http://www.julesberman.info/seerdist.pdf
With this data, it is possible to review the graphic distributions and to find trends or anomalies of biologic importance.
For example, consider the occurrences of mesothelioma, by age, and by site, comparing mesotheliomas of the pleura and of the peritoneum.
Crude occurrences of pleural mesothelioma, by age
Crude - 0 0 0 3 4 9 27 45 88 184 310 495 664 885 1066 1075 759 412
Normalized rate of pleural mesotheliomas
Normalized - 0 0 0 1 2 4 13 19 39 92 178 370 617 927 1202 1451 1540 975
Crude occurrences of peritoneal mesothelioma, by age
Crude - 0 0 0 3 4 11 12 21 30 40 48 83 110 103 107 75 44 27
Normalized rate of peritoneal mesotheliomas
Normalized - 0 0 0 1 2 5 5 9 13 20 27 62 102 107 120 101 89 63
From the numbers, it is clear that pleural mesothelioma occurs much more frequently than peritoneal mesothelioma.
In addition, there seems to be about a ten year difference in the peak age of occurrence of pleural and peritoneal mesotheliomas. Peritoneal mesotheliomas seem to occur in a slightly younger age group.
How can we determine whether this apparent difference in the age distributions of pleural and peritoneal mesotheliomas is, in fact, significant?
A short Perl script calls an external statistics module that accepts the normalized age distributions of pleural and peritoneal mesotheliomas and applies the F and Student t tests. (Note: you must install the Statistics::TTest module to run the script)
#!/usr/bin/perl
use Statistics::PointEstimation;
use Statistics::TTest;
open(STDOUT, ">tftest.txt");
my @r1=qw(0 0 0 1 2 4 13 19 39 92 178 370 617 927 1202 1451 1540 975);
my @r2=qw(0 0 0 1 2 5 5 9 13 20 27 62 102 107 120 101 89 63);
my $ttest = new Statistics::TTest;
$ttest->set_significance(98);
$ttest->load_data(\@r1,\@r2);
$ttest->output_t_test();
$ttest->print_t_test(); #list out t-test related data
exit;
The output is shown:
Click on the image to see a larger format.The Perl script produces an F-test and t-test statistic for the distribution of normalized mesothelioma rates, for pleural and peritoneal sites, by age.
We can be confident, at a 98% confidence level, that there is a difference in the population that develops pleural mesothelioma, compared with the population that develops peritoneal mesothelioma.
What can account for this difference? Assuming no statistical error (i.e., falsely rejecting the null hypothesis), I see four possibilities.
1. Multiple diseases in one name
(i.e. peritoneal mesothelioma may be a biologically distinct neoplasm, different from pleural mesothelioma).
2. Multiple environmental causes
(i.e. the causes of pleural mesothelioma are different from the causes of peritoneal mesothelioma, resulting in a different age distribution of these tumors).
3. Multiple genetic causes with different latencies
(i.e., gene variants that predispose pleural mesothelioma may be different from gene variants that predispose peritoneal mesothelioma, accounting for different latency periods and differences in the age distribution of tumors)
4. Faulty or insufficient data
(i.e. the differences are due to faulty data)
5. Combinations of 1,2,3, and 4
If anyone reading this blog can think of any other explanation(s), please comment.
Other web pages related to this topic are:
http://www.julesberman.info/seerdist.pdf
http://www.julesberman.info/seer2.htm
http://www.julesberman.info/cdc_ch.pdf
-© 2008 Jules Berman
As with all of my scripts, lists, web sites, and blog entries, the following disclaimer applies. This material is provided by its creator, Jules J. Berman, "as is", without warranty of any kind, expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. In no event shall the author or copyright holder be liable for any claim, damages or other liability, whether in an action of contract, tort or otherwise, arising from, out of or in connection with the material or the use or other dealings.
key words: pleura, peritoneum, abdominal mesothelioma, subtype, neoplasms, neoplasms, carcinogenesis, epidemiology
In June, 2014, my book, entitled Rare Diseases and Orphan Drugs: Keys to Understanding and Treating the Common Diseases was published by Elsevier. The book builds the argument that our best chance of curing the common diseases will come from studying and curing the rare diseases.
I urge you to read more about my book. There's a generous preview of the book at the Google Books site.
