For doctors, diagnosing gets a technological boost

Sept. 6, 2007 — -- Pediatrician Stephen Borowitz was walking the floors of the University of Virginia Children's Hospital with his residents when he was presented with an unusual case.The patient was a boy who was very ill with a severe childhood disease called hemorrhagic shock and encephalopathy syndrome. Borowitz says the boy had significant neurological damage and was fed through an intravenous feeding tube.

The immediate problem was that he had a fever. But he was showing other symptoms that didn't match his condition. "He had developed diarrhea, which is extremely unusual for him, and he seemed uncomfortable," Borowitz says.

Borowitz worried that the culprit was a bloodstream infection, a typical problem with patients with intravenous feeding tubes. But something still didn't seem right.

So Borowitz and his residents consulted Isabel, a Web-based medical technology that generates a list of possible diagnoses based on the patients' symptoms.

"I put all his symptoms into Isabel and it came up with a number of ideas," he says. "One of them was gallbladder disease, which I probably should have thought of, but I didn't."

An ultrasound was ordered, and gallbladder disease was indeed the problem, and it may not have been related to the boy's pre-existing condition or his feeding tube.

Misdiagnoses are common

According to a 2003 Journal of the American Medical Association review of autopsy studies, doctors misdiagnose 8% to 24% of the time. Cognitive errors, such as latching onto a diagnosis that seems the most likely without considering other possibilities — which experts call "anchoring" — are among many root causes, according to Jerome Groopman, chairman of experimental medicine at Harvard University and author of the book How Doctors Think.

The solution for some is technology. Doctors are increasingly using the Internet, even search programs as basic as Google, when they're stumped, according to "Googling for a Diagnosis," a British Medical Journal study last year.

Although Isabel is used in only 18 hospitals, interest in similar decision-support systems is growing in the medical community, according to the American Medical Informatics Association. Priced at around $50,000 a year for a typical 300 bed hospital, Isabel is considered a robust tool, highly rated by the Healthcare Information and Management Systems Society.

"One of the things I try to model for my residents is that I'm trying to learn new things even though I've been doing this for a long time," Borowitz says.

"It's the acknowledgment that I'm fallible and I need to use all the tools I can to make sure I'm giving the best care."

When doctors diagnose, they "match" a patient's symptoms against the patterns of several likely diseases, narrowing down the list as they go, according to Lawrence Weed, professor emeritus of medicine at the University of Vermont. This decision-making process, known as combinatorial thinking, involves juggling too much information for it to be successful without the aid of technology, Weed says.

"The mind can't possibly deal with the complexity of the problem that a patient presents," Weed says. "What if you said, 'Let's give (doctors) eight years of geography at Harvard and then let them to drive across the country without a map'?"

Weed developed Problem Knowledge Couplers — a technology that "couples" patient symptoms with relevant medical literature. With Couplers, patients can enter their symptom information into the Web-based tool and walk through the medical knowledge with their doctor. About 50 private employers now provide access to Couplers.

A correct diagnosis can hinge on a doctor recalling a crucial piece of information — one he or she may have learned years ago in medical school or read in a journal months ago, says physician and Isabel developer Joseph Britto. Similar to Couplers, Isabel allows doctors to "click through" medical knowledge related to a possible diagnosis. Isabel, Britto says, was developed to help doctors reduce errors by lightening the "burden of memory."

"In the traditional medical environment, people expect you to know everything," says Napoleon Knight, a physician at the Carle Foundation Hospital near Chicago, who uses Isabel in the emergency room to help diagnose his patients. "It can be difficult sometimes to keep all that knowledge right at the top of your brain so you can pull it out when you really need it."

'Cookbook' medicine?

Groopman, however, fears that placing too much emphasis on technology will take the spotlight off clinical judgment.

"With these cookbook-type recipes for diagnosis and treatment, the risk is that's it's garbage in, garbage out," Groopman says. "They're only as good as the physician who is identifying what the key symptom or key finding is about the patient."

Many doctors who use Isabel argue that technology doesn't supersede individual judgment but rather acts as an aid in the decision-making process.

"Certainly it will never take the place of judgment," Knight says. "There's still a lot that you learn about an individual patient just by walking into the room and seeing the look on their face, or by placing your hand on their forehead."