Tag: Real-World Evidence generation

Generation of RWE with the most realistic clinical data through the application of AI capabilities matched with scientific capabilities.

Shame: It took me years to realize this.

I used to think that publishing was difficult because of competition.

It took me years to realize my mistake: publishing is not difficult because of the competition, but because of incompetence.

If publishing is difficult, it is not the fault of those who publish a lot. 
Those people spit out science lessons with their mere walks.
You get smarter just watching them drink their coffee.
Obviously many onlookers are impervious to learning. The goggles of envy transform the successful into a lucky fool.
Or into a supernatural, unattainable being and therefore worthy of being criticized in the hospital cafeteria.

Good. One of the things I’ve learned has to do with mindset.
This is…for example, when someone finds out how we’re getting people published using AI and says it’s a lie and tries to make fun of it, you have to know that they don’t know. 

I’ve always been amazed at people who are evidence-producing machines whereas I’ve published very little in my life.

But if I saw someone doing it a lot I didn’t question him, I didn’t judge him. I just looked at them. 
And I learned that people in Medicine if they publish a lot it’s almost always because they have one or more large registries with a lot of patients.

So I invented something, a machine to make infinite disease registries, the only way possible, which is using AI.

Not for me to publish, but for others to do it, each one in his own field.
And the invention worked out quite well. 
Of course, if you don’t publish, nothing happens and you are no less. 
But you have two ways. 
One is to say… “that’s a lie, you can’t publish so much for using AI. You’re a bullshiter”. Which shows that you don’t know what the world is going through,.
And the other is to say…. “Damn, I’m going to see how he does it to see if I can apply something for myself and publish a lot next year”. 

You can't go around without knowing what IA transportability is.

The actual price of an AI project.

Who will pay for the AI is not who you think.

When federated learning is a scam.

Today I’m going to do something that the light people will really like. You know, people with no substance.

The ones who are on social media giving likes and throwing milk jugs over their heads for the challenge of the week.

The ones who say “in my opinion” before speaking.

All of them are going to love it.

Because I’m going to give “value” content.

Oh yes, valueeeeeeeeeee.

And these people love giving value. It pleases them.

The value thing is in federated learning.

Which consists, in case you don’t know, and you don’t have to, in that you put the machine learning to learn from local data, without taking the data to the cloud.

And you take the learned algorithm, but without taking the data with you.

And people obviously like that.

But I’m going to tell you something.

I’m sure no one else is going to tell you. Really, no one.

Just for being on this list, which is free, you get it.

Although for teaching the things I teach here I could charge thousands of euros at any business school.

The thing is that federated learning is ONLY valid if the data from that place of origin is already clean, well structured, modeled and standardized.

Otherwise, no.

In other words, it works very well for making AI that learns radiology, because there are very standardized formats.

But it does not work, for example, for Natural Language Processing.

Because everyone writes as they please.

And for that reason, whether you like it or not, the text has to be taken out to clean it up.

For this reason, the safest way to work with clinical texts is not to federate, which I have already told you is not possible, but to sign contracts that say what you are going to do with this data.

This is a case that is not solved with technology, but with regulation.

And that’s it.

Come on, don’t get ripped off.

Have a nice day.

PS. To do a study extracting information from medical records, using the cloud, but a cloud managed and controlled by the owner of the information, here.

Enrol in a project