A Blood Test for Brain Damage, and AI Eye Doctors


[INTRO] Concussions are just the worst. Among other things, they can cause massive
headaches, memory loss, nausea, and make you lose consciousness. Not to mention the potentially life-threatening
complications, like bleeding in the brain. So when someone hits their head really hard,
it’s important to know if they have a concussion. And now, the process of figuring that out
will be a little easier. Because last week, the U.S. Food and Drug
Administration approved the first-ever blood test for diagnosing a concussion. Concussions are notoriously hard to diagnose. Doctors mostly base it on symptoms, using
a 15-point scale to check the severity based on things like whether you can open your eyes,
whether you can speak coherently, and whether you can move. All important things. Then, they follow-up with a computed tomography,
or CT scan, which creates a 3D image using X-rays and can show whether any part of your
brain is bleeding, or if it’s swelling. The problem is, CT scans involve a lot of
radiation exposure. A head CT is like getting a hundred chest
X-rays at once, and that can increase your chances of developing harmful DNA mutations
that lead to cancer later in life. Not to mention, the scans only show damage
in about 10% of concussion cases. So as if hitting your head wasn’t bad enough
in the first place, you then have to expose yourself to a bunch of radiation that might
not even tell you whether you have a concussion! There’s a reason doctors do these CT scans,
though. They may not be very good at diagnosing concussions
in general, but they are super useful for detecting brain lesions — the damage that
might mean there’s bleeding or swelling. And you definitely want to know if that’s
happening, so surgeons can go in and try to fix the problem. That’s where this new blood test can help,
because it predicts the results of the CT scan. The test works by detecting two proteins that
appear in the blood within an hour after a brain injury. One is an enzyme in neurons that breaks down
proteins they don’t need anymore, called UCH-L1. The other, known as GFAP, is a structural
protein in astrocytes — star-shaped brain cells that help support your neurons. Normally, if all is well, these proteins stay
inside your brain cells where they belong. But if you hit your head hard enough to break
open some brain cells, the proteins will get into your bloodstream. That’s what this test looks for. Based on the blood levels of the two proteins,
it can predict whether someone’s CT scan will come back positive or negative. The FDA gave the blood test a green light
because, in a clinical trial of around 2,000 people, it correctly predicted the brain lesions
found by CT scans 97.5% of the time. And it was even better at predicting a negative
result. So if you take this blood test and it’s
negative, great. I mean, you could still have a concussion,
but at least you know your brain isn’t bleeding or anything. And you can skip the CT scan because it probably
won’t give you new information. If it’s positive, on the other hand, doctors
will know to do the scan to see what’s going on in your brain. So the blood test won’t necessarily make
diagnosing concussions more accurate. But at least it’ll make the process easier
on patients. According to the FDA, the blood test should
help doctors rule out CT scans in a third of people, if not more. And that will add up, since about 2.8 million
Americans head to the ER every year for concussions. So hurray for less radiation! — If blood tests will soon be handy for concussions,
how about something that sounds even more futuristic: using artificial intelligence
as doctors! This week, an international group of scientists
unveiled their latest effort to use AI in medicine. Specifically, they programmed a system to
diagnose eye diseases that can lead to blindness, like age-related macular degeneration, where
the center of the retina starts to get damaged. The best way to diagnose these types of diseases
is with an imaging technique called optical coherence tomography, or OCT, which uses light
to create a 3D map of the retina. If the scan shows deposits or fluid buildup,
you can use that to diagnose the problem. In some cases, doctors can then start treatment
right away. The researchers wanted to see if an AI could
make the same calls. So they programmed a type of artificial intelligence
known as a neural network. A neural network is basically a bunch of interconnected
processing units set up to analyze data in a way that lets the system learn for itself. To train it, you just give it a bunch of examples
of whatever you want it to learn — in this case, 100,000 OCT scans. The then AI comes up with its own rules for
solving the problem — here, how to link what’s in the image to the correct diagnosis. Then, when you give it a new example, like
an OCT scan it’s never seen before, it uses those rules to figure out the most likely
answer. Neural networks are used in some of the most
advanced AI in the world, and this isn’t the first time they’ve been trained to diagnose
diseases. What’s different about this system is that
the researchers only needed 100,000 OCT scans to train it, whereas most neural networks
would need millions of examples. They did that by using something called transfer
learning to create a shortcut, basically borrowing some of the knowledge from another program
and applying it to this new, more complicated problem — diagnosing diseases. In the end, this new system could diagnose
the eye conditions in 30 seconds with 96.6% accuracy, on par with eye doctors. The computer even outperformed 2 of the 6
experts in the study. While these researchers focused on eye diseases,
they also trained the system to tell the difference between bacterial and viral pneumonia in chest
X-rays. And the same basic approach could be used
for pretty much any other image-based diagnosis. It will probably take a while before AI like
this becomes standard in medical treatment. But once it is, it’ll allow patients to
be diagnosed more quickly and easily, especially when there’s a shortage of specialists. We have seen the future of medicine, and it
is now. Thanks for watching this episode of SciShow
News, and a special thanks to President of Space fSR Foxley! It’s wonderful to have his support and the support of all of our patrons. Thank you so much for helping people get this And for helping us make it [ OUTRO ]

100 comments

  1. In a future video, can you talk about the flu vaccine Japan is trying out? The one that purports to get rid of the flu in 24 hours.

  2. Thank you SR Foxley, and thank you Hank Green and all the wonderful people at SciShow who are constantly keeping us up to date with relevant science news.

  3. Did you copy the t-shirt and blazer look from Cenk Uygur? Maybe you have been doing this a long time, but that particular t-shirt is rather distracting so I just noticed now.

  4. I hate to be that guy, but as a radiologic technologist it bothered me that you showed a slice of a chest CT when talking about head CT's

  5. Nice! I love neural networks:D im working to a Neural network to reproduce human conversations for my thesis, it's just amazing,
    the only problem on using neural networks for medicine is that they work as a "black box" , basically they give you the answer, but you have no way to see how they got to that answer, which might be a problem when diagnosing a desees, when you want to know why the ai think the patient is sick… a decision tree could be a better way

  6. It's the 21st century! Why don't I have an AI telling me accurately that it's going to be a nice, sunny day on Friday!?

  7. I fell on the back of my head once in school in 7th grade during PE and was taken to the nurse and told to stay home and go get a check in at the doctor's.

    I didn't go to the hospital and waited for the pain to subside

    3 years since then, I sometimes feel a sharp "phantom pain" from the impact and it makes my fragile brain shiver. My mother says my short term memory hasn't been as great as before that incident. Could I have possibly been harboring an ischemic stroke all this time?

  8. Both news make medicine quicker and cheaper. I'd have loved to see that pointed out since medicine need as much cost reduction as we can give it.

  9. For those who are interested, the 15 point scales John mentioned earlier in the video to detect brain damage is called Glasgow Come Scale.

  10. I am an orphan child, my channel is what makes me happy, and only my channel, brother and the rest of my family stay with you. I hope you subscribe to my channel. Believe me, this will make me happy. I know you are good people. I hope you subscribe to my channel.😢💔

  11. I have a question I have a leopard gecko it looks at my phone when I play videos does it see what I see what do leopard geckos see when they look at a TV screen or a phone?

  12. I got a concussion last summer and a CT scan (none of which I remember, it was a bad one) and it cost my family a lot of money that we don't really have, and the fact that it increased my risk for cancer (I have family history of cancer too) makes me very glad that a blood test could replace it for other people

  13. @SciShow Working with doctors in the Emergency Department, I learned that there are simple rules that the physician can follow to determine if the patient has a concussion. One of such rule sets is the Canadian Head CT rule set which is a robust rule set. Patients are given CTs mainly for liability and to make the patient feel comfortable.

  14. I've long wondered what SR stood for. Now, thanks to Hank's shirt, we know our beloved President of Space is none other than the famous luchador Señor Foxley. Gracias, señor.

  15. It took me 2 months be diagnosed with post concussive syndrome, which lasted almost a year. I didn't even know I had a concussion before then

  16. Could you do a video on the new research in Myalgic Encephalomyelitis? It's a common, but little known and highly stigmatized health condition. It would be awesome if you could help raise awareness.

  17. I met a team that's working on a visual system to test for concussion. Initially, it's to be deployed in sports, because it currently requires a known baseline for the person being tested, but they think that a healthy level will be found with continued use (like having a healthy blood pressure range).

    This test forces a blink reflex (air puffs) and records the blink in slow motion; depending on mental state, blinks happen with greater or less latency, for varying duration, and are more or less aligned with each other. It was found that people who've suffered a concussion had significantly less blink latency and were less connected to each other. Conversely, athletes in the middle of a game show the opposite reaction (higher blink latency at closer to the same time), so they are confident that it can quickly and accurately detect head injury in a player, allowing them to get back onto the field faster if they're fine or pull them from the game if they're not.
    Currently, the tests used in sports aren't very consistent and are easy to cheat (athletes purposely underperform on their baseline so they won't be taken out of a game if they're injured).

    One of the Ph.D's working on this project (on the medical side of it) told me that they hope this device can be used to detect other forms of brain damage or disease (early detection of Alzheimer's and Parkinson's for instance) once they have a better pool of data to compare it too, since the blink reflex is a fairly complex one that requires multiple parts of the brain and nervous system to perform and is sensitive to both damage and neural transmitter levels.

  18. Please add me to the list of folks that understand very well how much of a difference SR Foxley is making in the world. This community is the beginning of a whole new culture and the value of your support can not be over stated.

  19. That brain damage test is amazing!I wonder what instruments is it run on and what is the procedure for it? Always exciting to get my lab hands on a new test!

  20. Hank! What about fmri? Not just as it pertains to this subject(ie what use could they be put to?) but also in general? Please consider doing a video on fmri.

  21. Had to explain why you would test for GFAP in the blood following a concussion on an exam just this past week. I needs you earlier!! However, I do think I said something like what you said. 🤞

  22. Sorry Hank, you got the concussion diagnosis a little off. The 15 point Glasgow Coma scale is for rating consciousness not soley concussions. You don't need to be knocked out to have a concussion from my experience as an Athletic Training student. Evaluation I've seen has been with a combination of but not limited to ImPACT tests, VOMS testing, and SCAT 3 or newer SCAT 5 (which does have a small section for the Glasgow scale). Also even though there is a chance of brian lesion or bleeding the vast majority of patients from sports don't need a CT unless they have severe symptoms or worsening symptoms. Also fun fact, current research is showing that making a person with a concussion sit in a dark room for days is worse than normal activity that don't exasperate symptoms. There is plenty of more info on the NATA website and the NATA concussion protocol.

  23. With the national average cost of 1200$, varying GREATLY depending on which area you live in. But we'll just skip over the potentially political subject matter of healthcare.

  24. nice test
    can used in the area that not have CT scan like villages or in poor countries like a lot of places in Africa to decrease the cost of imaging .

  25. Disappointing! Apparently, the blood test only determines one form of brain damage – concussion. But, it doesn’t determine whether or not a person has other forms of brain damage – like having the brain deprived of oxygen for a prolonged period of time. The reason this matters is because I’ve been diagnosed with both dementia and brain damage – by different doctors. It would be nice to know if I have one or the other – or maybe something else, like mental illness.

  26. Hank, Stop bad mouthing medical radiation. The odds of anyone getting cancer is about 1 in 5, no matter your risk factors. Medical radiation is a concern, but a much more minor than your assessment.

  27. These AI systems could be useful in double checking a human dr's analysis of a scan! I once was hospitalized with sepsis-had a CT of my abdomen right away. My results were "normal". Well-3 days of suffering and fever later, they had another dr look at the same scan, and I had a kidneystone stuck in my ureter!! REALLY bad mistake! My kidney was really infected at that point! I was pretty angry about that, but I was too sick to complain. I needed two surgeries to deal with the problem…

  28. My father is a head injury survivor-head injuries are not something to mess around with! If you are doing anything that you should wear a helmet for-WEAR IT! Sadly my dad simply slipped on a slippery entryway, and whacked his head on concrete. It was an extremely long road to recovery, and he still suffers from certain impairments. Good news is that, with alot of effort and help, he has regained some ground. Neuroplasticity is amazing!

  29. Doctors do not always check a CT scan unless concern for bleeding in the brain is of concern. The image of a CT scan you showed was of a chest, not a head.

  30. Hit my head at work now have post concussion syndrome and cant sleep cant walk straight cant concentrate, doctors treat me like im chasing dope and all i want is to be normal again …………………..

Leave a Reply

Your email address will not be published. Required fields are marked *