Interesting Enemies For a Diagnostic Database 409
dlh writes: "Boston.com is carrying an article about Dr. Lawrence L. Weed's Problem Knowledge Coupler software. Apparently the medical profession is not exactly thrilled at the idea." Seems access to information is a positive thing, but certain doctors seem to feel threatened by this sort of database.
one of many professions to be threatened (Score:1, Informative)
this is nothing but good for the patient, itll lead to cheaper and more accurate diagnoses.
Re:used a damned large paintbrush didn't he? (Score:2, Informative)
Re:A MD's perspective? (Score:3, Informative)
I don't think this is a technological problem as much as a usability issue.
Re:Database vs Doctor (Score:3, Informative)
Doctors must also take into account that the person describing the symptoms may have more than one condition simultaneously, that the patient may be exagerating something common or normal as a symptom because he believes it is related to the other actual symptoms. As others have pointed out in this discussion people can unconsciously pick up symptoms based on information they have read. It is rare to have a doctor these days that knows you for very long and who has treated you and your family for many years but that would give the doctor more insight into what the problem could be.
The article starts off with an example where Dr. Cross had an unusual case for which he did not recognize the symptoms and which turned out to be a condition he hadn't even heard of before. This is a situation where using this program makes sense; it merely computerizes the literature search. But I disagree with you that doctor's could easily be replaced. This program can only be a helpful tool used in conjunction with all the physicians other tools.
The doctor must be the one who diagnoses. He can not become just a technician asking the patient questions and entering the response into a computer form. Physicians are licensed for the same reason that Professional Engineers are licensed. When human life hangs in the balance, someone must be accountable to make sure things are done right.
One Mechanic's View (Score:2, Informative)
"Bar." Your car is here for scheduled maintenance. Example: Oil change.
"Bar, on the face of it." While inspecting your car, I found the following condition. Example: bad brake light bulb.
"Bar, that's going to get worse." Example: That squealing means you need to have the front rotors turned and new front brake pads replaced before they start grinding.
"Bar, I've seen that a hundred times." This will fix a particular problem. Example: That grinding noise means you need to have the front rotors and pads replaced right now.
In the first example above a good AI remembers that exactly x quarts of oil are needed so the mechanic can do it as quickly as possible and the bill reflects it seamlessly. Doctors already do their accounting by computer. Results already come back from the lab with the data checked against norms and anomalies highlighted.
In the second example, we start looking for things. The better the checklist the better the inspection. A good AI list includes checking all the usual things, checking all the known odd things about that particular car, and leaving out items known not to be an issue. Example: Car model A is subject to a fuel pump recall. The first time the car comes in the item is on the list, check fuel pump. If it is old we change it, if it is new we note it, and in either case, it will not be an item again. No mechanic can remember all this.
The third example is the hardest one. This is where the human judgement factor is strongest, selling brakes preventively and talking about driving habits. There is room for AI in situations like this, but not as much. This is the customer service stuff mentioned in the third paragraph above. It isn't easy being a mechanic either.
In the fourth situation, the diagnostic part of the AI is exercised. Maybe the problem isn't the most common one. Example: The car has a bad ball joint which causes it to pull to the right when the brakes are applied and a bad brake caliper which causes it to pull to the left. Net pull is zero. If it isn't caught, an inadequate repair will be made. A good mechanic will find it most of the time. A good AI will help almost every mechanic find it almost every time. It passes on knowledge to the young and reminds the old. What I wouldn't give for a decent program like this. I think that it would reduce errors of cognition. "It looked like bar to me, boss." Who among us has always looked for and found the colons among the semicolons?
FWIW, When you take your car to the shop, make sure you describe the symptoms you are concerned about more than your theory or preferred solution. Leave a note on the passenger seat with the same information and a five dollar tip for the mechanic and you will get better service. Trust me on this.
In conclusion, a good AI assistant is useful at every step and most of the kinds of things one can do are already being done. It will make a doctor faster, more accurate and richer. From a patient's perspective the most important thing is a timely correct treatment. I don't see how this can hurt the process. What seems to be wanted is better AI and I have no doubt that writing the good stuff will require brilliant doctors. It will make me feel safer. Patience.
SingCP@yahoNOSPAMo.com
Reaction from PKC (Score:2, Informative)