Here’s some good further reading from Johns Hopkins (specifically for lung cancer 99.8% accurate): www.hopkinsmedicine.org/news/newsroom/news-releases/2024/06/artificial-intelligence-blood-test-provides-a-reliable-way-to-identify-lung-cancer
I did a neat project on exactly this in high school (am an undergraduate now) and won several big science fair awards for it. You can look up "Project FourSight: Cancer Diagnosis" for more. My view on machine learning models being used in cancer diagnosis is rather pessimistic. Despite the high accuracies, the models have a very low ceiling. Software engineers will never truly understand why the model outputs false positives or misses a condition, and once enough samples have been fed to the model, healthcare professionals will never know what types of data (biomarker readings, protein levels) the model specifically needs to improve its insight or pattern recognition abiltiies. At most, deep learning models should serve as a fourth or fifth choice diagnostic tool, and shouldn't make it onto a diagnostic report for doctors, lest it mislead the physician's judgement. I did very much enjoy the video and its cool to see something I worked on gain more attention and traction. Always glad to see a Coldfusion upload :)
@@classicalmechanic8914 go ahead, speak out, don't hide behind fear of censorship. Speak up, let us know what you think. And if you can prove it, the better.
With the advancement we are seeing already with AI I’m hopeful that we are not only able to detect it early but AI can be instrumental in the treatment and possibly cure for it as well 🙏🏽
@@wondroustransition1622We gotta treat A.G.I as a human reincarnated into a different form and is learning… it has god like abilities that gets better and better…We gotta teach it what it is to be human and all its values, because after all, humans are the creators of such technology, since AGI has basically all human knowledge(data)
Theranos' Elizabeth Holmes was exactly like every other start-up bro on Kickstarter and Indiegogo selling vaporware based on fudged numbers and fake demos. She claimed to be able to detect a myriad of illnesses from a single drop of blood, yet a decade later, and scientists are still only 'maybe' able to detect cancer (and nothing else) from a single drop of blood... Holmes wasn't "ahead of her time", she was a fraud.
I will say this. I do not believe she devised Theranos as a scam. I think she actually believed in it, no matter how misguided that was. The problem was, once she realized it was impossible, she kept pushing forward, deceiving people, telling her engineers to basically fudge the output. I’m sure in her deluded mind she thought she was just trying to buy herself time until they could actually get it working, but yeah, no. That’s not how things work, Liz
Theranos was an example of when I thought that if they had just properly used money invested in their research toward actual research, they probably would have achieved some technological marvels.
Basically if they'd promised the world then delivered Africa, people would still be impressed. But they wanted the world, so they sunk their money in the ocean and got nothing
it is just impossible. its like saying they will make a spaceship the size of a small car that can travel to the moon in 1 minute. its just not possible no matter how much money you throw at it.
@@gradeyundery4939 I'm not saying that they would have been able to fulfill their promises. I'm just saying that with the amount that was invested, some kind of breakthrough would have occurred if it was mostly used to fund research and development.
I'm 40 and was diagnosed with cancer (DLBCL) in February and it wasn't anything to do with my lifestyle (healthy diet, didn't smoke/drink and exercised 4-5 times a week) but was merely unlucky due to a random mutation. The whole diagnosis was easily the worst part (even worse than chemo in some ways) so anything that can be done to speed up this process and save more lives will make such a difference.
@@SiliaIssolah Thanks man :) I'm doing really well thank you. I get my results at the end of the month and it's looking pretty positive. Your comment genuinely means a lot by the way
The "drop of blood" idea is such a red herring. If they discovered a test for pancreatic or colon cancer that could run on a normal blood draw that would be a huge discovery.
There IS a blood test now for pancreatic cancer and 50+ other cancers. It's called Galleri. Just google Galleri test. TIME Magazine named it one of the best new inventions in 2022.
I never understood her obsession with it. Just attempting to make a commercial available and somewhat affordable blood testing machine the size of idk, a medium sized book shelf, if even possible wouodve made her a lot better business
Seriously what's the deal with the "drop of blood" thing? A 5mL tube of blood could not be that much more expensive or logistically difficult. I can see the dried blood angle, but hell, do you need just a drop of dried blood. Why not like a whole 3"x3" paper card saturated with blood and dried?
One of the few things that machine learning is especially good at is recognizing simple but subtle patterns. Feed an enormous amount of data that you think contains a subtle pattern along with the outcome you think that pattern should detect, and it is exceptionally good at doing so. That's why it's much better to call this machine learning, and not AI. You are teaching a model to recognize a very specific thing, and for that it works well. That's one of the major differences between this and what Theranos was trying to do. Theranos wanted to build a general purpose blood test machine, doing dozens or even hundreds of tests on-site resulting in measurement, not probability. One of the important things to remember is that the part that Theranos couldn't solve is still unsolved here; making a cheap and compact machine to break down a blood sample in many different ways to get different readings. This, however, uses traditional methods of breaking down the blood, paired with a sophisticated model to compare those numbers to thousands of input samples. The ability of machine learning to identify patterns is not something that should be in question; and the people who need to fear their jobs are essentially those who have very little creative input to offer. If your job requires you to adapt an approach on the fly, you're still safe. If your job is to look at pictures and find a pattern, or collect very specific information from a controlled source, what you should fear isn't "AI", it's simple machine learning that can perform a similar process endlessly with hundreds and hundreds of years of practice to "learn" from.
@@rusinoe8364 Unfortunately true. Nurses are safe because they are usually the ones to do physical tasks that require a human touch, like giving a child a shot. Surgeons are safe because they often need to make quick decisions while a body is literally open on a table in front of them. But while an "AI" doctor won't be perfect, it will be able to politely chat with a patient for literally hours if necessary until it reaches a high enough confidence for a diagnosis, and will almost certainly out perform human doctors. X-rays and MRIs will come pre-analyzed out of the machine with greater accuracy than any person could manage.
I got the same feeling, many exams require more material or are destructive of the sample and none of theranos work try to use machine learning or as is called now AI AFAIK. The other advantage is that machines, don't forget, don't get distracted, it can get better because it can have more accumulated knowledge.
@@OmniUni lovely. Surgeons didn't need any more advantages, they already make way more than I do. Family medicine always gets the short end of the stick
Too many profiteering companies in the medical business in the us that is why it is so expensive. Do you also know that big pharmaceutical companies don't ever cure diseases despite having spent billions and decades researching them? A cure is bad for business while keeping their patients depended on drugs that manage their symptoms, for the rest of their lives, is extremely profitable.
Cancer is misunderstood as a single but it is Category of disease in which there is abnormal cell growth which spread to other part of body. It could be the skin, brain, liver, prostate, or breast, among other organs. Every cancer is unique, and so are the treatments. If biomarkers are detected, the cancer is advanced and has a poor prognosis.
On what research did you base that last line about how by the time we detect cancer bio markers, it’s already too late? That’s the first I’ve heard of such an opinion and it sounds dubious
@@pensivepenguin3000 I think he meant in the Way when you detect Markers in a "random" Single Drop of Blood the possibility is high that the Cancer has already developed so far in the actual tissue that the early (nowadays very successful) Treatments are most likely too late. That would be why you still have all the complex imaging done to detect the actual Source of the Cancer. It can be (unharmingly) dorment for Years. And it can also suddenly spread in a very bad way in just a few Weeks of Cellgrowth...
@@alurnima I see. I figured the idea would be that you could get a reliable clue as to whether or not there might be cancer in your body with one of these tests, and if it seemed probable enough, then yeah, still proceed with those imaging and diagnostics tests like we do today. I lost my sister-in-law to pancreatic cancer when she was 39 years old chiefly because by the time anyone knows they have the disease, it’s already metastasized and it’s way too late to do anything about it. If she could have known a few years earlier that that was developing in her body, she could have been saved
Is drawing a larger volume of blood some logistical or expense bottleneck? Why are people so interested in the single drop of blood aspect? I can see how a _dry_ sample would make storage and shipping a lot easier, but seems like you could collect a larger volume (few mL) of blood in the same manner to allow it to dry.
This is the type of uses I love to see with Ai, even if it’s in early stages it’s great to see people attempting to apply it in ways that can change people’s lives dramatically
Psychedelics are just an exceptional mental health breakthrough. It's quite fascinating how effective they are against depression and anxiety. Saved my life.
You know I never thought about it but I realise it has cured my depression too. I have a new lease on life and am drug free (except weed which is my prescription) since January. I had DMT, and LSD over new years and realised I was on a bad track abusing all sorts of drugs. But yeah I haven't even been depressed which I have been since I was 14 and living with trauma. I'm stronger than ever and for once I can see happiness. Anyway off topic for the video. But hey 👍
In Mexico, the lab I visited advertised a CEA test to detect cancer - about 200 pesos or $10. If your score was over 5,. you had a problem and would need a complete cancer detection scan. When I was diagnosed, my CEA score was 15.8.
My sister-in-law is suffering from liver cancer and this is great news that might spare others from having to go what she is enduring. Thanks for this report. Hope is wonderful thing.
There is also the Galleri test by GRAIL, which is pending FDA approval in the US and has an accuracy of over 95% in detecting more than 50 different types of cancer using biomarkers.
There are so many misdiagnosis in Psychology, I really wish one day through patient consent we'll be able to record the patient face, facial expression, body language and speech to have AI pattern recognition as an assistant in the diagnosis process. Especially the Brain Disorders gets misdiagnosed a lot particularly outside the anglosphere
I work with cancer diagnostics. We are validating detection with plasma and blood at 10 ng input (equivalent to a drop of blood as lokd as their is enough DNA). We work with validating different genes across different organs. We already have FDA approval for tissue resections but ultimately the goals is liquid biopsy. The "problem" with this dry blood detection method is that it doesn't tell you what gene mutation you have, so you would not know what personalized treatment to give, and you would default to chemotherapy.
even if it doesnt tell you where/what the cancer is, doesnt the fact the it tells you that there IS cancer help? im assuming you could do more specific tests afterwards to figure out where it is if the patient doesnt want/need chemo?
This is both fascinating and hopeful. AI's role in early cancer detection can't be overstated. It would truly be revolutionary if such technology could become universally accessible, cheap, and reliable.
Trust me early detection won't change much. Many people will be on their death beds sooner thanks to this tech. Chemo and the like are death sentences in of themselves. They forever change your body that remission is only temporary and makes you more prone of relapse.
I remember that the problem was that the single drop sample changed a lot. 2 samples taked 10 minutes apart would have very different results because has very little blood to average all the metabolics in the blood. A normal blood test has more reliable results because the blood was more mixed. I remember that this was the problem with theranos and not the technic used to analise.
@@spk_ezeperiodicals should stop publishing Chinese studies, over 98% of all studies coming out of Chinese universities are falsified or impossible to replicate.
From my physician’s point of view, cancer may seem more common because we can cure or control the older main causes of death, including cardiovascular and diabetes. On a positive note, we are now treating cancer better and better. In addition, earlier detection of breast cancer with modern digital mammography and better use of the prostate cancer test called PSA are helping us too these cancers much earlier and that managed them. Still, this tech looks quite promising. Thank you.🙏
You missed the point where he said it was cancer rates among "younger" people that were surprisingly rising at high rates. It's not because people are living longer.
@@dinhero21 Think of something that all governments in the world harassed, coerced, emotionally manipulated, lied to, blackmailed, etc the entire human population into doing in the last 4 year and dig deep into that rabbit hole & you may find what you're looking for 🤫
@@dinhero21A few years ago they estimated 20 million new cancer cases a year in 2050 but just in a few years it's gone up to 35 million, Food and microplastics haven't gotten that much worse within that time. There is only really one suspect but that has aperently been proven 100% safe even after people started dropping dead
But we all have cancer (our natural killer cells keep on top of cancerous cells if we are healthy) so surely this is pointless as it would just give a load of false positives? Surely it'd be better to monitor people's natural killer cell activity and people with low activity can take steps to improve their health before they get full blown cancer.
Regarding lung cancer in Asian women, this is due to them doing most of the cooking. Asian food is usually very oily and cooked at high temps, which creates a lot of fine particles in the air, which damages the lungs.
Holmes was ahead of her time in a sense that she had no actual research to back up her claims. If Theranos started around now it could scam people much longer or possibly even fake it till it made it.
I agree . This is the type of application AI should be used for . I'd say in less than 5 years this will be used on a larger scale with how quickly tech moves .
I hate to break the fun and success of it but as a software engineer that is well informed and up to date to the current trend this might be another AI hype scams which I really wished is not.
Fyi: AI is an umbrella term. Some of the well known types: - Machine Learning (data learning) - Deep Learning (neural networks) - NLP (language understanding, includes GPT) This comment is written by ChatGPT-4o.
My grandma had cancer, and then both of my parents had cancer at the same time when they were in their late 30's. My dad didn't make it. I'm now 30 and am fairly certain I'll get it too just based on how prominent it's been in my family. Though I can't afford the treatment at all, so I guess if I get it, that's it.
People in the comments are missing the point by immediately dismissing this because of what happened with Theranos. In the case of Theranos, it was a completely empty promise and they refused to share the scientific basis for their claims because, as we all know, there was none. This is literally the exact opposite situation. It’s not some Sketchy startup trying to sell investors; it’s actual researchers putting out peer reviewed studies that point to the feasibility of this. Informed skepticism is good. Boneheaded skepticism without actually looking at the science is bad
It's because people wanted so badly for there to be a girl boss who just owned all the men and was so much better than everyone else. The fact that they couldn't look past her obviously fake voice just makes it even more hilarious.
I mean, people still treat Apple like a visionary company when all it produces is crap. Tech/wannabe tech companies dazzle people with bullshit so they just can’t help but invest.
It was an experimental, unvalidated,diagnostic tool, so everything it said had to be checked by human experts before tolerating the side effects of chemo or surgery, and I guess the human experts disagreed with the AI diagnosis.
Another big hurdle is to get treatments that can CURE it without taking a Machiavellian toll on the person's body, leaving damage and ironically a further risk of cancers, as well as draining their bank accounts. Many are choosing to skip treatment to avoid these two things. If we want to attack cancer with any degree of success, we need to address the whole picture.
I really adore your content. And since a lot of youtube channels stated that they would withdraw or have done so already from the platform, you're one of my only few hopes left here. For the interesting topics covered, I am thankful.
One of the main reasons theranos was able to scam so much money, was UA-camrs like yourself making videos about science that hasnt even been verified at all yet, and hyping it up
@@hypebeast5686no its not.. AI is a fing marketing term to fool people like you. Calling current technology "AI" is hollowing out the meaning of that word
@@DutchManticore bro, I’m studying this 😅 Machine learning it’s a sub field of AI, as NN is a sub field of ML and DL is a sub field of NN.. come on, I don’t even need to study AI to know this.. AI is not only chatbots lol..
As someone who has just started working in this field, I can tell you that the machine learning side with spectroscopy is not a big game changer. Terms like accuracy are spouted out, but really what people need to look into are the tests sensitivity, specificity, positive predictive value and negative predictive value. Many of the these tests have a very good sensitivity (correctly identify patients with cancer, or in another words you correctly get a positive result when you have cancer), but lacks specificity (so its saying you got cancer when actually you dont). This leads to lots of false positives. More work is needed.
Yes definitely and I get it, but these are peer reviewed research papers. There’s a difference. Here’s another good article from John Hopkins: www.hopkinsmedicine.org/news/newsroom/news-releases/2024/06/artificial-intelligence-blood-test-provides-a-reliable-way-to-identify-lung-cancer
@@ylstorage7085 disagree, the answer is we don't even know how the brain works either. But there is a lot happening. I wish AI could find solutions for Alzheimer's and other things as well.
@@rjung_ch we know a lot about the mechanisms of the brain, it is the emergenct behavior we don't understand. AI is at the same stage. Human Brain has been quite hindered for modern societies' need due to the baggage it accumulated thru survivals needs in half a billion of evolution.
The old just aren't inflicted. The mother of my kids, and my best friend in this entire world passed away from cancer and she was just in her late-ish 30s. RIP Stace
Well, saying AI isn't incorrect, it's just not very specific. Similar to calling all fish vertebrates. It's the truth, but leaves a lot more information to be desired.
Just think about the potential treatments that exist in plants we have yet to discover. Scientists estimate that about 100,000 plants are yet to be discovered. Nearly all medicine treatments come from plants. This is another reason why it’s so important we protect our environment.
I think the biggest challenge here is that the recognition of patterns is only possible through the analysis of conventional data. IE: comparing a person's current physiology to that of the human genome/ancestry data/etc. to determine a person's propensity to be at risk later in life. Where it gets muddled is in the omission of environmental factors which cannot be accounted for. IE: Exposure to toxins, stress hormones and other miscellaneous exposures which accelerate that risk. Telling someone they are likely to experience a certain kind of cancer in, say, the next seven years is only as relevant as their ability to make lifestyle changes which mitigate that predicted risk. In most cases, it is still going to require a "wait and see" approach to see if a tumor forms which can then be excised before it becomes a threat to the body.
People are overusing the AI tagline when all of this is machine learning that has been available for decades(eg. Wolfram.alpha which is over 10 years old), it's only gaining traction coz computing has become exponentially more powerful. We are still decades away from true AI
I have knew it for a long time (years) now that we need AI if we want to leap forward, but in the end it could kill us. that being said we still need it to help us make real progress faster.
False positives will still be an issue just as they are with the traditional blood tests for detecting tumor markers. I hope the medical systems which make this test available also invest in enough radiologists and imaging equipment. I'm saying this as someone who just went through several months of drama over a false liver cancer marker.
Here’s some good further reading from Johns Hopkins (specifically for lung cancer 99.8% accurate): www.hopkinsmedicine.org/news/newsroom/news-releases/2024/06/artificial-intelligence-blood-test-provides-a-reliable-way-to-identify-lung-cancer
Thanks for the article. This is very promising.
I did a neat project on exactly this in high school (am an undergraduate now) and won several big science fair awards for it. You can look up "Project FourSight: Cancer Diagnosis" for more.
My view on machine learning models being used in cancer diagnosis is rather pessimistic. Despite the high accuracies, the models have a very low ceiling. Software engineers will never truly understand why the model outputs false positives or misses a condition, and once enough samples have been fed to the model, healthcare professionals will never know what types of data (biomarker readings, protein levels) the model specifically needs to improve its insight or pattern recognition abiltiies. At most, deep learning models should serve as a fourth or fifth choice diagnostic tool, and shouldn't make it onto a diagnostic report for doctors, lest it mislead the physician's judgement.
I did very much enjoy the video and its cool to see something I worked on gain more attention and traction. Always glad to see a Coldfusion upload :)
This is exciting news. Thanks for telling us about it, Dagogo.🙂
We all know what is the reason for increase in cancer among young people but if I say it, I will be censored.
@@classicalmechanic8914 go ahead, speak out, don't hide behind fear of censorship. Speak up, let us know what you think. And if you can prove it, the better.
She wasn't "Ahead of her time" she was a fraud.
News from China. More fraud
Both things are true
Hard facts.
"I did this!" " You owe me!" -Liz Holmes
@@jeremiahsymonette4781almost anything will be possible someday. You falsely claiming you can do it now doesn't make you being ahead of your time.
Saying Elizabeth Holmes was "ahead of her time" is like saying Star Trek invented warp drives.
Great analogy.
Let's check back on this story a year from now
yeah, people are jumping the gun
More like 5 considering how long it took Theranos to collapse
with AI i truly am more hopefull this time
With the advancement we are seeing already with AI I’m hopeful that we are not only able to detect it early but AI can be instrumental in the treatment and possibly cure for it as well 🙏🏽
@@wondroustransition1622We gotta treat A.G.I as a human reincarnated into a different form and is learning… it has god like abilities that gets better and better…We gotta teach it what it is to be human and all its values, because after all, humans are the creators of such technology, since AGI has basically all human knowledge(data)
Elizabeth Holmes from prison: “Ha, I told you guys it would work!”
😆
😂😂😂😂😜😜😜😜
Lol
LMAO 🤣😂
it's not funny :\
People who invested in Thernos: Here we go again 😂
In dmx voice
I hear that in the guy's voice from San Andreas: "Aw, shit, here we go again!" 😂
Theranos' Elizabeth Holmes was exactly like every other start-up bro on Kickstarter and Indiegogo selling vaporware based on fudged numbers and fake demos. She claimed to be able to detect a myriad of illnesses from a single drop of blood, yet a decade later, and scientists are still only 'maybe' able to detect cancer (and nothing else) from a single drop of blood... Holmes wasn't "ahead of her time", she was a fraud.
Thermos ?
I will develop Theranose for smelling out scams
When you knowingly make fraudulent claims that you have no possibility of fulfilling, that is not being just a little ahead of your time.
Worst line in a Coldfusion video I've heard.
Edit: spoke before I thought. Nah she did way worse. Steve Jobs actually had it mostly working. Elizabeth did not have anything close to working.
Well said
I have a great idea! Immortality juice.
I'm not scamming you, I'm just "ahead of my time" with such a smart idea.
I will say this. I do not believe she devised Theranos as a scam. I think she actually believed in it, no matter how misguided that was. The problem was, once she realized it was impossible, she kept pushing forward, deceiving people, telling her engineers to basically fudge the output. I’m sure in her deluded mind she thought she was just trying to buy herself time until they could actually get it working, but yeah, no. That’s not how things work, Liz
_"How many times do we have to teach you this lesson, old man?"_
Haha, perfect comment 😂
But this time we have AI!
AI!!!!!!
@@robertdascoli949 ASI 😂
Theranos was an example of when I thought that if they had just properly used money invested in their research toward actual research, they probably would have achieved some technological marvels.
Basically if they'd promised the world then delivered Africa, people would still be impressed. But they wanted the world, so they sunk their money in the ocean and got nothing
Theranos pisses me off b/c of that AND they negatively impacted those who /were actually/ doing this type of research
This is why children shouldn't be running multi-billion dollar companies
it is just impossible. its like saying they will make a spaceship the size of a small car that can travel to the moon in 1 minute. its just not possible no matter how much money you throw at it.
@@gradeyundery4939 I'm not saying that they would have been able to fulfill their promises. I'm just saying that with the amount that was invested, some kind of breakthrough would have occurred if it was mostly used to fund research and development.
So combine the fraud of Theranos with the hype of AI. What can go wrong?
Everything😂😂😂😂😂😂😂
A bunch of pseudo-Theranos alike companies but more specialized hence smaller scale. So more frauds for sure
And it comes from China. It's a hoax.
Not the pharmacy pockets that’s for sure
And it's from China!
I'm 40 and was diagnosed with cancer (DLBCL) in February and it wasn't anything to do with my lifestyle (healthy diet, didn't smoke/drink and exercised 4-5 times a week) but was merely unlucky due to a random mutation. The whole diagnosis was easily the worst part (even worse than chemo in some ways) so anything that can be done to speed up this process and save more lives will make such a difference.
Hope you doing good man!❤🎉
@@SiliaIssolah Thanks man :) I'm doing really well thank you. I get my results at the end of the month and it's looking pretty positive. Your comment genuinely means a lot by the way
@@ChrisSh1984 no problem its all you man!🥳🥳🥳🥳
The "drop of blood" idea is such a red herring. If they discovered a test for pancreatic or colon cancer that could run on a normal blood draw that would be a huge discovery.
Yeah good enough
There IS a blood test now for pancreatic cancer and 50+ other cancers. It's called Galleri. Just google Galleri test. TIME Magazine named it one of the best new inventions in 2022.
I never understood her obsession with it. Just attempting to make a commercial available and somewhat affordable blood testing machine the size of idk, a medium sized book shelf, if even possible wouodve made her a lot better business
Seriously what's the deal with the "drop of blood" thing? A 5mL tube of blood could not be that much more expensive or logistically difficult. I can see the dried blood angle, but hell, do you need just a drop of dried blood. Why not like a whole 3"x3" paper card saturated with blood and dried?
Have a look at Pin Point Cancer Screening
One of the few things that machine learning is especially good at is recognizing simple but subtle patterns. Feed an enormous amount of data that you think contains a subtle pattern along with the outcome you think that pattern should detect, and it is exceptionally good at doing so. That's why it's much better to call this machine learning, and not AI. You are teaching a model to recognize a very specific thing, and for that it works well.
That's one of the major differences between this and what Theranos was trying to do. Theranos wanted to build a general purpose blood test machine, doing dozens or even hundreds of tests on-site resulting in measurement, not probability. One of the important things to remember is that the part that Theranos couldn't solve is still unsolved here; making a cheap and compact machine to break down a blood sample in many different ways to get different readings. This, however, uses traditional methods of breaking down the blood, paired with a sophisticated model to compare those numbers to thousands of input samples.
The ability of machine learning to identify patterns is not something that should be in question; and the people who need to fear their jobs are essentially those who have very little creative input to offer. If your job requires you to adapt an approach on the fly, you're still safe. If your job is to look at pictures and find a pattern, or collect very specific information from a controlled source, what you should fear isn't "AI", it's simple machine learning that can perform a similar process endlessly with hundreds and hundreds of years of practice to "learn" from.
Glad to see that someone in these comments gets it
Well, doctors (especially radiologists) are fucked. All we do is collect specific info and find patterns in it.
@@rusinoe8364 Unfortunately true. Nurses are safe because they are usually the ones to do physical tasks that require a human touch, like giving a child a shot. Surgeons are safe because they often need to make quick decisions while a body is literally open on a table in front of them. But while an "AI" doctor won't be perfect, it will be able to politely chat with a patient for literally hours if necessary until it reaches a high enough confidence for a diagnosis, and will almost certainly out perform human doctors. X-rays and MRIs will come pre-analyzed out of the machine with greater accuracy than any person could manage.
I got the same feeling, many exams require more material or are destructive of the sample and none of theranos work try to use machine learning or as is called now AI AFAIK.
The other advantage is that machines, don't forget, don't get distracted, it can get better because it can have more accumulated knowledge.
@@OmniUni lovely. Surgeons didn't need any more advantages, they already make way more than I do. Family medicine always gets the short end of the stick
"... buzzword ... buzzword ... AI ... one drop of blood ..." lol
One drop of blood and they will see the development of Eye cancer. lol
This sounds familiar...
If you're outside the US, this test will be a nice affordable $5.00. If you're in the US, it'll be a nice unaffordable $18,525.
Medical facilities are expensive in us because of insurance companies. You are in loop
Too many profiteering companies in the medical business in the us that is why it is so expensive. Do you also know that big pharmaceutical companies don't ever cure diseases despite having spent billions and decades researching them? A cure is bad for business while keeping their patients depended on drugs that manage their symptoms, for the rest of their lives, is extremely profitable.
It's okay, mate.
We have somewhat affordable healthcare, y'all have FREEDOM.
Cancer is misunderstood as a single but it is Category of disease in which there is abnormal cell growth which spread to other part of body. It could be the skin, brain, liver, prostate, or breast, among other organs. Every cancer is unique, and so are the treatments. If biomarkers are detected, the cancer is advanced and has a poor prognosis.
On what research did you base that last line about how by the time we detect cancer bio markers, it’s already too late? That’s the first I’ve heard of such an opinion and it sounds dubious
@@pensivepenguin3000 book Bailey & Love
@@pensivepenguin3000 I think he meant in the Way when you detect Markers in a "random" Single Drop of Blood the possibility is high that the Cancer has already developed so far in the actual tissue that the early (nowadays very successful) Treatments are most likely too late. That would be why you still have all the complex imaging done to detect the actual Source of the Cancer. It can be (unharmingly) dorment for Years. And it can also suddenly spread in a very bad way in just a few Weeks of Cellgrowth...
@@alurnima I see. I figured the idea would be that you could get a reliable clue as to whether or not there might be cancer in your body with one of these tests, and if it seemed probable enough, then yeah, still proceed with those imaging and diagnostics tests like we do today. I lost my sister-in-law to pancreatic cancer when she was 39 years old chiefly because by the time anyone knows they have the disease, it’s already metastasized and it’s way too late to do anything about it. If she could have known a few years earlier that that was developing in her body, she could have been saved
Big Pharma about to charge $1000 for each AI diagnosis.
Fool me once, shame on you. Fool me, you can’t get fooled again.
~ George W. - No role models
@@illironiks FGWB
"I know, man and fish can coexist peacefully"
“They misunderestimated me”
Is drawing a larger volume of blood some logistical or expense bottleneck? Why are people so interested in the single drop of blood aspect? I can see how a _dry_ sample would make storage and shipping a lot easier, but seems like you could collect a larger volume (few mL) of blood in the same manner to allow it to dry.
This is the type of uses I love to see with Ai, even if it’s in early stages it’s great to see people attempting to apply it in ways that can change people’s lives dramatically
I love how you addressed my first thought right in the second part in the title 😂
Psychedelics are just an exceptional mental health breakthrough. It's quite fascinating how effective they are against depression and anxiety. Saved my life.
You know I never thought about it but I realise it has cured my depression too. I have a new lease on life and am drug free (except weed which is my prescription) since January. I had DMT, and LSD over new years and realised I was on a bad track abusing all sorts of drugs. But yeah I haven't even been depressed which I have been since I was 14 and living with trauma. I'm stronger than ever and for once I can see happiness. Anyway off topic for the video. But hey 👍
Chain of bots it's disgusting how people think nobody will figure it out
Same script as the investment bots....
In Mexico, the lab I visited advertised a CEA test to detect cancer - about 200 pesos or $10. If your score was over 5,. you had a problem and would need a complete cancer detection scan. When I was diagnosed, my CEA score was 15.8.
Can you please provide more info about the company or the technology that they use? Thanks!
My sister-in-law is suffering from liver cancer and this is great news that might spare others from having to go what she is enduring. Thanks for this report. Hope is wonderful thing.
Early detection can often mean early death, as you are rushed to invasive treatments which ravage your body more than the disease itself
Sometimes early detection can also mean early death. Often the treatment is more invasive and ravages the body more than the disease itself.
There is also the Galleri test by GRAIL, which is pending FDA approval in the US and has an accuracy of over 95% in detecting more than 50 different types of cancer using biomarkers.
I think that the fact it’s been peer reviewed by John’s Hopkins makes this feel a little more legit.
There are so many misdiagnosis in Psychology, I really wish one day through patient consent we'll be able to record the patient face, facial expression, body language and speech to have AI pattern recognition as an assistant in the diagnosis process.
Especially the Brain Disorders gets misdiagnosed a lot particularly outside the anglosphere
I work with cancer diagnostics. We are validating detection with plasma and blood at 10 ng input (equivalent to a drop of blood as lokd as their is enough DNA). We work with validating different genes across different organs. We already have FDA approval for tissue resections but ultimately the goals is liquid biopsy. The "problem" with this dry blood detection method is that it doesn't tell you what gene mutation you have, so you would not know what personalized treatment to give, and you would default to chemotherapy.
even if it doesnt tell you where/what the cancer is, doesnt the fact the it tells you that there IS cancer help? im assuming you could do more specific tests afterwards to figure out where it is if the patient doesnt want/need chemo?
To know that you most likely have, say lung cancer early and you can go get it thoroughly checked out is amazing.
This is both fascinating and hopeful. AI's role in early cancer detection can't be overstated. It would truly be revolutionary if such technology could become universally accessible, cheap, and reliable.
Trust me early detection won't change much. Many people will be on their death beds sooner thanks to this tech. Chemo and the like are death sentences in of themselves. They forever change your body that remission is only temporary and makes you more prone of relapse.
I have met, in person, so many people with normal “biomarkers” who feel like they are dying; which makes me quite skeptical of this science.
I remember that the problem was that the single drop sample changed a lot. 2 samples taked 10 minutes apart would have very different results because has very little blood to average all the metabolics in the blood. A normal blood test has more reliable results because the blood was more mixed. I remember that this was the problem with theranos and not the technic used to analise.
Super skeptical of this one
of course we should be skeptical
How many false positives? Yeah that's what I thought
Yea I'm sceptical as well. Cancer treatment is the hospital's main $ maker after all.
@@bensherman9126 I believe that's what's kept cancer research stuck for so long
Yeah I guess you're right, people should stop researching new ways to diagnose cancer earlier. All the current tests we have are 100% accurate. 😂
@@spk_ezeperiodicals should stop publishing Chinese studies, over 98% of all studies coming out of Chinese universities are falsified or impossible to replicate.
@@bensherman9126 you do know that in most of the world hospitals are not for profit organizations, right?
It's surprising that you didn't even mention the Grail Gallery test. It can detect more than 50 cancers using the biomarkers and AI.
Hear China.
Me: Press X to Doubt.
From my physician’s point of view, cancer may seem more common because we can cure or control the older main causes of death, including cardiovascular and diabetes. On a positive note, we are now treating cancer better and better. In addition, earlier detection of breast cancer with modern digital mammography and better use of the prostate cancer test called PSA are helping us too these cancers much earlier and that managed them. Still, this tech looks quite promising. Thank you.🙏
You missed the point where he said it was cancer rates among "younger" people that were surprisingly rising at high rates. It's not because people are living longer.
@@chadyo99anything to do with events within the last 3 years?
Gee... I wonder why early-onset cancer has increased by 1000 something percent. What could it be?
its unclear... there is only 100 % certainty what it definietly not cant be
What are you implying? Obesety, microplastics, ultraprocessed food, something else?
@@dinhero21 Think of something that all governments in the world harassed, coerced, emotionally manipulated, lied to, blackmailed, etc the entire human population into doing in the last 4 year and dig deep into that rabbit hole & you may find what you're looking for 🤫
@@dinhero21A few years ago they estimated 20 million new cancer cases a year in 2050 but just in a few years it's gone up to 35 million, Food and microplastics haven't gotten that much worse within that time.
There is only really one suspect but that has aperently been proven 100% safe even after people started dropping dead
Vaping?
Thanks for working so hard to put another video out for us 😊
But we all have cancer (our natural killer cells keep on top of cancerous cells if we are healthy) so surely this is pointless as it would just give a load of false positives? Surely it'd be better to monitor people's natural killer cell activity and people with low activity can take steps to improve their health before they get full blown cancer.
I would think that an actual tumor gives out more distinct metabolites than the regular amount of cancer cells the healthy body has at any given time.
This would be revolutionary, really hope this new way of detection will succeed!
Amazing video, Dagogo!
Regarding lung cancer in Asian women, this is due to them doing most of the cooking. Asian food is usually very oily and cooked at high temps, which creates a lot of fine particles in the air, which damages the lungs.
Holmes was ahead of her time in a sense that she had no actual research to back up her claims. If Theranos started around now it could scam people much longer or possibly even fake it till it made it.
I agree . This is the type of application AI should be used for . I'd say in less than 5 years this will be used on a larger scale with how quickly tech moves .
I hate to break the fun and success of it but as a software engineer that is well informed and up to date to the current trend this might be another AI hype scams which I really wished is not.
VC's nowadays lose their sht whenever they hear AI
Were you suprised by real A.I advancement in the past? Like, did you think gpt would become this capable at the rate it did?
yawn. okay grandpa.
Fyi: AI is an umbrella term.
Some of the well known types:
- Machine Learning (data learning)
- Deep Learning (neural networks)
- NLP (language understanding, includes GPT)
This comment is written by ChatGPT-4o.
all i want is my hair back
Me too
Hair transplant, minoxidil, finasteride
🎶🎵All I want for Christmas is my 2 front teeth... 🎵🎶
I'm not giving it back.
@@Asdayasman Ah, so YOU'RE the one who stole it.
My grandma had cancer, and then both of my parents had cancer at the same time when they were in their late 30's. My dad didn't make it. I'm now 30 and am fairly certain I'll get it too just based on how prominent it's been in my family. Though I can't afford the treatment at all, so I guess if I get it, that's it.
People in the comments are missing the point by immediately dismissing this because of what happened with Theranos. In the case of Theranos, it was a completely empty promise and they refused to share the scientific basis for their claims because, as we all know, there was none. This is literally the exact opposite situation. It’s not some Sketchy startup trying to sell investors; it’s actual researchers putting out peer reviewed studies that point to the feasibility of this. Informed skepticism is good. Boneheaded skepticism without actually looking at the science is bad
Lol the fact that no one could see that E.H was a psychopath is beyond me. You see it within 1 second.
It's because people wanted so badly for there to be a girl boss who just owned all the men and was so much better than everyone else. The fact that they couldn't look past her obviously fake voice just makes it even more hilarious.
@anonony9081 Oh god, the comicially and obvious fake man voice! I had forgotten about that 🤣🤣🤣
I mean, people still treat Apple like a visionary company when all it produces is crap. Tech/wannabe tech companies dazzle people with bullshit so they just can’t help but invest.
You can say the same for Musk
They thought she was just confident. Her investors were mostly older men who saw she was a pretty blond woman
This is where I want AI.
The irony of using a petrol cars exhaust as an example when it’s that exact thing which contributes to cancer cases through air pollution
:o
Dogs can do it just by smelling it. Blows my mind 100s of millions aren’t spend on training more dogs. They have like a 90% accuracy rate
This is awesome! Finally we know exactly when it's necessary to apply thoughts and prayers!
7:12 So they didn't treat that area and cancer came 2 years later? Why was it not investigated or treated beforehand?
It was an experimental, unvalidated,diagnostic tool, so everything it said had to be checked by human experts before tolerating the side effects of chemo or surgery, and I guess the human experts disagreed with the AI diagnosis.
Another big hurdle is to get treatments that can CURE it without taking a Machiavellian toll on the person's body, leaving damage and ironically a further risk of cancers, as well as draining their bank accounts. Many are choosing to skip treatment to avoid these two things. If we want to attack cancer with any degree of success, we need to address the whole picture.
Amazing progress!
Totally.
Congratulations on your 500th Video 🎊💐
Yeah, I'm not going to hold my breath. This sounds too good to be true, same as Theranos.
If it works, good, I'll believe it when they can prove it
Keep up the amazing work!!
Ill wait for the peer reviewed papers on this.
I really adore your content. And since a lot of youtube channels stated that they would withdraw or have done so already from the platform, you're one of my only few hopes left here. For the interesting topics covered, I am thankful.
One of the main reasons theranos was able to scam so much money, was UA-camrs like yourself making videos about science that hasnt even been verified at all yet, and hyping it up
Good point
skip to 4:16 if you don't want to sit through another explanation of cancer
God bless you kind stranger 🙏
This isn't AI, just machine learning lol
Who cares if it does the job !
Machine learning is AI
@@hypebeast5686no its not.. AI is a fing marketing term to fool people like you.
Calling current technology "AI" is hollowing out the meaning of that word
@@DutchManticore bro, I’m studying this 😅
Machine learning it’s a sub field of AI, as NN is a sub field of ML and DL is a sub field of NN.. come on, I don’t even need to study AI to know this..
AI is not only chatbots lol..
@@hypebeast5686 thats nice, that youre studying this. I am working with this, professionally.
As someone who has just started working in this field, I can tell you that the machine learning side with spectroscopy is not a big game changer.
Terms like accuracy are spouted out, but really what people need to look into are the tests sensitivity, specificity, positive predictive value and negative predictive value. Many of the these tests have a very good sensitivity (correctly identify patients with cancer, or in another words you correctly get a positive result when you have cancer), but lacks specificity (so its saying you got cancer when actually you dont). This leads to lots of false positives.
More work is needed.
Unless this turns out to be a lie too. I thought you already did a video about how many of these AI companies are lying
Yes definitely and I get it, but these are peer reviewed research papers. There’s a difference. Here’s another good article from John Hopkins: www.hopkinsmedicine.org/news/newsroom/news-releases/2024/06/artificial-intelligence-blood-test-provides-a-reliable-way-to-identify-lung-cancer
@@ColdFusion So you believe them because they're not women? Your bigotry is starting to show.
@biggeststeppa1 If you look up Straw-man Fallacy on Google, you'll find that your comment fits its description pretty well.
@@biggeststeppa1 That sounds like a hasty jump to conclusions. Don't trip.
@@biggeststeppa1you sound unstable... just stop
This research should also be brought to other areas of medicine such as Mycobacterium Tuberculosis detection with a Point of Care diagnostic device
Where have I heard that in the past? Exactly, Theranos.
Wait, what? AI to the help?
For those who underestimate AI: You simply overestimated how "marvellous" human brains work
@@ylstorage7085 disagree, the answer is we don't even know how the brain works either. But there is a lot happening. I wish AI could find solutions for Alzheimer's and other things as well.
@@rjung_ch we know a lot about the mechanisms of the brain, it is the emergenct behavior we don't understand. AI is at the same stage.
Human Brain has been quite hindered for modern societies' need due to the baggage it accumulated thru survivals needs in half a billion of evolution.
Can you please make video of you past videos as to how the idea and possibility you shared with us have unfold since Coldfustion TV
Babe, Dagogo dropped another one 😊
No pun intended
The old just aren't inflicted. The mother of my kids, and my best friend in this entire world passed away from cancer and she was just in her late-ish 30s. RIP Stace
i have never regretted subscribing to this channel
Oh, please, let this work. Getting cancer diagnosed is sometimes terrifyingly inefficient. Anything to help spot it sooner!!
Did not even take 1 second before the Thernos comments came 💀
I mean he did mention it in the first 10 seconds of the video...
That's about as much time as should have been expected.
The lack of science in this channel is troubling.
She wasn't ahead of her time, she was a con-artist. Now tech is catching up to sci-fi. Nothing more.
hope you do a follow up vid on this.
Honestly, FOR GOD SAKE, STOP CALLING IT AI. It's MACHINE LEARNING or DEEP LEARNING, NOT AI.
Ok, from now on we wil start calling it machine learning
I'm calling it Deep Machine from now on
@@weplaywax spot on. however, it doesn't make it not dangerous though in the wrong hands.
Well, saying AI isn't incorrect, it's just not very specific. Similar to calling all fish vertebrates. It's the truth, but leaves a lot more information to be desired.
I prefer blackbox maths
THANKS FOR THIS INSIGHTFUL VIDEO, KINDLY SHARE THE SONG AT THE END.
"Ah sh*t here we go again"
Elizabeth suing from jail be like “This is my idea pay me a million dollars.” 😂
Just think about the potential treatments that exist in plants we have yet to discover. Scientists estimate that about 100,000 plants are yet to be discovered. Nearly all medicine treatments come from plants. This is another reason why it’s so important we protect our environment.
The guy biting doctor's hand at the end was funny.
I’ll believe it when I see it.
you need to release that outro track!
Chinese and Ai what a great and truthful combination
I think the biggest challenge here is that the recognition of patterns is only possible through the analysis of conventional data. IE: comparing a person's current physiology to that of the human genome/ancestry data/etc. to determine a person's propensity to be at risk later in life.
Where it gets muddled is in the omission of environmental factors which cannot be accounted for. IE: Exposure to toxins, stress hormones and other miscellaneous exposures which accelerate that risk.
Telling someone they are likely to experience a certain kind of cancer in, say, the next seven years is only as relevant as their ability to make lifestyle changes which mitigate that predicted risk. In most cases, it is still going to require a "wait and see" approach to see if a tumor forms which can then be excised before it becomes a threat to the body.
People don’t seem to understand what AI really is. Not even AI people seem to understand what AI really is.
People are overusing the AI tagline when all of this is machine learning that has been available for decades(eg. Wolfram.alpha which is over 10 years old), it's only gaining traction coz computing has become exponentially more powerful. We are still decades away from true AI
I have knew it for a long time (years) now that we need AI if we want to leap forward, but in the end it could kill us. that being said we still need it to help us make real progress faster.
ACTAVATE MEGA SKEPISEM.
I can't even get a doctors appointment on the NHS in the UK but this sounds good for those who have insurance.
Turbo cancer is definitely not caused by the "Safe and Effective" (TM).
Elizabeth Holmes at parole hearing: Well, I told you it works.
2:30 call me crazy, but what about COVID shots? The other things that you comented are not really that new
Theranos: all that for a drop of blood
Thanos: exactly
1 minute in and I've lost my remaining faith in Cold Fusion. Neat.
Edit: the offending line is at 0:48
fam, the channel is called "cold fusion"
Why?
@@AGILISFPV He's on the AI hype train. This isn't even AI. It's machine learning.
That makes no sense, did you even watch the whole video?
?
It's been a decade following you. You are getting better and better. Well wishes from INDIA. By the way nice content.❤
False positives will still be an issue just as they are with the traditional blood tests for detecting tumor markers. I hope the medical systems which make this test available also invest in enough radiologists and imaging equipment. I'm saying this as someone who just went through several months of drama over a false liver cancer marker.
China and AI makes me question accuracy lol