--Sarcoma tumour cohort

select att.tumourid
, att.diagnosisyear
, att.site_icdo3rev2011_3char
, att.age
, morphological_subgroup
, case 
when sarcoma_group = 'Bone' then 'Bone sarcoma'
when sarcoma_group = 'STS' then 'Soft tissue sarcoma'
end as sarcoma_group
, case
-- GISTS of the OGJ get counted as oesophagus and hence other.  This code should only be used for 2018 diag onwards
when diagnosisyear >= 2018 and site_coded = 'C167' then 'Other'
when att.site_icdo3rev2011_3char = 'C16' then 'Stomach'
when att.site_icdo3rev2011_3char = 'C17' then 'Small intestine'
else 'Other' end
as GDO_gist_site
from av2020.av_tumour_england att
inner join GDO.morph_sarcoma sarc
--- join the lookup on site/morph/behaviour in ICD-O-3 Rev 2011
--- These fields only complete for 2013 onwards
on sarc.morph_icdo3rev2011 = att.morph_icdo3rev2011
and sarc.site_icdo3rev2011_3char = att.site_icdo3rev2011_3char
and sarc.behaviour_icdo3rev2011 = att.behaviour_icdo3rev2011
where 
diagnosisyear between 2013 and 2020
and ctry_code ='E' -- England residents using country code
and statusofregistration ='F' -- Finalised cases
and dedup_flag=1 -- Excluding duplicates, note quality issue in text above
and age between 0 and 200 -- Sensible age
and sex in (1,2) -- Known sex
-- Variation from CAS-SOP #1 : DO NOT EXCLUDE C44 or D codes, these are real sarcomas!
--- SEX EXCLUSION FOR C-CODES
and ((sex = '2' and site_icd10r4_o2_3char_from2013 not in ('C60','C61','C62','C63'))
or (sex = '1' and site_icd10r4_o2_3char_from2013 not in ('C51','C52','C53','C54','C55','C56','C57','C58'))) -- Sex doesn’t agree with tumour site
---- SEX EXCLUSION FOR D-CODES 
and ((sex = '2' and ((site_icd10r4_o2_3char_from2013 not in ('D29','D40')) AND (site_icd10r4_o2_from2013 not in ('D074','D075','D076')))) -- exclude male D-code tumours for females
or (sex = '1' and ((site_icd10r4_o2_3char_from2013 not in ('D06','D25','D26','D27','D28','D39')) AND (site_icd10r4_o2_from2013 not in ('D070','D071','D072','D073'))))) -- exclude female D-code tumours for males

;