Bioethicist David Wendler and colleagues from the US National Institutes of Health developed a computer-based algorithm that promises to predict wishes of incapacitated patients, by incorporating patients’ medical history and bio-psycho-social aspects, and extracting wish data for patients in similar circumstances.
To use the decision tool, called a “population-based treatment indicator,” the doctor first enters the incapacitated patient’s circumstances and personal characteristics into a computer. Perhaps, for example, the patient has pneumonia and severe Alzheimer disease, and he is a 60 year old, well educated, Native American, male. The computer analyzes the treatment preferences of similar individuals and estimates the likelihood that the patient would want antibiotics to treat his pneumonia.
A finding that 90% of highly educated Native American men over the age of 50 do not want to receive antibiotics to treat pneumonia in the setting of advanced Alzheimer disease would provide strong evidence that this patient would not want antibiotics in these circumstances either.
David Wendler and colleagues (US National Institutes of Health), who devised the tool, analyzed how well the tool performs compared to asking a loved one (loved ones are known as “surrogates”).
There is obviously no way to determine which medical treatments patients actually want at the time they are incapacitated, and so studies looking at whether surrogates accurately predict patients’ treatment choices must use hypothetical scenarios. For example, one study used the following scenario:
“You recently suffered a major stroke leaving you in a coma and unable to breathe without a machine. After a few months, the doctor determines that it is unlikely that you will come out of the coma. If your doctor had asked whether to try to revive you if your heart stopped beating in this situation, what would you have told the doctor to do?”
Analysis of 16 such studies reveals that surrogates accurately predict patients’ treatment preferences about 68% of the time. In comparison, Dr Wendler and colleagues found that a preliminary computer-based decision tool predicted the patient’s treatment preferences with the same accuracy, and improved decisions tools undoubtedly would be more accurate than surrogates.
Alarmists no doubt will raise concerns about either the government or the hospital controlling such a computer tool to decide for those who cannot speak for themselves. We are, however, not alarmed (not yet, at least). After all, with safeguards (such as courts) this tool might be quite useful, as it will not make an extreme decision, unlike some of the relatives tend to.
Full paper at PLoS Medicine…
Press release…