0
$\begingroup$

In risk prediction models there is a need to evaluate the added diagnostic value of a new variable (biomarker). Different measures have been suggested, among them there is the reclassification calibration statistic (RC statistic).

I need to understand the RC statistic but I can not figure out how it is calculated. The sources I've read present some data and the formula, but I don't knnow how to get the RC statistic. Here are some links: 1, 2, 3, 4, 5 or 6.

The link 3 provides this data table: table

The formula is

formula

where nk is the number in cell k, Ok is the observed number of events in cell k, and p‒k is the average predicted risk in cell k for the model under consideration. Is it possible to calculate the RC from that table?

Further, the text says "Observations in a reclassified cell are considered ‘correctly’ reclassified if the observed rate is closer to the new than to the old risk stratum. For example, 696 women were reclassified from <5% to 5-<10% 10-year risk. The observed 10-year risk based on a Kaplan-Meier estimate for these 696 women was 6.8%, which falls into the 5-<10% category. The average estimated risk for these women from the model without SBP was 4.0%, while that from the model with SBP was 6.1%, which is closer to the observed risk of 6.8%." But I don't know where to get the average estimated risks from - can I somehow calculate them from the table?

Here is the data from the table cells

n <- c(20372, 696, 23,  0,
       635, 1441, 307, 7,
       4, 204, 519, 90,
       0, 2, 54, 204)

np <- c(96.6, 3.3, 0.1, 0.0,
        26.6, 60.3, 12.8, 0.3,
        0.5, 25.0, 63.5, 11.0,
        0.0, 0.8, 20.8, 78.5)

cases <- c(218, 38, 0, 0,
           22, 96, 36, 1,
           0, 7 , 59, 24,
           0, 0, 11, 48)

casesp <- c(82.2, 14.8, 0.0, 0.0,
           14.2, 61.9, 23.2, 0.6,
           0.0, 7.8, 65.6, 26.7,
           0.0, 0.0, 18.6, 81.4)

controls <- c(19933, 642, 23, 0,
              589, 1291, 263, 6,
              4, 188, 434, 58,
              0, 2 , 38, 140)

controlsp <- c(96.8, 3.1, 0.1, 0.0,
               27.4, 60.1, 12.2, 0.3,
               0.6, 27.5, 63.4, 8.5,
               0.0, 1.1, 21.1, 77.8)

observedrisk <- c(1.3, 6.8, 0.0, NA,
                  4.4, 8.4, 14.6, 17.5,
                  0.0, 4.3, 14.3, 34.2,
                  NA, 0.0, 25.9, 29.4)

df <- data.frame(n, np, cases, casesp, controls, controlsp, observedrisk)

Any help appretiated!

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.