Google Used To Diagnose Disease

dptalia writes "About 20% of all diseases are misdiagnosed, a percentage that has remained steady since the 1930s. However, scientists have discovered that by inputting the key symptoms into Google they can get the correct diagnosis about 58% of the time. For rare and unusual diseases, this provides doctors the information they need to get a correct cure. Of course, Google is only as good as its knowledge base, and its users, so this isn't a cure for everything."

20% error compared to 42% error of Google?

What the blurb doesn't say, how much of the 58% google gets right overlaps with the 20% doctors get wrong, if at all.

Re:

What the blurb doesn't say, how much of the 58% google gets right overlaps with the 20% doctors get wrong, if at all.

The blurb isn't much to begin with - it is only 28 cases that were difficult to diagnose.

Even so, there isn't much information about the 28

Re:20% error compared to 42% error of Google?

Don't get too excited about these numbers. The whole study is based on 26 examples.

Re:

As long as it was a random sample, that still is perfectly valid with a sufficient margin of error and certainty interval. Bigger samples are necessary when you want to prove a relationship, not for demonstrating that there might be one.

Weighted Errors

Silly statistics biased by observer error. Cleraly they did no weight their queries by the probability of a patient showing up with a given disease. If you are sick, then statistically, you have a cold in nearly all of cases of sickness. Therefore if, no

Conclusion

So the conclusion is: Google performs worse than docters. And that was using input from trained doctors. Is it a slow news day or is it time again to boost Google's stock value?

No...

The write-up is a bit funny and misleading.

It's saying of the 20% that's mis-diagnosed, Google correctly identified 58% of those.

However, what no one has brought up is that when something is misdiagnosed, no one knows until they do the autopsy, so you can't just do simple math to lower the error rate to 8%. As you suggest, while google does better when the doctor is wrong, Google is worse than the doctor when he's correct. I'm not sure it's even correct to assume that if the doctor used Google the diagnoses would be better or worse, since there is an element of human judgment in medical practice.

What is does suggest is that doctors and patients should consider using Google to do a check on their patients and themselves for diagnosis and treatment options.

Re:

Exactly. But it has long been known that expert + reference > expert or reference. How many of us use references everyday? I've reached the age where learning anything new requires that I forget a commensurate about of information, so I use reference

Re:

It would have done better, except that it comes up with susbtance abuse disorder ("smoking crack") so often.

Since we're using famous websites

There should be a global wiki for medical professionals searchable by symptoms.

The contribution weight of better/senior/more respected doctors should be higher compared to new graduates. The wide open public should not be allowed to write, but should be allowed to read it.

This way better healthcare will be available in poor countries with Internet access, people will be able to double-check their diagnosis online and better doctors will be able to make a name for themselves the way CowboyNeal has.

Re:

This way better healthcare will be available in poor countries with Internet access

and who happen to not only read English and Latin, but also have a fairly broad knowledge of human anatomy. Oh, and they need to know the English/Latin anatomy terms and nam

Re:Since we're using famous websites

It's called http://pubmed.com/ [pubmed.com] and I use it all the time in exactly the same way. Google is my second choice. You can't practice medicine without internet access now.

ASO, MD
Neurology

Re:Since we're using famous websites

A few of my friends and I (are we're all in the biology field in some degree, as researchers) refuse to use doctors who don't know what the internet is. I'm glad you do, but it is sad when you talk to a doctor about some large issue you have, and the doctor doesn't know about/use the internet to make sure they're aware of all the treatment issues.

One of the most interesting cases in our group was a friend who had osteonecrosis in one of his knees. Some of the doctors he went to weren't keeping up with modern practice, and they recommended full knee replacements. He finally found a younger doctor who was up to date, and the surgery he had involved boring small holes into his knee, so that blood would enter those areas and rebuild the bone there.

The surgery was a complete success, my friend didn't need an artificial knee (at age 30!), and now he's perfectly healthy. The recovery time for the new surgery was much lower, and it was an all around good solution.

That's actually not been shown to work

These lesions usually spontaneously resolve, or can be treated with bisphosphonates (osteoporosis meds) and a bone stimulator. Surgical drilling has not been shown to affect the outcome. The fact that your friends knees became better probably had nothing to do with the surgery. Knee replacements are indicated when the osteonecrosis leads to collapse of the knee joint, usually in large lesions. Since your friend is young, a total knee replacement would not be the preferred treatment - an osteotomy (cutting the bone to change the knee alignment and weight bearing area) would be the preferred treatment.

-Francis C. MD
Dept. Musculoskeletal Oncology, Orthopaedic Surgery.

Re:Since we're using famous websites

A mistake that patients and other laypeople commonly make is to think that their search is just as good as the doctor's. It isn't. An untrained individual (patient, curious person, whoever) using Internet resources to gather information about their real or perceived diagnosis usually ends up barking up the wrong tree. I see it all the time in my patients. I warn them about it and still they make this mistake. I deal with rare diseases, the 20% that are usually diagnosed wrong. Trust me, Google by itself or any other internet resource doesn't do you any good if you don't know EXACTLY what the key symptoms are. And selecting those is not something an amateur can do. So you can go on and tell me about how you corrected your doctor and beat the medical establishment and crap like that, but at least for the kind of disorder discussed here (IPEX and family) you as an amateur would not arrive at that diagnosis. And oh, Google is not the best resource for medical type searches. Try Pubmed, or OMIM, or if you're really serious (IPEX is an X-linked disorder caused by FOXP3 mutations) use the London Dysmorphology Database (LDDB). Amateurs should NOT, I repeat NOT, try to diagnose their own diseases. They simply lack the background to judge their own symptoms.

I would prefer

If there was a publically available performance/competency grade for doctors online so I could just google for a good doctor in my area rather than hoping some med student hits paydirt with an 'I feel lucky search'

Re:

The UK government has been pushing for choice for a while, in healthcare and schooling. Personally, I don't want to be able to choose, I want to be offered the best possible standard wherever I happen to go/send my child...

Good luck

Good luck finding any cure for anything even remotly related to female anatomy. "Hi miss. I currently can't help you diagnose your symptoms right now, as I left my credit card at home and its required to validate that I am old enough to access my.....references...."

Re:

Not quite; "vagina" is rarely used in porn contexts, so a search for e.g. "vaginal cancer" yields perfectly representable results.

Gives you ideas

The key thing is that Google gives you ideas on how to solve the problem.

I had a long term and quite painful medical problem to do with the eustation tube in my ear being blocked. The doctors, and even the ENT specialist didn't really have much of a clue. We tried steroids (that helped a little), pinching the nose and blowing, decongestants and all sorts.

What Google did for me was to keep going back to doctors with "would xxxx work?". It got me prompting them. Eventually, I tried out some massage, which someone had recommended on groups (that Google found) as a way to relieve the tension. And met a massage therapist who applied some Bowen Technique which solved the problem (the jaw alignment was out after dental work).

I wouldn't use Google alone, but sometimes, doctors don't think of everything. Some of their suggestions were little more than "switch it off and on again".

Re:

Considering that the majority, if not all of Osteopathy is a pseudoscience and treatments like Bowen technique are unproven it's no surprise your doctor wouldn't recommend it. I'd question any doctor who would.

Re:

Seriously, this only attests to the limits of science.

Re:

My doctor didn't recommend Bowen.

Did Bowen work for me? Yes. Absolutely. Has it been scientifically tested? No (although there is some testing being done now).

Before doing my Bowen, I was struggling to concentrate. I would fall asleep at about 8pm, be

Re:Gives you ideas - got to compare it to PUBMED

As a physician who specializes in difficult cases, maybe I can provide a slightly different perspective: What Google has done with Google Scholar has been to incorporate the PUBMED database (a database of all scholarly journals) as well as the database o

What about...

"Google is only as good as it's knowledge base, and it's users, so this isn't a cure for everything."

It might not cure everything, but how does Google fare as a cure for the common cold?

misgivings...

I can think of two somewhat trivial reasons why this could be bad medicine:

Latent Hypochondriacs will type in some general symptoms and find that they have the dreaded newest and hippest malady. I foresee needless worrying and driven-up-the-wall family mem

Another great medical breakthrough!

"For the past 70 years, we used to be wrong only 20% of the time, but now we've discovered a new exciting method which allows us to be wrong 42% of the time!"

The article is full of hype

The article says that the researchers found the correct diagnosis amongst the top 3 found by google in 15 cases out of 26.

In other words, they took a very tiny sample, and then cherry-picked the good results from the bad ones. There's no mention of any serious statistical analysis (why pick 26 as a sample size? why pick 3 results instead of 4 or 5?). And there's no mention of any "control" experiment (e.g. guessing the answer, or perhaps looking it up in a medical textbook). This is a classic example of how to fit the facts to the desired conclusion.

Re:

And even then, it's hardly a 'good' result is it?

What's basically been said is "Google can be used for searching about stuff."

Actually....

...I understood that among the main reasons why doctors misdiagnose as often as they do is because patients rarely use a precise language for describing their symptoms. Also, virtually all medical tests have a percentage of error. Both of these combine

Apostrophe abuse

Zonk, this summary abuses apostrophes badly.

As Dave Barry said, "An apostrophe doesn't mean - Yikes! Look out! Here comes an S".

Tip: It's means "it is".

Re:

Its not like he cares. One thing I can say about getting my news from my local newspaper, at least it's got it's punctuation straight. Duck's in a row, you know?

Thank's,

"The Management"

Don't trust things like this 100%... not even 58%

I hope this doesn't get modded "Funny" 'cause I assure you it wasn't... I've got irritable bowel syndrome, and I'm a bit of a hypochondriac. OK, so not a "crazy thinking I'm ill ALL the time hypochondriac", but I'm very apprehensive. About a year or so ago I had some symptoms (which I won't describe here for obvious reasons...) and decided to Google for them. I spent about 1 week crying (yes, really crying) thinking I had Colon cancer, and about 1 year more to live or so. It took 3 doctors and all sorts of horrible tests (which I won't describe here either .... for obvious reasons...) for me to realize I was being silly and there wasn't anything wrong with me. I can't imagine what my state of mind would've been if, prior to searching for the symptoms, I'd read this on slashdot... I woulds been even MORE sure that there was a 58% chance I had colon cancer and I might've killed myself... So, if you're even a little apprehensive don't EVER google for your symptoms!

Disagree - wrong use

Your first error was assuming you would be able to correctly interpret the data you received.
Data knowledge, that's what doctors study all those years for.

Second error was not to talk to someone competent about your fears - worries grow if not confronted

Re:Don't trust things like this 100%... not even 5

well, as you say it was modded funny, which is a tad strange, anywho;

What you did was right, and maybe it caused you a little worry but it was for the best. Say you had those symptoms and thought (like most people tend to) it'll jkust go away, I'm sure

Only wrong 42% of the time but useless 100%

While it is only wrong 42% of the time, which is about half of the time, it's impossible to know when it is right and when it is wrong. As such it is useless 100% of the time. Now a doctor being only wrong 20% of the time is much more useful, as you can as

So basically you're saying...

...that Google has now made Dr. House obsolite? Seriously, that dude is wrong way more than 54% of the time. Then you don't have to put up with the vicious, cutting sarcasm and depressing world view.

Umm... Google?

I kinda hoped doctors had a better shared resource for such things than Google.

hypochondria

I've been using Google to help me diagnose my medical problems about every day for years now. The only problem that I've run into is that at the top of all my results these days, it says "Did you mean hypochondria?"

This is a very, very important topic, by the way

This idea, that people can list their symptoms and answer questions about how they feel, and receive a diagnosis from a database, is an idea whose time has come. It offers the opportunity, for the first time, for people to have access to knowledge that they need to understand what might be causing ill health, pain and suffering. This opportunity also allows for people to provide information back to the database that can be used to improve it.

It is too often the case that our search for information about alleviating our ill health, diseases, disorders and pain is limited by the amount of money that we have to give to doctors and hospitals. It is too often that the doctors themselves are wrong when diagnosing the causes of our symptoms. It is too often that doctors fail to learn from the mistakes they make when attempting to diagnose ill health and diseases.

It is time for people to be given a mechanism to empower them in the search for good health, a mechanism that does not depend upon how much money they have with which to purchase the opinions of doctors, one which can be improved as it is used.

In virtually every area of human knowledge we recognize that software and databases are used to do jobs that no single person could possibly be able to do, be expected to do, to do these jobs better than, faster than, and at far less cost than any single person could do them. It's time to accept that this is also true of assisting us in understanding the meaning of the symptoms of our ill health, ill nutrition, pain and suffering.

There should be no objection by anyone to the idea that it is anyone's basic right to such knowledge, and that the Internet is the ideal method of providing this.

There's a very old medical condition for which I

was hoping Google could help identify a cure, or at least a treatment. So I entered "megalomania" and "politician". Informative, to be sure, but the only effective treatment seems to involve shooting them until they are dead.

Well google saved my fiancee's life

Specialist put her on a drug that caused her ever increasing grand mal seizures. He kept uping the dosage despite seizures being a contra-indication. She started with occassional seizures and progressed to a couple a day. She'd had previously had brain surgery to remove an araknoid cyst some time before and was experiencing petite mal (blank staring) seizures and narcolepsy. (I now suspect that carbonmonoxide poisoning due to a faulty car exhaust was partly to blame and not the brain injury, nor subsequent treatment but the truth is I won't know). Anyway the drug was also killing her personality and making her moody and erratic. Unfortunately coming off the drug immediately leaves patients prone to being suicidal so we had to bring her down over a period of weeks.

Did the doctor work out what was going on? No the arrogant son of a bitch didn't bother to give the fact that his patient had developed seizures a second thought. Fucker wanted her to stay on the medication. I had googled it, and after we pointed out to him that it was a contraindication and asked to have her come off it for a while, he said okay. Again I'm the one who looked up the fact that suddenly stopping would have made her suicidal.

Three things were re-enforced for me:
1) Yes Google is only as good as the researcher. Using Google to find a specialist site is probably one of the better ways to go. Thing is you have to learn some of the lingo and understand what you're seeing. Takes a bit of plugging away to do that.

2) The medical profession is full of arrogant tossers. The only less practical, more corrupt systems I know of are our legal and political systems. Some doctors are good despite the system. However the system encourages self serving educated idiots who take no interest in themselves (not to mention overworked perpetually tired doctors making life and death decisions). Most doctors don't take kindly to being second guessed, think they know best even when they haven't considered something properly, and think themselves above using technology to diagnose a patient. In the 21st Century the medical profession remains very 16th Century.

3) Get a good doctor and they make you better. Get a bad one and they'll take a minor problem you have and kill you with their incorrect treatment. It is entirely possible to know better than your doctor. In that case you still do need someone medically trained. Get a second or third opinion. Your life can depend on it.

She was deteriorating so quickly that I have no doubt whatsoever that had I not worked out what was wrong with my fiancee she'd have been dead within about 6 months from the time I did work it out (if not sooner). Having a search engine there to be able to research her condition was literally a life saver. Google happened to be king of the hill at the time.

Internet (possibly) Saved My Life

This happened Feb, 2003.

2 months after finishing college and starting a new job in a new area, I woke up one morning with an odd stomach pain. I didn't think anything of it, so I went to work. By lunch time, the pain did not relax at all. It didn't get worse... just a steady piercing pain. I told a co-worker I was taking a half day. By 5pm, I was starting to get really worried because this was not a normal feeling stomach pain, and it was still there.

I went to Google and typed in stomach pain, and that's when I was starting to really get worried. Several websites started directing me to Appendicitis. After reading more, I had all the Appendicitis symptoms except "nauseated". I called a friend, and he said, "Nah, man! It's probably just something you ate! You said you aren't feeling nauseated, right? I'd wait until you were nauseated."

I had crappy insurance. I didn't want to go to the hospital unless I needed to, but since everything I read online was pointing to Appendicitis, I eventually decided that peace of mind was worth an out-of-pocket exam, so I jumped in the car and drove myself to the ER.

I went to the front desk, and he asked, "What do you think is wrong?"
I said, "I think I have Appendicitis."
"All right, fill this out and sit over there."

When I got to finally see a nurse, I said, "I think I have Appendicitis."
"Does this hurt?" "Yes."

When I got to finally a doctor, I said, "I think I have Appendicitis."
"We'll run some tests."

They ran a blood test. Came back positive.
They ran some x-ray type test. Came back positive.

By 10pm, the doctor came and said, "You have Appendicitis." By 5am, they were operating on me.

After one flaming bag of pus removed, and ~$5,000 worth of medical debt, I spent the next week on disability leave playing Final Fantasy X in my apartment. Good game, btw.

Like Dilbert's Scott Adams

Scott Adams was able to outdiagnose his doctors using Google [typepad.com].

It's true

Just last Tuesday I was feeling like a miserable failure [google.com], so I asked Google what the problem could be. I got the right answer in just one click.

self diagnosis = fun!

while at work one day back in 1997 i got these weird blisters on my face. they got worse quite quickly. a fever came. sweats. sitting in my cube i started panicking and typed a search string containing my various symptoms into the search engine of the day at that time, prolly hotbot (!)

the search engine told me that at best i had herpes but more likely leprosy.

my doctor finally returned my call, had me come over, and told me it was chickenpox... ...

can you imagine what a hypochondriac's google search logs might looks like?

I am a doctor and I use Google

But not for this purpose. It's a good resource for handouts explaining diseases in layman's terms. It's also good for diagrams to show patients. And occasionally I'll fire it up if I don't recognize a trade name for a new medication.

But for diagnosis, no. Here are the limitations of this study as I see them. The New England Journal cases are weird, uncommon diseases. They often feature a constellation of uncommon symptoms, such as the example used in the article - IPEX (immunodeficiency, polyendocrinopathy, enteropathy, X linked). If you search for just immunodeficiency and polyendocrinopathy, you will get the answer. This is because those are rare symptoms and their combination is even rarer. You would get the same result on any of the well-traveled medical professional sites. If you had a patient with more common symptoms such as with fatigue, weight loss, and night sweats, the prospects of a successful search are low. Another problem with the study is that diagnosis requires a determination of which symptoms are important. If you search for "immunodeficiency polyendocrinopathy hangnail" you don't get IPEX. The researchers in the study got to choose which features of the disease to include and made sure to search for them in medical language. If they had searched for "immunodeficiency low thyroid" they would get an article about greyhounds. It's the same symptom, but not searched medically (polyendocrinopathy). A final issue is that one of the reason these cases are so hard (they all come from Massachusetts General Hospital, where I've cared for a few of them) is that they take awhile to unfold. Usually by the time they are written up nicely, they are far easier than when only one or two symptoms have developed or when the bloodwork is only half finished. When a case appears in the New England Journal, you start thinking rare things immediately. When it appears in your clinic, you should think of common things first.

Anyway, I definitely think that google (or more likely other diagnostic algorithms) has a role in the future of diagnosis. I don't think that it is anywhere near that point yet. I think the study actually supports that (58% is pretty poor!)

Re:

Did he ever give you a prescription for 'more cowbell'?

Re:

No, they're saying that doctors get it wrong 20% of the time, while a group found that google gets 52% of that 20% right.

Do you really think doctors spend all their time searching for diagnoses on google?

Re:Wow!!! 8 percent better than a coin flip!!! OMG

If you know how to use coin flips to arrive at a correct diagnosis from arbitrary symptoms with a success rate of 50%, you should start getting ready for a trip to Stockholm.