Robo-docs

Medical errors kill more people each year than auto accidents, breast cancer or AIDS. Can automating medicine prevent tragedies like the Andrea Yates case?

By Ivan Oransky, M.D.

Apr 9, 2002 | Andrea Yates was, in the words of a psychiatrist who treated her for one episode of postpartum depression with psychosis, one of the five sickest patients the psychiatrist had ever treated. She neglected to bathe or to drink water, she acted bizarrely and she suffered from severe delusions and hallucinations that experts say made her a clear danger to herself and others. But just days before she drowned her five children in a bathtub, Andrea Yates' doctor decided to take her off her antipsychotic medications -- a mistake, in hindsight, that may have cost her children their lives.

What if we took humans out of the equation? What if a dispassionate computer had been making the decisions about Yates' care, rather than a human doctor sitting across a desk from her? Would a computer have left her on medication? Would her children still be alive?

Three years ago, the National Institute of Medicine estimated that medical mistakes kill between 44,000 and 98,000 people per year in hospitals. If that's true, it means medical errors kill more people each year than car accidents, breast cancer or AIDS. Efforts to reduce such errors get only a fraction of the attention -- and funding -- that goes to AIDS research, but arguably it would be far easier to substantially reduce life-threatening medical errors than it has been to create an AIDS vaccine.

While some researchers have successfully poked some holes in the estimates of the number of patients killed by errors, the real effort should be aimed at ways to change the practice of medicine to make it safer. One doctor declaiming loudly that something should and can be done to reduce errors is Atul Gawande, a surgical resident in Boston, a staff writer for the New Yorker and now the author of a new book, "Complications: A Surgeon's Notes on an Imperfect Science."

Gawande is arguably the best nonfiction doctor-writer around; his talents are a source of envy among the rest of us, and this collection showcases his work well. He's prescient and thoughtful, in awe of the medicine he practices without being an unthinking cheerleader. He is able to enter a story, but never overstates his own role as some doctor-writers are wont to do. The title of Gawande's book recalls the title of author and scientist Lewis Thomas' essay collection "The Youngest Science: Notes of a Medicine Watcher." That's apt, because Gawande's work is well on its way to becoming the heir to Thomas' humble, insightful and brilliantly crafted oeuvre.

Gawande's greatest contribution, however, is that he has no fear of fighting the myth of the infallibility of doctors. At times, machines can best man. In 1996, attempting to diagnose heart attacks, a Swedish cardiologist read 2,240 electrocardiograms (EKGs) -- the squiggly lines that show the electrical rhythms running through the heart. Of 1,120 heart attack readings, the cardiologist picked up 620. A computer, reading the same 2,240 EKGs, found 738. Neither was perfect, but the computer had won. Deep Blue had defeated Gary Kasparov.

Computer-based diagnostic systems have been in existence some 30 years, and more than a decade ago a philosopher suggested that "diagnosis without doctors" would be an improvement over human-based systems. For the most part, however, the medical community has seized on the limitations, not the promise, of such systems. The last major study, in 1994, found that they made correct diagnoses only about half to three-quarters of the time, making them suitable only for teaching medical students how to diagnose hypothetical patients.

It turns out, though, that doctors may have been too quick to reject computerized diagnostics across the board. Hospitals have found that computerized systems are invaluable when used to help make highly specialized decisions such as which antibiotics to use in an intensive care unit and which patients with HIV should be on medicines to prevent deadly pneumonias. Machines are also at least as good as pathologists when it comes to reading Pap smears -- and as the Swedish study showed, you may want a computer, not a cardiologist, to check your EKG.

Next Page: "Why didn't you just take him outside and shoot him?"

• View blog reactions