mz-health/OMOP
mz-health
/
OMOP
mirror of https://github.com/OHDSI/CommonDataModel.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixing tables due to kable update, adding fix to drug_era script

This commit is contained in:
Clair Blacketer 2022-04-07 11:14:50 -04:00
parent 8451b5027b
commit 800dca15e2
10 changed files with 11322 additions and 11306 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6955
docs/cdm53.html
View File

File diff suppressed because it is too large Load Diff

7563
docs/cdm54.html
View File

File diff suppressed because it is too large Load Diff

7448
docs/cdm60.html
View File

File diff suppressed because it is too large Load Diff

12
docs/site_libs/header-attrs-2.13/header-attrs.js Normal file
View File

@ -0,0 +1,12 @@
// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
// be compatible with the behavior of Pandoc < 2.8).
document.addEventListener('DOMContentLoaded', function(e) {
var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
var i, h, a;
for (i = 0; i < hs.length; i++) {
h = hs[i];
if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6
a = h.attributes;
while (a.length > 0) h.removeAttribute(a[0].name);
}
});

2
docs/site_libs/navigation-1.1/codefolding.js
View File

@ -34,7 +34,9 @@ window.initializeCodeFolding = function(show) {
showCodeButton.append(showCodeText);
showCodeButton
.attr('data-toggle', 'collapse')
.attr('data-bs-toggle', 'collapse') // BS5
.attr('data-target', '#' + id)
.attr('data-bs-target', '#' + id) // BS5
.attr('aria-expanded', showThis)
.attr('aria-controls', id);

324
docs/sqlScripts.html
View File

@ -13,7 +13,7 @@
<title>sqlScripts.knit</title>
<script src="site_libs/header-attrs-2.11/header-attrs.js"></script>
<script src="site_libs/header-attrs-2.13/header-attrs.js"></script>
<script src="site_libs/jquery-3.6.0/jquery-3.6.0.min.js"></script>
<meta name="viewport" content="width=device-width, initial-scale=1" />
<link href="site_libs/bootstrap-3.3.5/css/cosmo.min.css" rel="stylesheet" />
@ -63,6 +63,7 @@ if (window.hljs) {
<link rel="stylesheet" href="style.css" type="text/css" />
@ -88,6 +89,9 @@ button.code-folding-btn:focus {
summary {
display: list-item;
}
details > summary > p:only-child {
display: inline;
}
pre code {
padding: 0;
}
@ -312,7 +316,7 @@ div.tocify {
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-bs-toggle="collapse" data-target="#navbar" data-bs-target="#navbar">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
@ -328,7 +332,7 @@ div.tocify {
</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-landmark"></span>
Background
@ -348,7 +352,7 @@ div.tocify {
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-list-alt"></span>
Conventions
@ -368,7 +372,7 @@ div.tocify {
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-history"></span>
CDM Versions
@ -386,7 +390,7 @@ div.tocify {
<a href="cdm53.html">CDM v5.3</a>
</li>
<li class="dropdown-submenu">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">NEW CDM v5.4</a>
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">NEW CDM v5.4</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="cdm54.html">CDM v5.4</a>
@ -399,7 +403,7 @@ div.tocify {
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-plus-square"></span>
Proposals
@ -411,7 +415,7 @@ div.tocify {
<a href="https://github.com/OHDSI/CommonDataModel/issues?q=is%3Aopen+is%3Aissue+label%3AProposal">Under Review</a>
</li>
<li class="dropdown-submenu">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">Accepted</a>
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">Accepted</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="https://github.com/OHDSI/CommonDataModel/issues/252">Region_concept_id</a>
@ -421,7 +425,7 @@ div.tocify {
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-question"></span>
How to
@ -441,7 +445,7 @@ div.tocify {
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-life-ring"></span>
Support
@ -700,174 +704,168 @@ GROUP BY person_id
<h3>Drug Eras</h3>
<p>If the DRUG_EXPOSURE table is populated this script will string together periods of time that a person is exposed to an active drug ingredient, allowing for 30 gaps in between. It will then insert the resulting era records into the DRUG_ERA table. <strong>NOTE</strong> This query only works with 5.3 and below.</p>
<pre class="sql"><code>
/****************************************************
OHDSI-SQL File Instructions
-----------------------------
1. Set parameter name of schema that contains CDMv4 instance
(@SOURCE_CDMV4, @SOURCE_CDMV4_SCHEMA)
2. Set parameter name of schema that contains CDMv5 instance
(@TARGET_CDMV5, @TARGET_CDMV5_SCHEMA)
3. Run this script through SqlRender to produce a script that will work in your
source dialect. SqlRender can be found here: https://github.com/OHDSI/SqlRender
4. Run the script produced by SQL Render on your target RDBDMS.
&lt;RDBMS&gt; File Instructions
-------------------------
1. This script will hold a number of placeholders for your CDM V4 and CDMV5
database/schema. In order to make this file work in your environment, you
should plan to do a global &quot;FIND AND REPLACE&quot; on this file to fill in the
file with values that pertain to your environment. The following are the
tokens you should use when doing your &quot;FIND AND REPLACE&quot; operation:
[CDM]
[CDM].[CDMSCHEMA]
*********************************************************************************/
/* SCRIPT PARAMETERS */
-- Code taken from:
-- https://github.com/OHDSI/ETL-CMS/blob/master/SQL/create_CDMv5_drug_era_non_stockpile.sql
{DEFAULT @TARGET_CDMV5 = &#39;[CDM]&#39; } -- The target CDMv5 database name
{DEFAULT @TARGET_CDMV5_SCHEMA = &#39;[CDM].[CDMSCHEMA]&#39; } -- the target CDMv5 database plus schema
if object_id(&#39;tempdb..#tmp_de&#39;, &#39;U&#39;) is not null drop table #tmp_de;
USE @TARGET_CDMV5;
WITH
ctePreDrugTarget(drug_exposure_id, person_id, ingredient_concept_id, drug_exposure_start_date, days_supply, drug_exposure_end_date) AS
(-- Normalize DRUG_EXPOSURE_END_DATE to either the existing drug exposure end date, or add days supply, or add 1 day to the start date
SELECT
d.drug_exposure_id
, d.person_id
, c.concept_id AS ingredient_concept_id
, d.drug_exposure_start_date AS drug_exposure_start_date
, d.days_supply AS days_supply
, COALESCE(
---NULLIF returns NULL if both values are the same, otherwise it returns the first parameter
NULLIF(drug_exposure_end_date, NULL),
---If drug_exposure_end_date != NULL, return drug_exposure_end_date, otherwise go to next case
NULLIF(dateadd(day,days_supply,drug_exposure_start_date), drug_exposure_start_date),
---If days_supply != NULL or 0, return drug_exposure_start_date + days_supply, otherwise go to next case
dateadd(day,1,drug_exposure_start_date)
---Add 1 day to the drug_exposure_start_date since there is no end_date or INTERVAL for the days_supply
) AS drug_exposure_end_date
FROM @cdm_schema.drug_exposure d
JOIN @cdm_schema.concept_ancestor ca ON ca.descendant_concept_id = d.drug_concept_id
JOIN @cdm_schema.concept c ON ca.ancestor_concept_id = c.concept_id
WHERE c.vocabulary_id = &#39;RxNorm&#39; ---8 selects RxNorm from the vocabulary_id
AND c.concept_class_id = &#39;Ingredient&#39;
AND d.drug_concept_id != 0 ---Our unmapped drug_concept_id&#39;s are set to 0, so we don&#39;t want different drugs wrapped up in the same era
AND coalesce(d.days_supply,0) &gt;= 0 ---We have cases where days_supply is negative, and this can set the end_date before the start_date, which we don&#39;t want. So we&#39;re just looking over those rows. This is a data-quality issue.
)
/****
DRUG ERA
Note: Eras derived from DRUG_EXPOSURE table, using 30d gap
****/
IF OBJECT_ID(&#39;tempdb..#cteDrugTarget&#39;, &#39;U&#39;) IS NOT NULL
DROP TABLE #cteDrugTarget;
/* / */
-- Normalize DRUG_EXPOSURE_END_DATE to either the existing drug exposure end date, or add days supply, or add 1 day to the start date
SELECT d.DRUG_EXPOSURE_ID
,d.PERSON_ID
,c.CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE
,COALESCE(DRUG_EXPOSURE_END_DATE, DATEADD(day, DAYS_SUPPLY, DRUG_EXPOSURE_START_DATE), DATEADD(day, 1, DRUG_EXPOSURE_START_DATE)) AS DRUG_EXPOSURE_END_DATE
,c.CONCEPT_ID AS INGREDIENT_CONCEPT_ID
INTO #cteDrugTarget
FROM @TARGET_CDMV5_SCHEMA.DRUG_EXPOSURE d
INNER JOIN @TARGET_CDMV5_SCHEMA.CONCEPT_ANCESTOR ca ON ca.DESCENDANT_CONCEPT_ID = d.DRUG_CONCEPT_ID
INNER JOIN @TARGET_CDMV5_SCHEMA.CONCEPT c ON ca.ANCESTOR_CONCEPT_ID = c.CONCEPT_ID
WHERE c.DOMAIN_ID = &#39;Drug&#39;
AND c.CONCEPT_CLASS_ID = &#39;Ingredient&#39;
AND c.STANDARD_CONCEPT = &#39;S&#39;;
/* / */
IF OBJECT_ID(&#39;tempdb..#cteEndDates&#39;, &#39;U&#39;) IS NOT NULL
DROP TABLE #cteEndDates;
/* / */
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DATEADD(day, - 30, EVENT_DATE) AS END_DATE -- unpad the end date
INTO #cteEndDates
FROM (
SELECT E1.PERSON_ID
,E1.INGREDIENT_CONCEPT_ID
,E1.EVENT_DATE
,COALESCE(E1.START_ORDINAL, MAX(E2.START_ORDINAL)) START_ORDINAL
,E1.OVERALL_ORD
FROM (
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,EVENT_DATE
,EVENT_TYPE
,START_ORDINAL
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY EVENT_DATE
,EVENT_TYPE
) AS OVERALL_ORD -- this re-numbers the inner UNION so all rows are numbered ordered by the event date
, cteSubExposureEndDates (person_id, ingredient_concept_id, end_date) AS --- A preliminary sorting that groups all of the overlapping exposures into one exposure so that we don&#39;t double-count non-gap-days
(
SELECT person_id, ingredient_concept_id, event_date AS end_date
FROM
(
SELECT person_id, ingredient_concept_id, event_date, event_type,
MAX(start_ordinal) OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type ROWS unbounded preceding) AS start_ordinal,
-- this pulls the current START down from the prior rows so that the NULLs
-- from the END DATES will contain a value we can compare with
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type) AS overall_ord
-- this re-numbers the inner UNION so all rows are numbered ordered by the event date
FROM (
-- select the start dates, assigning a row number to each
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE AS EVENT_DATE
,0 AS EVENT_TYPE
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY DRUG_EXPOSURE_START_DATE
) AS START_ORDINAL
FROM #cteDrugTarget
SELECT person_id, ingredient_concept_id, drug_exposure_start_date AS event_date,
-1 AS event_type,
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY drug_exposure_start_date) AS start_ordinal
FROM ctePreDrugTarget
UNION ALL
-- add the end dates with NULL as the row number, padding the end dates by 30 to allow a grace period for overlapping ranges.
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DATEADD(day, 30, DRUG_EXPOSURE_END_DATE)
,1 AS EVENT_TYPE
,NULL
FROM #cteDrugTarget
SELECT person_id, ingredient_concept_id, drug_exposure_end_date, 1 AS event_type, NULL
FROM ctePreDrugTarget
) RAWDATA
) E1
INNER JOIN (
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE AS EVENT_DATE
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY DRUG_EXPOSURE_START_DATE
) AS START_ORDINAL
FROM #cteDrugTarget
) E2 ON E1.PERSON_ID = E2.PERSON_ID
AND E1.INGREDIENT_CONCEPT_ID = E2.INGREDIENT_CONCEPT_ID
AND E2.EVENT_DATE &lt;= E1.EVENT_DATE
GROUP BY E1.PERSON_ID
,E1.INGREDIENT_CONCEPT_ID
,E1.EVENT_DATE
,E1.START_ORDINAL
,E1.OVERALL_ORD
) E
WHERE 2 * E.START_ORDINAL - E.OVERALL_ORD = 0;
) e
WHERE (2 * e.start_ordinal) - e.overall_ord = 0
)
/* / */
, cteDrugExposureEnds (person_id, drug_concept_id, drug_exposure_start_date, drug_sub_exposure_end_date) AS
(
SELECT
dt.person_id
, dt.ingredient_concept_id
, dt.drug_exposure_start_date
, MIN(e.end_date) AS drug_sub_exposure_end_date
FROM ctePreDrugTarget dt
JOIN cteSubExposureEndDates e ON dt.person_id = e.person_id AND dt.ingredient_concept_id = e.ingredient_concept_id AND e.end_date &gt;= dt.drug_exposure_start_date
GROUP BY
dt.drug_exposure_id
, dt.person_id
, dt.ingredient_concept_id
, dt.drug_exposure_start_date
)
--------------------------------------------------------------------------------------------------------------
, cteSubExposures(row_number, person_id, drug_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count) AS
(
SELECT ROW_NUMBER() OVER (PARTITION BY person_id, drug_concept_id, drug_sub_exposure_end_date ORDER BY person_id)
, person_id, drug_concept_id, MIN(drug_exposure_start_date) AS drug_sub_exposure_start_date, drug_sub_exposure_end_date, COUNT(*) AS drug_exposure_count
FROM cteDrugExposureEnds
GROUP BY person_id, drug_concept_id, drug_sub_exposure_end_date
--ORDER BY person_id, drug_concept_id
)
--------------------------------------------------------------------------------------------------------------
/*Everything above grouped exposures into sub_exposures if there was overlap between exposures.
*So there was no persistence window. Now we can add the persistence window to calculate eras.
*/
--------------------------------------------------------------------------------------------------------------
, cteFinalTarget(row_number, person_id, ingredient_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count, days_exposed) AS
(
SELECT row_number, person_id, drug_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count
, datediff(day,drug_sub_exposure_start_date,drug_sub_exposure_end_date) AS days_exposed
FROM cteSubExposures
)
--------------------------------------------------------------------------------------------------------------
, cteEndDates (person_id, ingredient_concept_id, end_date) AS -- the magic
(
SELECT person_id, ingredient_concept_id, dateadd(day,-30,event_date) AS end_date -- unpad the end date
FROM
(
SELECT person_id, ingredient_concept_id, event_date, event_type,
MAX(start_ordinal) OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type ROWS UNBOUNDED PRECEDING) AS start_ordinal,
-- this pulls the current START down from the prior rows so that the NULLs
-- from the END DATES will contain a value we can compare with
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type) AS overall_ord
-- this re-numbers the inner UNION so all rows are numbered ordered by the event date
FROM (
-- select the start dates, assigning a row number to each
SELECT person_id, ingredient_concept_id, drug_sub_exposure_start_date AS event_date,
-1 AS event_type,
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY drug_sub_exposure_start_date) AS start_ordinal
FROM cteFinalTarget
IF OBJECT_ID(&#39;tempdb..#cteDrugExpEnds&#39;, &#39;U&#39;) IS NOT NULL
DROP TABLE #cteDrugExpEnds;
UNION ALL
/* / */
-- pad the end dates by 30 to allow a grace period for overlapping ranges.
SELECT person_id, ingredient_concept_id, dateadd(day,30,drug_sub_exposure_end_date), 1 AS event_type, NULL
FROM cteFinalTarget
) RAWDATA
) e
WHERE (2 * e.start_ordinal) - e.overall_ord = 0
SELECT d.PERSON_ID
,d.INGREDIENT_CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,d.DRUG_EXPOSURE_START_DATE
,MIN(e.END_DATE) AS ERA_END_DATE
INTO #cteDrugExpEnds
FROM #cteDrugTarget d
INNER JOIN #cteEndDates e ON d.PERSON_ID = e.PERSON_ID
AND d.INGREDIENT_CONCEPT_ID = e.INGREDIENT_CONCEPT_ID
AND e.END_DATE &gt;= d.DRUG_EXPOSURE_START_DATE
GROUP BY d.PERSON_ID
,d.INGREDIENT_CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,d.DRUG_EXPOSURE_START_DATE;
/* / */
INSERT INTO @TARGET_CDMV5_SCHEMA.drug_era
SELECT row_number() OVER (
ORDER BY person_id
) AS drug_era_id
)
, cteDrugEraEnds (person_id, drug_concept_id, drug_sub_exposure_start_date, drug_era_end_date, drug_exposure_count, days_exposed) AS
(
SELECT
ft.person_id
, ft.ingredient_concept_id
, ft.drug_sub_exposure_start_date
, MIN(e.end_date) AS era_end_date
, drug_exposure_count
, days_exposed
FROM cteFinalTarget ft
JOIN cteEndDates e ON ft.person_id = e.person_id AND ft.ingredient_concept_id = e.ingredient_concept_id AND e.end_date &gt;= ft.drug_sub_exposure_start_date
GROUP BY
ft.person_id
, ft.ingredient_concept_id
, ft.drug_sub_exposure_start_date
, drug_exposure_count
, days_exposed
)
SELECT
row_number()over(order by person_id) drug_era_id
, person_id
,INGREDIENT_CONCEPT_ID
,min(DRUG_EXPOSURE_START_DATE) AS drug_era_start_date
,ERA_END_DATE
,COUNT(*) AS DRUG_EXPOSURE_COUNT
,30 AS gap_days
FROM #cteDrugExpEnds
GROUP BY person_id
,INGREDIENT_CONCEPT_ID
,drug_type_concept_id
,ERA_END_DATE;
</code></pre>
, drug_concept_id
, MIN(drug_sub_exposure_start_date) AS drug_era_start_date
, drug_era_end_date
, SUM(drug_exposure_count) AS drug_exposure_count
, datediff(day,MIN(drug_sub_exposure_start_date),drug_era_end_date)-SUM(days_exposed) as gap_days
INTO #tmp_de
FROM cteDrugEraEnds dee
GROUP BY person_id, drug_concept_id, drug_era_end_date;
INSERT INTO @cdm_schema.drug_era(drug_era_id,person_id, drug_concept_id, drug_era_start_date, drug_era_end_date, drug_exposure_count, gap_days)
SELECT * FROM #tmp_de;</code></pre>
</div>
</div>
<div id="example-etl-script" class="section level2">

6
rmd/cdm53.Rmd
View File

@ -92,9 +92,9 @@ for(tb in tables) {
print(kable(x = loopTable, align = "l", row.names = FALSE, format = "html", escape = FALSE) %>%
column_spec(1, bold = T) %>%
column_spec(2, width = "3in", include_thead = T) %>%
column_spec(3, width = "4in", include_thead = T) %>%
column_spec(4:9, width = "1in", include_thead = T) %>%
# column_spec(2, width = "3in", include_thead = T) %>%
# column_spec(3, width = "4in", include_thead = T) %>%
# column_spec(4:9, width = "1in", include_thead = T) %>%
kable_styling(c("condensed","hover"), position = "center", full_width = T, font_size = 13))

6
rmd/cdm54.Rmd
View File

@ -108,9 +108,9 @@ for(tb in tables) {
print(kable(x = loopTable, align = "l", row.names = FALSE, format = "html", escape = FALSE) %>%
column_spec(1, bold = T) %>%
column_spec(2, width = "3in", include_thead = T) %>%
column_spec(3, width = "4in", include_thead = T) %>%
column_spec(4:9, width = "1in", include_thead = T) %>%
# column_spec(2, width = "3in", include_thead = T) %>%
# column_spec(3, width = "4in", include_thead = T) %>%
# column_spec(4:9, width = "1in", include_thead = T) %>%
kable_styling(c("condensed","hover"), position = "center", full_width = T, font_size = 13))

6
rmd/cdm60.Rmd
View File

@ -104,9 +104,9 @@ for(tb in tables) {
print(kable(x = loopTable, align = "l", row.names = FALSE, format = "html") %>%
column_spec(1, bold = T) %>%
column_spec(2, width = "3in", include_thead = T) %>%
column_spec(3, width = "4in", include_thead = T) %>%
column_spec(4:9, width = "1in", include_thead = T) %>%
# column_spec(2, width = "3in", include_thead = T) %>%
# column_spec(3, width = "4in", include_thead = T) %>%
# column_spec(4:9, width = "1in", include_thead = T) %>%
kable_styling(c("condensed","hover"), position = "center", full_width = T, font_size = 13))

300
rmd/sqlScripts.Rmd
View File

@ -232,178 +232,172 @@ GROUP BY person_id
### Drug Eras
If the DRUG_EXPOSURE table is populated this script will string together periods of time that a person is exposed to an active drug ingredient, allowing for 30 gaps in between. It will then insert the resulting era records into the DRUG_ERA table. **NOTE** This query only works with 5.3 and below.
If the DRUG_EXPOSURE table is populated this script will string together periods of time that a person is exposed to an active drug ingredient, allowing for 30 gaps in between. It will then insert the resulting era records into the DRUG_ERA table. **NOTE** This query only works with the **version 5** series and below.
```{sql eval = FALSE, echo = TRUE}
/****************************************************
OHDSI-SQL File Instructions
-----------------------------
1. Set parameter name of schema that contains CDMv4 instance
(@SOURCE_CDMV4, @SOURCE_CDMV4_SCHEMA)
2. Set parameter name of schema that contains CDMv5 instance
(@TARGET_CDMV5, @TARGET_CDMV5_SCHEMA)
3. Run this script through SqlRender to produce a script that will work in your
source dialect. SqlRender can be found here: https://github.com/OHDSI/SqlRender
4. Run the script produced by SQL Render on your target RDBDMS.
<RDBMS> File Instructions
-------------------------
1. This script will hold a number of placeholders for your CDM V4 and CDMV5
database/schema. In order to make this file work in your environment, you
should plan to do a global "FIND AND REPLACE" on this file to fill in the
file with values that pertain to your environment. The following are the
tokens you should use when doing your "FIND AND REPLACE" operation:
[CDM]
[CDM].[CDMSCHEMA]
*********************************************************************************/
/* SCRIPT PARAMETERS */
-- Code taken from:
-- https://github.com/OHDSI/ETL-CMS/blob/master/SQL/create_CDMv5_drug_era_non_stockpile.sql
{DEFAULT @TARGET_CDMV5 = '[CDM]' } -- The target CDMv5 database name
{DEFAULT @TARGET_CDMV5_SCHEMA = '[CDM].[CDMSCHEMA]' } -- the target CDMv5 database plus schema
if object_id('tempdb..#tmp_de', 'U') is not null drop table #tmp_de;
USE @TARGET_CDMV5;
WITH
ctePreDrugTarget(drug_exposure_id, person_id, ingredient_concept_id, drug_exposure_start_date, days_supply, drug_exposure_end_date) AS
(-- Normalize DRUG_EXPOSURE_END_DATE to either the existing drug exposure end date, or add days supply, or add 1 day to the start date
SELECT
d.drug_exposure_id
, d.person_id
, c.concept_id AS ingredient_concept_id
, d.drug_exposure_start_date AS drug_exposure_start_date
, d.days_supply AS days_supply
, COALESCE(
---NULLIF returns NULL if both values are the same, otherwise it returns the first parameter
NULLIF(drug_exposure_end_date, NULL),
---If drug_exposure_end_date != NULL, return drug_exposure_end_date, otherwise go to next case
NULLIF(dateadd(day,days_supply,drug_exposure_start_date), drug_exposure_start_date),
---If days_supply != NULL or 0, return drug_exposure_start_date + days_supply, otherwise go to next case
dateadd(day,1,drug_exposure_start_date)
---Add 1 day to the drug_exposure_start_date since there is no end_date or INTERVAL for the days_supply
) AS drug_exposure_end_date
FROM @cdm_schema.drug_exposure d
JOIN @cdm_schema.concept_ancestor ca ON ca.descendant_concept_id = d.drug_concept_id
JOIN @cdm_schema.concept c ON ca.ancestor_concept_id = c.concept_id
WHERE c.vocabulary_id = 'RxNorm' ---8 selects RxNorm from the vocabulary_id
AND c.concept_class_id = 'Ingredient'
AND d.drug_concept_id != 0 ---Our unmapped drug_concept_id's are set to 0, so we don't want different drugs wrapped up in the same era
AND coalesce(d.days_supply,0) >= 0 ---We have cases where days_supply is negative, and this can set the end_date before the start_date, which we don't want. So we're just looking over those rows. This is a data-quality issue.
)
/****
DRUG ERA
Note: Eras derived from DRUG_EXPOSURE table, using 30d gap
****/
IF OBJECT_ID('tempdb..#cteDrugTarget', 'U') IS NOT NULL
DROP TABLE #cteDrugTarget;
/* / */
-- Normalize DRUG_EXPOSURE_END_DATE to either the existing drug exposure end date, or add days supply, or add 1 day to the start date
SELECT d.DRUG_EXPOSURE_ID
,d.PERSON_ID
,c.CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE
,COALESCE(DRUG_EXPOSURE_END_DATE, DATEADD(day, DAYS_SUPPLY, DRUG_EXPOSURE_START_DATE), DATEADD(day, 1, DRUG_EXPOSURE_START_DATE)) AS DRUG_EXPOSURE_END_DATE
,c.CONCEPT_ID AS INGREDIENT_CONCEPT_ID
INTO #cteDrugTarget
FROM @TARGET_CDMV5_SCHEMA.DRUG_EXPOSURE d
INNER JOIN @TARGET_CDMV5_SCHEMA.CONCEPT_ANCESTOR ca ON ca.DESCENDANT_CONCEPT_ID = d.DRUG_CONCEPT_ID
INNER JOIN @TARGET_CDMV5_SCHEMA.CONCEPT c ON ca.ANCESTOR_CONCEPT_ID = c.CONCEPT_ID
WHERE c.DOMAIN_ID = 'Drug'
AND c.CONCEPT_CLASS_ID = 'Ingredient'
AND c.STANDARD_CONCEPT = 'S';
/* / */
IF OBJECT_ID('tempdb..#cteEndDates', 'U') IS NOT NULL
DROP TABLE #cteEndDates;
/* / */
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DATEADD(day, - 30, EVENT_DATE) AS END_DATE -- unpad the end date
INTO #cteEndDates
FROM (
SELECT E1.PERSON_ID
,E1.INGREDIENT_CONCEPT_ID
,E1.EVENT_DATE
,COALESCE(E1.START_ORDINAL, MAX(E2.START_ORDINAL)) START_ORDINAL
,E1.OVERALL_ORD
FROM (
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,EVENT_DATE
,EVENT_TYPE
,START_ORDINAL
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY EVENT_DATE
,EVENT_TYPE
) AS OVERALL_ORD -- this re-numbers the inner UNION so all rows are numbered ordered by the event date
, cteSubExposureEndDates (person_id, ingredient_concept_id, end_date) AS --- A preliminary sorting that groups all of the overlapping exposures into one exposure so that we don't double-count non-gap-days
(
SELECT person_id, ingredient_concept_id, event_date AS end_date
FROM
(
SELECT person_id, ingredient_concept_id, event_date, event_type,
MAX(start_ordinal) OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type ROWS unbounded preceding) AS start_ordinal,
-- this pulls the current START down from the prior rows so that the NULLs
-- from the END DATES will contain a value we can compare with
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type) AS overall_ord
-- this re-numbers the inner UNION so all rows are numbered ordered by the event date
FROM (
-- select the start dates, assigning a row number to each
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE AS EVENT_DATE
,0 AS EVENT_TYPE
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY DRUG_EXPOSURE_START_DATE
) AS START_ORDINAL
FROM #cteDrugTarget
SELECT person_id, ingredient_concept_id, drug_exposure_start_date AS event_date,
-1 AS event_type,
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY drug_exposure_start_date) AS start_ordinal
FROM ctePreDrugTarget
UNION ALL
-- add the end dates with NULL as the row number, padding the end dates by 30 to allow a grace period for overlapping ranges.
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DATEADD(day, 30, DRUG_EXPOSURE_END_DATE)
,1 AS EVENT_TYPE
,NULL
FROM #cteDrugTarget
SELECT person_id, ingredient_concept_id, drug_exposure_end_date, 1 AS event_type, NULL
FROM ctePreDrugTarget
) RAWDATA
) E1
INNER JOIN (
SELECT PERSON_ID
,INGREDIENT_CONCEPT_ID
,DRUG_EXPOSURE_START_DATE AS EVENT_DATE
,ROW_NUMBER() OVER (
PARTITION BY PERSON_ID
,INGREDIENT_CONCEPT_ID ORDER BY DRUG_EXPOSURE_START_DATE
) AS START_ORDINAL
FROM #cteDrugTarget
) E2 ON E1.PERSON_ID = E2.PERSON_ID
AND E1.INGREDIENT_CONCEPT_ID = E2.INGREDIENT_CONCEPT_ID
AND E2.EVENT_DATE <= E1.EVENT_DATE
GROUP BY E1.PERSON_ID
,E1.INGREDIENT_CONCEPT_ID
,E1.EVENT_DATE
,E1.START_ORDINAL
,E1.OVERALL_ORD
) E
WHERE 2 * E.START_ORDINAL - E.OVERALL_ORD = 0;
) e
WHERE (2 * e.start_ordinal) - e.overall_ord = 0
)
/* / */
, cteDrugExposureEnds (person_id, drug_concept_id, drug_exposure_start_date, drug_sub_exposure_end_date) AS
(
SELECT
dt.person_id
, dt.ingredient_concept_id
, dt.drug_exposure_start_date
, MIN(e.end_date) AS drug_sub_exposure_end_date
FROM ctePreDrugTarget dt
JOIN cteSubExposureEndDates e ON dt.person_id = e.person_id AND dt.ingredient_concept_id = e.ingredient_concept_id AND e.end_date >= dt.drug_exposure_start_date
GROUP BY
dt.drug_exposure_id
, dt.person_id
, dt.ingredient_concept_id
, dt.drug_exposure_start_date
)
--------------------------------------------------------------------------------------------------------------
, cteSubExposures(row_number, person_id, drug_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count) AS
(
SELECT ROW_NUMBER() OVER (PARTITION BY person_id, drug_concept_id, drug_sub_exposure_end_date ORDER BY person_id)
, person_id, drug_concept_id, MIN(drug_exposure_start_date) AS drug_sub_exposure_start_date, drug_sub_exposure_end_date, COUNT(*) AS drug_exposure_count
FROM cteDrugExposureEnds
GROUP BY person_id, drug_concept_id, drug_sub_exposure_end_date
--ORDER BY person_id, drug_concept_id
)
--------------------------------------------------------------------------------------------------------------
/*Everything above grouped exposures into sub_exposures if there was overlap between exposures.
*So there was no persistence window. Now we can add the persistence window to calculate eras.
*/
--------------------------------------------------------------------------------------------------------------
, cteFinalTarget(row_number, person_id, ingredient_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count, days_exposed) AS
(
SELECT row_number, person_id, drug_concept_id, drug_sub_exposure_start_date, drug_sub_exposure_end_date, drug_exposure_count
, datediff(day,drug_sub_exposure_start_date,drug_sub_exposure_end_date) AS days_exposed
FROM cteSubExposures
)
--------------------------------------------------------------------------------------------------------------
, cteEndDates (person_id, ingredient_concept_id, end_date) AS -- the magic
(
SELECT person_id, ingredient_concept_id, dateadd(day,-30,event_date) AS end_date -- unpad the end date
FROM
(
SELECT person_id, ingredient_concept_id, event_date, event_type,
MAX(start_ordinal) OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type ROWS UNBOUNDED PRECEDING) AS start_ordinal,
-- this pulls the current START down from the prior rows so that the NULLs
-- from the END DATES will contain a value we can compare with
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY event_date, event_type) AS overall_ord
-- this re-numbers the inner UNION so all rows are numbered ordered by the event date
FROM (
-- select the start dates, assigning a row number to each
SELECT person_id, ingredient_concept_id, drug_sub_exposure_start_date AS event_date,
-1 AS event_type,
ROW_NUMBER() OVER (PARTITION BY person_id, ingredient_concept_id
ORDER BY drug_sub_exposure_start_date) AS start_ordinal
FROM cteFinalTarget
IF OBJECT_ID('tempdb..#cteDrugExpEnds', 'U') IS NOT NULL
DROP TABLE #cteDrugExpEnds;
UNION ALL
/* / */
-- pad the end dates by 30 to allow a grace period for overlapping ranges.
SELECT person_id, ingredient_concept_id, dateadd(day,30,drug_sub_exposure_end_date), 1 AS event_type, NULL
FROM cteFinalTarget
) RAWDATA
) e
WHERE (2 * e.start_ordinal) - e.overall_ord = 0
SELECT d.PERSON_ID
,d.INGREDIENT_CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,d.DRUG_EXPOSURE_START_DATE
,MIN(e.END_DATE) AS ERA_END_DATE
INTO #cteDrugExpEnds
FROM #cteDrugTarget d
INNER JOIN #cteEndDates e ON d.PERSON_ID = e.PERSON_ID
AND d.INGREDIENT_CONCEPT_ID = e.INGREDIENT_CONCEPT_ID
AND e.END_DATE >= d.DRUG_EXPOSURE_START_DATE
GROUP BY d.PERSON_ID
,d.INGREDIENT_CONCEPT_ID
,d.DRUG_TYPE_CONCEPT_ID
,d.DRUG_EXPOSURE_START_DATE;
/* / */
INSERT INTO @TARGET_CDMV5_SCHEMA.drug_era
SELECT row_number() OVER (
ORDER BY person_id
) AS drug_era_id
)
, cteDrugEraEnds (person_id, drug_concept_id, drug_sub_exposure_start_date, drug_era_end_date, drug_exposure_count, days_exposed) AS
(
SELECT
ft.person_id
, ft.ingredient_concept_id
, ft.drug_sub_exposure_start_date
, MIN(e.end_date) AS era_end_date
, drug_exposure_count
, days_exposed
FROM cteFinalTarget ft
JOIN cteEndDates e ON ft.person_id = e.person_id AND ft.ingredient_concept_id = e.ingredient_concept_id AND e.end_date >= ft.drug_sub_exposure_start_date
GROUP BY
ft.person_id
, ft.ingredient_concept_id
, ft.drug_sub_exposure_start_date
, drug_exposure_count
, days_exposed
)
SELECT
row_number()over(order by person_id) drug_era_id
, person_id
,INGREDIENT_CONCEPT_ID
,min(DRUG_EXPOSURE_START_DATE) AS drug_era_start_date
,ERA_END_DATE
,COUNT(*) AS DRUG_EXPOSURE_COUNT
,30 AS gap_days
FROM #cteDrugExpEnds
GROUP BY person_id
,INGREDIENT_CONCEPT_ID
,drug_type_concept_id
,ERA_END_DATE;
, drug_concept_id
, MIN(drug_sub_exposure_start_date) AS drug_era_start_date
, drug_era_end_date
, SUM(drug_exposure_count) AS drug_exposure_count
, datediff(day,MIN(drug_sub_exposure_start_date),drug_era_end_date)-SUM(days_exposed) as gap_days
INTO #tmp_de
FROM cteDrugEraEnds dee
GROUP BY person_id, drug_concept_id, drug_era_end_date;
INSERT INTO @cdm_schema.drug_era(drug_era_id,person_id, drug_concept_id, drug_era_start_date, drug_era_end_date, drug_exposure_count, gap_days)
SELECT * FROM #tmp_de;
```
## **Example ETL Script**