You don't need to be signed in to read BMJ Blogs, but you can register here to receive updates about other BMJ products and services via our site.


StatsMiniBlog: ROC plots

19 May, 14 | by Bob Phillips

A (while ago) we published an explanatory page about ROC plots in the Education and Practice journal. There are a few great reasons why we should replicate it here:

1. So people can read it more easily

2. Because it fits into the stuttering series on diagnostics

3. It saves me having to write the same thing in different words.


Underpowered and over here.

14 May, 14 | by Bob Phillips

From @aLittleMedic

We’re great fans in the Archimedes blog of trying to get people to think about the meanings and impacts of research, like asking What would Jack want and not believing p-values. One key idea is that of an ‘important clinical difference‘ (see – avoided significantly …) that is essential in working out if a trial is telling you two treatments really are equivalent, or if the study is just underpowered.

If you’re designing a trial you’ll be wanting to be very very sure that this difference, that you’re gong to base all your study numbers upon is, made upon the best possible grounds. Aren’t you.


Let me tell you a story … journal clubs as literary criticism

23 Apr, 14 | by Bob Phillips

From the worlds greatest comic



Have you ever been to a journal club and had the slight suspicion that what you are addressing isn’t quite on-target? (Ever been part of #ADC-JC and realised that most of Twitter appears to be whispering at the back and passing notes to each other?) Ever considered if journal club really is a scientific pursuit?

A spoonful of Septrin helps the carinii stay down?

16 Apr, 14 | by Bob Phillips

 While the diagnosis of Pneumocystis carinii Pneumonia (yes – I know it’s changed it s name – but really, do you ask for Beanz when you want something tomatoey to go with your sausage, egg, black pudding, fried bread, mushrooms and juice in a morning?) may not be everyone’s weekly occurrence, there are probably a handful of children who are trying very hard not to develop in in your town.

The traditional approach to prophylaxis has been a spoonful of Septrin (TM), which got modifed to three times/week.  Most of the UK leukaemia fraternity now moves with a twice/week, twice/day approach. But in Italy, there are centre which use a once-per-week schedule.

“On the basis of large RCT?” I hear you ask, knowing the great reputation paed onc has for developing research.

“Not .. quite..” comes back the embarrassed answer. “But there is some evidence …?”


The Cabin of Dr. Ladhani

6 Apr, 14 | by Bob Phillips

Hot on the heels of thinking about thresholds for action and inaction comes a really interesting paper looking at the risk of serious infection in children with blood or CSF cultures taken in the South East of England (in 1m – 15y olds).

Before going on – what proportion of cultures do you think were positive?


Springing into action

2 Apr, 14 | by Bob Phillips

If you could get a multiplex PCR result back to you within 2 hours that told you your hot, grumpy, 2 month old patient did not have bacteraemia, would you discontinue antibiotics?

How sure would you need to be of that result – 95% certain? 98% certain? 99.5% certain?

What – in diagnostic analysis speak – would be your ‘threshold’?

The deciding of a threshold can be emotional, or rational, and both. The rational part of the idea relies on an equation:

Probability of wrong decision * consequence vs. probability of right decision * advantages

Rationality – based on a good understanding of some of the attributes of the diagnostic test in question – provides the probabilities. The ‘emotional’ part comes in when assessing what weight the consequences and the advantages both have. (Now there are rational approaches to coming up with these – utility values they get called – but they’re still emotional at heart.)

Sometimes the consequence is so emotionally overwhelming that there is no degree of ‘chance’ that is allowed to be acceptable.

But what about you? What value would you place? If the test was 99% correct – would that be enough? Comments welcome.

  • Archi

(You may recall this is the same maths that runs the decision
in treatment too.)


Researcher Tips for Children and Young People’s work

30 Mar, 14 | by Bob Phillips

We’ve published about academic training in the UK for paediatricians recently, we’ve heard that there is a decrease in the amount of paeds research happening, and we know that there’s stuff floating to push up the political vision of children and young people’s health.

We know that we can try to reduce waste by increasing efficiency in research, and we can look at boiling social media feeds to see how education (#FOAM) seems to splutter rich and velvety from every pore (but we’re not quite sure if it works).

Can we, here in the Arch Dis Child blog, draw these flumes together to share, via this blog, tweetering and facebookery (?? sp ??) hints and tips about how to get into, do and make more efficient our own efforts in researching in paediatrics and child health?

Why not start with a response here, a tweet to #CYPRtip or comment on our facebook post?

  • Archi

Gambling, alcohol and division.

23 Mar, 14 | by Bob Phillips

No, not an average afternoon at the Houses of Parliament, but another in our diagnostics series.

Moving yourself from looking at the predictive values of the tests as evaluated, to taking this information but using it in the situation you face, is a case of Bayesian mathematics.

Which sounds hard.

But its absolutely what you do. Take a serum potassium of 7.8 in a baby who you struggled +++ to get some blood out of, every drop taking minutes to leak from its squealing heel. You may re-test, but you’re unlikely to call ICU on hearing it.

What if that same value came back from the central line sample from a child on peritoneal dialysis who presented with vague abdominal pain?

There is a different ‘pre-test probability’ – expectation – associated with different clinical settings. The same result has a different ‘meaning’ – chance of being real – in different settings. However, sensitivity and specificity don’t change lots across different clinically relevant pre-test probability values. And this leads to the ability to use them to move from a known/estimated pre-test probability of disease, to a post-test value. This needs the use of the likelihood ratio (LR) and, most often, a nomogram.


(Fagins nomogram; from )

With a ruler, you go from your pre-test probability, through the LR in the centre, to read your post-test probability.

Likelihood ratios are calculated :

Likelihood of finding this result with disease / Likelihood of finding this result without disease


Really diseased 

Really not diseased 

Test +ve 

Test -ve 


So LR for Test+ is :

Likelihood of finding this result with disease [A/(A+C)] / Likelihood of finding this result without disease [B/(B+D)]

And LR for Test- is :

Likelihood of finding this result with disease [C/(A+C)] / Likelihood of finding this result without disease [D/(B+D)]


Now this also extends to multi-level tests:


Really diseased 

Really not diseased 

[Rh] >100 


[Rh] <50




The LR for serum rhubarb >100 is:

Likelihood of finding this result with disease [A/(A+C+E)] / Likelihood of finding this result without disease [B/(B+D+F)]

For [Rh] 50-99

Likelihood of finding this result with disease [C/(A+C+E)] / Likelihood of finding this result without disease [D/(B+D+F)]

Etc etc…


Armed with this, the ability to convert your diagnostic test numbers into something meaningful should become clinically clear.

  • Archi

Positive about predictions

19 Mar, 14 | by Bob Phillips

In a previous post I muttered about how unhelpful sensitivity and specificity are to practicing clinicians, and how what we really want to know are the predictive values of a test.

Remembering the Table


Really diseased 

Really not diseased 


Test +ve 

1.. A/(A+B) 

Test -ve 

2.. C/(C+D) 

5.. D/(C+D)


3… A/(A+C) 

4… D/(B+D) 



Subjective = meaningless.

16 Mar, 14 | by Bob Phillips

So, that’s a deliberately provocative title (which I was assured by a friend in social marketing was a good way to generate blog traffic) … but it’s vaguely accurate.

Does subjective = meaningless?


ADC blog homeapage

ADC Online

Education, debate, and meandering thoughts on child health, using evidence and research.Visit site

Latest from Archives of Disease in Childhood

Latest from Archives of Disease in Childhood