Search results

I think we should remember how much things have changed. A few years ago there was a debate in the house of lords and there were many of the lords who were praising PACE having been briefed by White and others and repeating the PACE story. This recent debate in the House of Commons really does...

I think it is there last defense so I don't think they will stop. But the question is how long the press will keep giving them an uncritical voice.

They also need to look beyond experts and ask international experts. If the CEO of the MRC says that PACE is fine then she is marking her own work. More generally if a committee sees a disease that affects quite a lot of people is not understood or researched then they should be asking why is...

I think there is an issue beyond NICE: Bad (NICE recommended) treatments are sometimes forced on patients either on children via threads of child protection of via insurance/benefits etc requiring people to take 'treatments'. Nice do say no one should be forced but doctors or others don't...

Whilst its not in the power to determine what is funded or what treatments are recommended I do think they have a responsibility to look at failures of the funding system such as why so little is funded (or why there are too few applications) or why the system funded PACE when its protocol...

I assume he is referring to big data approaches applied to data we routinely collect rather than running trials. We do collect a lot of data and some of it is contained in a structured form in databases which makes it useful and other pieces can be scraped and structured. This gives us the...

Also those who know activity was bad may have avoided barts.

Some what off topic but it made me think Back in the DHSS which is a half man half biscuit album from the days when health and social security were all run together.

I wonder if there can be an effect of patients choosing by choosing which center to be referred to (particularly between CBT and GET). In some places it may not be an issue but in London with the Kings and Barts centres offering different treatments would patients get to choose which the GP...

I thought Consort involved reporting all secondary outcomes and thus they didn't follow Consort. They may claim they did because the silently dropped some of the secondary outcomes in the SAP but that is not a new protocol and they give no reasoning.

I think so they have put their code and results figures on github https://github.com/cmlakhan/twinInsurance and they point to that page as well.

We've been discussing a paper https://www.s4me.info/threads/estimating-prevalence-demographics-and-costs-of-me-cfs-using-large-scale-medical-claims-data-and-machine-learning-2018-proskauer-et-al.7279/ where they use insurance data to look at ME. One of the issues with such data sets is the...

It also depends on the algorithms they use and how robust they are to outliers. I think some of the boosted trees that they use can be sensitive to outliers but it depends on the cost function (if it is a least squared one but I believe a cost function based on huber loss or absolute loss can be...

The assessment criteria and how they are operationalized is the thing that really matters rather than the label and I don't see how that is reflected in the dataset. It would have been nice to have seen some analysis around the quality of the data (i.e. more detailed checks) or looking at how...

From this studies perspective could there also be effects on who has insurance at different ages and the way chronic illness may affect coverage and hence inclusion in the dataset. Its not a purely random selection of patients.

ML can be easily fooled by poor quality data. So if you are using a large database like this for ML you really need to do a very careful scrub of the training (and test) data. The ML will simply pick up on trends in the dataset and if they are unreliable then the results will reflect this. The...

Its not just inherent in the interaction the manipulation of attitudes is fundamental to the interventions they are testing.

From what I understand these aren't necessarily using any particular criteria but are really down to a doctors judgement and preference for particular codes. But the fact they can model the ME codes but struggled with ME+CFS does suggest something about the consistency and usage of the codes...

I'm still reading through the paper. But what I think they have done from the ML perspective is used the ME diagnostic codes from a subset as labels for a supervised training algorithm (a boosted tree). Then they use the model (after testing that it works on a test set (and selecting the model...

I don't know much about the US insurance system but could the 20% coverage of people with medicare bias the results they get in that it covers individuals with disabilities which could include people with ME. I think the question is are there more likely to be people with ME in the data set due...