When doctors diagnose, they "match" a patient's symptoms against the patterns of several likely diseases, narrowing down the list as they go, This decision-making process, known as combinatorial thinking, involves juggling more information than what the human brain can handle and there is always a chance of misdiagnosis.
Now Isabel, a web-based diagnosis system, could come to their rescue. It applies sophisticated pattern recognition technology to a specially developed medical database to help zero in on diseases that match the data entered.
Take for instance the experience of US pediatrician Stephen Borowitz who was attending to a boy who 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.
"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.
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.
Isabel itself is considered a robust tool, highly rated by the Healthcare Information and Management Systems Society.
`Isabel' is a clinical decision support system aimed at reducing and managing diagnosis errors at the point of care, says Dr Joseph Britto, co-founder and CEO of Isabel Healthcare Inc.
The Isabel Diagnostic tool was inspired by the near fatal misdiagnosis of the 3
year old daughter of Isabel Healthcare's CEO, Jason Maude. Little Isabel nearly
died of necrotising fascitiis, the deadly flesh-eating bug, as a complication of
chicken pox. The diagnostic tool was created by paediatric intensive care
consultant Dr. Joseph Britto, who helped to save Isabel's life at St Mary's Hospital in London.
`Isabel' uses pattern recognition techniques, as opposed to standard key word searches.
It was launched in UK five years ago. With support from the UK Department of Health, the UK National Health Service and other key medical institutions, Isabel quickly gained credibility and support from around the world.
Within months of its launch, the system attracted more than 20,000 users from over 100 countries. Impressed with the system's high levels of speed and accuracy, demand rapidly grew for an adult version which was launched in January 2005 and is now used by many top-rated hospitals in the United States and around the world, says the company's official website.
In complicated situations, doctors could misdiagnose if symptoms fit a set pattern. An online support system throws up the different complications and data generated around similar symptoms and helps the doctor take a more informed decision.
"But that does not mean the doctor goes into auto-pilot," Joseph Britto stresses, underlining the importance of the doctor who will take the final call on treatment.
A doctor's job is not easy. An average clinician carries two million pieces of information and over 50 million clinical decisions are made for every one million members of the population, according to data provided by Isabel Healthcare.
"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."
Some, however, fear 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," says Jerome Groopman. "They're only as good as the physician who is identifying what the key symptom or key finding is about the patient."