Henriapi illustrates this phenomenon as well.

Only instead of, you know, good and bad cancer tumors or benign or malignant tumors we instead have diabetes or not and so we will use that as a supervised, we will solve that as a Supervised Learning problem just like we did for the breast tumor data.

So on. So this example...

We didn't sequence his genome.

So 0 may denote the benign tumor and 1 positive class may denote a malignant tumor.

Here's an example of a training set for a classification task for classifying a tumor as malignant or benign and notice that malignancy takes on only two values zero or no or one or one or yes.

Mice with multiple myeloma, an incurable malignancy of the bone marrow, respond dramatically to the treatment with this drug.

Walt, your tumor has shrunk by 80 percent.

So, if angiogenesis is a tipping point between a harmless cancer and a harmful one, then one major part of the angiogenesis revolution is a new approach to treating cancer by cutting off the blood supply.

That's another classification problem, and earlier we also talked about the example of classifying tumors as a cancerous malignant or as benign tumors.

In other words, I'm going to tell my patient that the tumor, sadly, has a 70 chance or a 0.7 chance of being malignant.

I'll show you an example of that real quickly.

What does that mean?

Let's see you want to look at medical records and try to predict of a breast cancer as malignant or benign.

That's counterindicative for a hemorrhagic tumor.

A few years ago I felt a lump on the side of my neck, and it was my turn in the MRI machine.

But, as a cancer doc, this is what I see.

Let's flip the table yet again

And a different set of patients, they look a little different, whose tumors turn out to be malignant, as denoted by the crosses.

This is old information we've known since about the 80s, yet there's no medicine I can prescribe to a patient with this or any of the numerous solid tumors caused by these three ...

Tumors?

Chronic viral ulcerative lesion.

She suffers from a chronic illness.

And bone marrow is actually what we use to save the lives of tens of thousands of patients, most of whom have advanced malignancies like leukemia and lymphoma and some other diseases.

So given a data set like this, what the learning algorithm might do is throw the straight line through the data to try to separate out the malignant tumors from the benign ones and, so the learning algorithm may decide to throw the straight line like that to separate out the two classes of tumors.

OK. Now let's move from sleep to diseases.

These are years that we could get.

So dystonia is a disorder affecting children.

He was taken off the Dutch ship in Martinique and died a week later of consumption. Oh...

So this is a photograph of Henry, two weeks after he had a malignant cancer removed from the left side of his face his cheekbone, his upper jaw, his eye socket.

Similarly, we have the tools with which to ask the question

So a real skyrocketing of chronic childhood disease that includes other things

This was at a time that treatment actually existed in rich countries.

But often there is this intuition that the negative class is conveying the absence of something, like the absence of a malignant tumor, whereas one, the positive class, is conveying the presence of something that we may be looking for.

The cancer.

But inevitably, these tumors progress towards being enormous, ulcerating tumors like this one here.

So, it's not an option for low income patients.

If someone discovers a breast tumor, a lump in their breast, a malignant tumor is a tumor that is harmful and dangerous and a benign tumor is a tumor that is harmless.

This is a little Bangladeshi girl from the east end of London who's got a huge malignant tumor on the right side of her face, which has already made her blind and which is rapidly growing and is going to kill her shortly.

Women suffer from that disease.

And one afternoon, I got a call from my doctor.

And this is, in 2004, the FDA has approved MR guided focused ultrasounds for the treatment of symptomatic uterine fibroids.

So instead of drawing crosses,

And started to use different symbols, circles and crosses, to denote malignant versus benign examples.

This one in particular sticks in my mind, because this is the first case of this disease that I saw myself.