ElMaestro
★★★

Denmark,
2020-06-21 00:41
(962 d 01:55 ago)

Posting: # 21552
Views: 1,794

## Reference ranges, prediction intervals [GxP / QC / QA]

Hi all,

pardon me if this is the wrong category. Not sure where else to put it?!?

I am reading up on prediction intervals.
Wikipedia is a good place to start for someone like me. Mainly because I know nothing and am uncritical of most new things.

Wikipedia says: "Prediction intervals are commonly used as definitions of reference ranges, such as reference ranges for blood tests to give an idea of whether a blood test is normal or not. For this purpose, the most commonly used prediction interval is the 95% prediction interval, and a reference range based on it can be called a standard reference range."

I find that very interesting and the idea is appealing and intuitive: We have n observations from a group of people we think are normal. We define the reference range form them. Then we sample the next subjects and checks if they are within the interval of observations defining normal ("standard"), too. And so forth. That interval defining normal builds the sample mean and a sampling variance from the normal ones into the prediction. Sounds right. At least to me when I read it. To you, too?

I have been an auditor and inspector doing work at various path labs for BE on four continents. When I ask to see how they define the reference ranges, the story is often that CROs or path labs sample some subjects and take the 2.5th percentile and the 97.5th percentile to define reference ranges*. I have generally accepted that. I have generally accepted anything as long as the CRO or path lab has given the ref. range some consideration.

Thinking very hard about it I have not ever seen any CRO use the prediction interval approach to define ref. ranges. Should they? What is your opinion here? Have you seen the approach with prediction intervals in use in any operations relating to BE?

*: the exception is hemoglobin and hematocrit. After WHO published their rule about aberrant hemoglobin a few years back, some CROs revised their reference ranges in funny ways so that anyone on the brink of keeling over due to anemia could still be enrolled. Or they revised their SOPs on ways PI's or delegates could clear such subjects for participation. But I digress, this latter aspect is more a question of low ethical standards than a question of reference ranges. OK, I will take a deep inhalation from the Schütozomycin bong now, I promise to be calm the rest of the day.

Pass or fail!
ElMaestro
Helmut
★★★

Vienna, Austria,
2020-06-21 15:28
(961 d 11:09 ago)

@ ElMaestro
Posting: # 21555
Views: 1,281

## Reference ranges, prediction intervals

Hi ElMaestro,

❝ We have n observations from a group of people we think are normal. We define the reference range form them. Then we sample the next subjects and checks if they are within the interval of observations defining normal ("standard"), too. And so forth. That interval defining normal builds the sample mean and a sampling variance from the normal ones into the prediction. Sounds right. At least to me when I read it. To you, too?

Yep, if we agree upon that $$\small{x\in\mathcal{N}(\mu,\sigma^2)}$$.

❝ […] CROs or path labs sample some subjects and take the 2.5th percentile and the 97.5th percentile to define reference ranges. I have generally accepted that. I have generally accepted anything as long as the CRO or path lab has given the ref. range some consideration.

Nonparametrics are always fine for me.

❝ […] I have not ever seen any CRO use the prediction interval approach to define ref. ranges.

❝ Should they?

Yes.

❝ What is your opinion here?

Both parametric and nonparametric are fine. I any case the number of subjects should be reasonably large.

set.seed(123456) n       <- 100 mean    <- 20 sd      <- 5 x       <- rnorm(n = n, mean = mean, sd = sd) pred.p  <- mean(x)+c(-1, +1)*qt(1-0.05/2, n-1)*sd(x)*sqrt((1+1/n)) pred.np <- as.numeric(quantile(x, p = c(0.025, 0.975))) ref     <- data.frame(method = c("parametric", "nonparametric"),                       location = c(mean(x), median(x)),                       pred.lo = c(pred.p[1], pred.np[1]),                       pred.hi = c(pred.p[2], pred.np[2])) col     <- c("blue", "red") tmp.x   <- seq(min(x), max(x), length.out = 201) tmp.y   <- dnorm(tmp.x, mean = ref[1, 2], sd = sd(x)) h       <- hist(x, breaks = "FD", plot = FALSE) ylim    <- range(c(tmp.y, h\$density)) plot(h, freq = FALSE, col = "bisque", border = "darkgrey",      ylim = ylim, las = 1, font.main = 1) lines(tmp.x, tmp.y, col = "blue") abline(v = c(ref[1, 3:4], ref[2, 3:4]), lwd = 2, col = rep(col, each = 2)) rug(x, ticksize = 0.015); box() legend("topright", bg = "white", title = "95% prediction intervals",        legend = ref[, 1], lwd = 2, col = col, cex = 0.9) subj    <- 2500 smpl    <- rnorm(n = subj, mean = mean, sd = sd) comp    <- data.frame(method = c("parametric", "nonparametric"),                       within.range = c(length(which(smpl >= ref[1, 3] &                                                     smpl <= ref[1, 4]))/subj,                                        length(which(smpl >= ref[2, 3] &                                                     smpl <= ref[2, 4]))/subj)) cat("Reference ranges based on", n, "subjects:\n"); print(ref, row.names = FALSE) cat("Fraction of", subj, "tested subjects within",     "reference ranges:\n"); print(comp, row.names = FALSE) Reference ranges based on 100 subjects:         method location  pred.lo  pred.hi     parametric 20.08410 10.17835 29.98985  nonparametric 20.23954 11.06342 28.14009 Fraction of 2500 tested subjects within reference ranges:         method within.range     parametric       0.9560  nonparametric       0.9136

In Austria samples are sent to labs for – mandatory – annual interlaboratory comparisons (“Ring­ver­suche”). Funny that the lab gets a certificate of attendance but if a result is off, only a separate notification (not stated in the certificate).

IMHO, reference ranges come in two flavors. (Semi-)official ones which are based on the outcome of the interlaboratory comparisons. They are often wider than the ones of labs because different methods come into play. AFAIK, sometimes when reagents are modified, vendors notify labs that results may change (and hence, the reference range has to be adapted). See this post what to do if that happens during a study.

❝ Have you seen the approach with prediction intervals in use in any operations relating to BE?

Not my cup of tea, sorry.

Dif-tor heh smusma 🖖🏼 Довге життя Україна!
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Ohlbe
★★★

France,
2020-06-22 17:38
(960 d 08:58 ago)

@ ElMaestro
Posting: # 21560
Views: 1,222

## Reference ranges, prediction intervals

Dear ElMaestro,

❝ Thinking very hard about it I have not ever seen any CRO use the prediction interval approach to define ref. ranges.

I can't remember ever seeing a path lab defining their own reference ranges: whether CRO, central lab involved in Phase III trials, or the lab next door where I had my cholesterol level measured once some years ago (I never went back: what you don't know won't hurt you). Whenever I asked, the answer was that they were taking the ranges recommended by the vendor of the machine and reagents. Which may have been determined in a rather different population on another continent.

Actually I worked for some time at a hospital lab which was involved in such an exercise on behalf of the manufacturer, to establish the normal ranges for thyroid hormones on a new lab machine. They even used a sample of my own blood (talk about freely given consent). Not sure there was much statistics involved then.

❝ After WHO published their rule about aberrant hemoglobin a few years back, some CROs revised their reference ranges in funny ways so that anyone on the brink of keeling over due to anemia could still be enrolled. [...] But I digress, this latter aspect is more a question of low ethical standards than a question of reference ranges.

Regards
Ohlbe