward Snowden leaks and the Heartbleed bug, said Dr. Russ Altman, the director of Stanford University’s biomedical informatics training program.

Also standing in the way are concerns about how far computers should encroach on doctors’ turf. As artificial intelligence systems get smarter, experts say, the line between making recommendations and making decisions could become more murky.

At the moment, the technology isn’t good enough to tell doctors with 100 percent certainty what the best treatment for a patient may be.

Despite these limitations,  some physicians and researchers find the possibilities of artificial intelligence  to be tantalizing.

“Electronic health records [are] like large quarries where there’s lots of gold, and we’re just beginning to mine them,” said Dr. Eric Horvitz, the managing director of Microsoft Research.