Warning: file_get_contents(http://webbiscuits.net/images/blan.gif) [function.file-get-contents]: failed to open stream: HTTP request failed! HTTP/1.1 404 Not Found in /home/residenc/public_html/wp-content/themes/residencynotes/header.php on line 26
Tuesday, March 13th 2007

Who Needs A Family Member…

…to make decisions if you’re in a dire medical situation. Apparently a computer can do just as well even better.

I’ll Only Sign On If They Use An Apple II

By signing what is known as an “advance directive”, people can specify what types of medical care they would want if they lost the ability to make decisions. Many people, however, do not complete such a directive in advance of these critical situations and their relatives or others must then decide on their behalf.

But how well can surrogates accurately predict the wishes of patients? Researchers have previously addressed this question by asking people how they would want to be treated in various hypothetical medical scenarios and, in a separate room, asking surrogates to guess what those responses had been. A review of 16 studies found that surrogates got it right only 68% of the time.

The data suggested that most people want life-saving treatment if there is at least a 1% chance that following the intervention they would have the ability to reason, remember and communicate. If there is less than a 1% chance, people generally say they would choose not to have the treatment.

[The lead author] imagines a situation in which a surrogate is told there is only a 5% chance that an incapacitated loved one will survive a life-saving surgery following an auto accident. He says that the relative might predict that the patient would not want the intervention while the formula would predict that they did.

Wendler now wants to collect medical care preferences from people of various ethnic, religious and gender groups, which will help his team refine the formula. He believes that a computer program might one day predict patient’s wishes to an accuracy of 90%.

And thus a computer can measures the odds and decides if someone would want continued care.