Search results

Why do you believe p is a probability because if scales between 0 and 1. I don't really understand how your paper got published. You seem to have shown that you can train a model on data to discriminate between two classes but that is not hard. I can do that with random data that I allocate...

Making it a number between 0 and 1 doesn't make it a probability just a number between 0 and 1. But that is likely to be the reasoning. In neural networks the logistic function is used to introduce a non-linearity and also limit the output to between 0 and 1 although these days I think a...

But there is a serious question as to whether this is a valid operation. The FSS scores are basically just answers to a random set of questions vaguely about fatigue. Is it valid to add them up and average? What is the meaning? I also don't get the rational for using the logistic function and...

I don't think its always about shaming the poor sometimes I think its about the rich trying to justify why they are entitled to be rich and pretending its deserved rather than an accident of birth.

To me its that they create layers of abstractions that are not valid or not valid to use under certain circumstances but because they've created that abstraction they forget. So they have a set of questions and call is a depression scale and then use that abstraction of the depression scale as...

The problem with some studies is that they use questionnaire where the questions are not designed to separate not being able to do stuff from not wanting to do stuff. So things like HADS is bad at this. It has the depression quesions So the ones I've bolded could be due to illness or being...

I think he is just keeping us informed of what is out there.

This is one of the really frustrating things. By hounding families whose children have ME there is an opportunity cost around not helping others who need help.

I think that is one of the things they have relied on. A slight nudge to other academics to be quiet and to not knock the boat. Also behind the scene nudges to journalists. I think they way the medical community has backed bad research and failed to act is one of the big scandals around PACE...

The service is RUH Bath (i.e. the hospital trust) not the university. Crawley works for Bristol University. In general I'm not impressed with the letter. I think if someone didn't understand the issues then they wouldn't get much from reading this. I also object to the ME isn't CFS as there is...

They claim that in trials GET does no harm but most trials didn't bother to look. PACE was relatively good in that it did look but I think they changed there definition of serious deterioration in the Lancet paper from the full protocol. It was hard to meet because the deterioration needed to be...

I think these stories are far too common. My father new someone who was told he had stress headaches but it was too late when it turned out to be a brain tumor. Doctors are encouraged to dismiss patients these days as the worried well. I don't know what the motivations have been in the past...

I suspect they did two different analyses one with men and women and a different one looking for correlations with income so they may not have explored the relationship. Then the journalist combines these in a single sentence. It would be interesting to know what else they looked at (say age...

(Sorry a long complex question) I have a question around collecting, testing and interpreting samples. ME becomes worse with exertion and this can last multiple days. Should we therefore consider the body as a dynamic system when taking samples and thus always take them with an understanding...

I think you should name them so that parents are warned. Last time QMUL or Barts (basically White) wrote a submission to NICE saying aids and adaptations should not be given to patients.

I think if anyone has paid they should ask for a refund because the CFQ (not scale) is not fit for purpose in measuring fatigue and it certainly isn't a scale.

Its a case of methodology and understanding the algorithms. When training a classifier on data you can give very good results on training data with low error it doesn't mean that the classifier will generalize at all to any unseen data or it that it hasn't picked up on irrelevant features in the...

But when generating a formula like this based on the data you need separate training and test sets otherwise the regression will just pick up on random variations within the given test set based - that is what the regression optimization is designed to do. The way that you know if it works is to...

I know that at least one 3d printer manufacturer is printing parts of its printers. But I don't think they deliver half a printer and expect you to print the rest out yourself. But they are working on printing metal, electronics etc so perhaps one day!

Machine learning techniques would certainly find patterns in data that humans wouldn't but care needs to be taken that they are not superficial features of the data or collection devices. But the big issue is availability of large volumes of data. Here there is work on things like nano sensors...