mimic-iv/concepts/convert_bigquery_to_postgres: fix regular expressions

Currently, `REGEX_DATETIME_DIFF` doesn't match for all occurrences of
`DATETIME_DIFF` and `postgres-make-concepts.sql` errors out. For example:

```
psql:demographics/age.sql:30: ERROR:  column "year" does not exist
LINE 22: ...mittime, DATETIME(pa.anchor_year, 1, 1, 0, 0, 0), YEAR) + pa..
```

Also, `PERL_REGEX_ROUND` doesn't correctly match `ROUND(...)` with
nested functions, for example with a nested `DATETIME_DIFF`:

```
psql:demographics/icustay_detail.sql:33: ERROR:  syntax error at or near "as"
LINE 17: , ROUND( CAST( DATETIME_DIFF(ie.outtime as numeric),ie.intim...
```

Update both regular expressions accordingly.

Author: schu

mimic-iv/concepts/convert_bigquery_to_postgres.sh

@@ -4,12 +4,12 @@
 # String replacements are necessary for some queries.
 export REGEX_SCHEMA='s/`physionet-data.(mimiciv_hosp|mimiciv_icu|mimiciv_derived).([A-Za-z0-9_-]+)`/\1.\2/g'
 # Note that these queries are very senstive to changes, e.g. adding whitespaces after comma can already change the behavior.
-export REGEX_DATETIME_DIFF="s/DATETIME_DIFF\(([^,]+), ?([^,]+), ?(DAY|MINUTE|SECOND|HOUR|YEAR)\)/DATETIME_DIFF(\1, \2, '\3')/g"
+export REGEX_DATETIME_DIFF="s/DATETIME_DIFF\(([^,]+), ?(.*), ?(DAY|MINUTE|SECOND|HOUR|YEAR)\)/DATETIME_DIFF(\1, \2, '\3')/g"
 export REGEX_DATETIME_TRUNC="s/DATETIME_TRUNC\(([^,]+), ?(DAY|MINUTE|SECOND|HOUR|YEAR)\)/DATE_TRUNC('\2', \1)/g"
 # Add necessary quotes to INTERVAL, e.g. "INTERVAL 5 hour" to "INTERVAL '5' hour"
 export REGEX_INTERVAL="s/interval ([[:digit:]]+) (hour|day|month|year)/INTERVAL '\1' \2/gI"
 # Add numeric cast to ROUND(), e.g. "ROUND(1.234, 2)" to "ROUND( CAST(1.234 as numeric), 2)".
-export PERL_REGEX_ROUND='s/ROUND\(((.|\n)*?)\, /ROUND\( CAST\( \1 as numeric\)\,/g'
+export PERL_REGEX_ROUND='s/ROUND\(((.|\n)*?)(\, [24]\))/ROUND\( CAST\( \1 as numeric\)\3/g'
 # Specific queries for some problems that arose with some files.
 export REGEX_INT="s/CAST\(hr AS INT64\)/CAST\(hr AS bigint\)/g"
 export REGEX_ARRAY="s/GENERATE_ARRAY\(-24, CEIL\(DATETIME\_DIFF\(it\.outtime_hr, it\.intime_hr, HOUR\)\)\)/ARRAY\(SELECT \* FROM generate\_series\(-24, CEIL\(DATETIME\_DIFF\(it\.outtime_hr, it\.intime_hr, HOUR\)\)\)\)/g"

mimic-iv/concepts/postgres/demographics/age.sql

@@ -23,7 +23,7 @@ SELECT
 	, ad.admittime
 	, pa.anchor_age
 	, pa.anchor_year
-	, DATETIME_DIFF(ad.admittime, DATETIME(pa.anchor_year, 1, 1, 0, 0, 0), YEAR) + pa.anchor_age AS age
+	, DATETIME_DIFF(ad.admittime, DATETIME(pa.anchor_year, 1, 1, 0, 0, 0), 'YEAR') + pa.anchor_age AS age
 FROM mimiciv_hosp.admissions ad
 INNER JOIN mimiciv_hosp.patients pa
 ON ad.subject_id = pa.subject_id

mimic-iv/concepts/postgres/demographics/icustay_detail.sql

@@ -8,7 +8,7 @@ SELECT ie.subject_id, ie.hadm_id, ie.stay_id
 -- hospital level factors
 , adm.admittime, adm.dischtime
 , DATETIME_DIFF(adm.dischtime, adm.admittime, 'DAY') as los_hospital
-, DATETIME_DIFF(adm.admittime, DATETIME(pat.anchor_year, 1, 1, 0, 0, 0), YEAR) + pat.anchor_age as admission_age
+, DATETIME_DIFF(adm.admittime, DATETIME(pat.anchor_year, 1, 1, 0, 0, 0), 'YEAR') + pat.anchor_age as admission_age
 , adm.race
 , adm.hospital_expire_flag
 , DENSE_RANK() OVER (PARTITION BY adm.subject_id ORDER BY adm.admittime) AS hospstay_seq
@@ -18,7 +18,7 @@ SELECT ie.subject_id, ie.hadm_id, ie.stay_id
 
 -- icu level factors
 , ie.intime as icu_intime, ie.outtime as icu_outtime
-, ROUND( CAST( DATETIME_DIFF(ie.outtime as numeric),ie.intime, 'HOUR')/24.0, 2) as los_icu
+, ROUND( CAST( DATETIME_DIFF(ie.outtime, ie.intime, 'HOUR')/24.0 as numeric), 2) as los_icu
 , DENSE_RANK() OVER (PARTITION BY ie.hadm_id ORDER BY ie.intime) AS icustay_seq
 
 -- first ICU stay *for the current hospitalization*

mimic-iv/concepts/postgres/firstday/first_day_height.sql

@@ -23,7 +23,7 @@ WITH ce AS
 SELECT
     ie.subject_id
     , ie.stay_id
-    , ROUND( CAST( AVG(height) as numeric),2) AS height
+    , ROUND( CAST( AVG(height) as numeric), 2) AS height
 FROM mimiciv_icu.icustays ie
 LEFT JOIN mimiciv_derived.height ht
     ON ie.stay_id = ht.stay_id

mimic-iv/concepts/postgres/measurement/blood_differential.sql

@@ -100,27 +100,27 @@ subject_id, hadm_id, charttime, specimen_id
     WHEN basophils_abs IS NULL AND basophils IS NOT NULL AND impute_abs = 1
         THEN basophils * wbc / 100
     ELSE basophils_abs
-END as numeric),4) AS basophils_abs
+END as numeric), 4) AS basophils_abs
 , ROUND( CAST( CASE
     WHEN eosinophils_abs IS NULL AND eosinophils IS NOT NULL AND impute_abs = 1
         THEN eosinophils * wbc / 100
     ELSE eosinophils_abs
-END as numeric),4) AS eosinophils_abs
+END as numeric), 4) AS eosinophils_abs
 , ROUND( CAST( CASE
     WHEN lymphocytes_abs IS NULL AND lymphocytes IS NOT NULL AND impute_abs = 1
         THEN lymphocytes * wbc / 100
     ELSE lymphocytes_abs
-END as numeric),4) AS lymphocytes_abs
+END as numeric), 4) AS lymphocytes_abs
 , ROUND( CAST( CASE
     WHEN monocytes_abs IS NULL AND monocytes IS NOT NULL AND impute_abs = 1
         THEN monocytes * wbc / 100
     ELSE monocytes_abs
-END as numeric),4) AS monocytes_abs
+END as numeric), 4) AS monocytes_abs
 , ROUND( CAST( CASE
     WHEN neutrophils_abs IS NULL AND neutrophils IS NOT NULL AND impute_abs = 1
         THEN neutrophils * wbc / 100
     ELSE neutrophils_abs
-END as numeric),4) AS neutrophils_abs
+END as numeric), 4) AS neutrophils_abs
 
 , basophils
 , eosinophils

mimic-iv/concepts/postgres/measurement/height.sql

@@ -6,7 +6,7 @@ WITH ht_in AS
   SELECT 
     c.subject_id, c.stay_id, c.charttime
     -- Ensure that all heights are in centimeters
-    , ROUND( CAST( c.valuenum * 2.54 as numeric),2) AS height
+    , ROUND( CAST( c.valuenum * 2.54 as numeric), 2) AS height
     , c.valuenum as height_orig
   FROM mimiciv_icu.chartevents c
   WHERE c.valuenum IS NOT NULL
@@ -18,7 +18,7 @@ WITH ht_in AS
   SELECT 
     c.subject_id, c.stay_id, c.charttime
     -- Ensure that all heights are in centimeters
-    , ROUND( CAST( c.valuenum as numeric),2) AS height
+    , ROUND( CAST( c.valuenum as numeric), 2) AS height
   FROM mimiciv_icu.chartevents c
   WHERE c.valuenum IS NOT NULL
   -- Height cm

mimic-iv/concepts/postgres/measurement/urine_output_rate.sql

@@ -79,13 +79,13 @@ select
 , ur.urineoutput_6hr
 , ur.urineoutput_12hr
 , ur.urineoutput_24hr
-, CASE WHEN uo_tm_6hr >= 6 THEN ROUND( CAST( CAST((ur.urineoutput_6hr/wd.weight/uo_tm_6hr) AS NUMERIC) as numeric),4) END AS uo_mlkghr_6hr
-, CASE WHEN uo_tm_12hr >= 12 THEN ROUND( CAST( CAST((ur.urineoutput_12hr/wd.weight/uo_tm_12hr) AS NUMERIC) as numeric),4) END AS uo_mlkghr_12hr
-, CASE WHEN uo_tm_24hr >= 24 THEN ROUND( CAST( CAST((ur.urineoutput_24hr/wd.weight/uo_tm_24hr) AS NUMERIC) as numeric),4) END AS uo_mlkghr_24hr
+, CASE WHEN uo_tm_6hr >= 6 THEN ROUND( CAST( CAST((ur.urineoutput_6hr/wd.weight/uo_tm_6hr) AS NUMERIC) as numeric), 4) END AS uo_mlkghr_6hr
+, CASE WHEN uo_tm_12hr >= 12 THEN ROUND( CAST( CAST((ur.urineoutput_12hr/wd.weight/uo_tm_12hr) AS NUMERIC) as numeric), 4) END AS uo_mlkghr_12hr
+, CASE WHEN uo_tm_24hr >= 24 THEN ROUND( CAST( CAST((ur.urineoutput_24hr/wd.weight/uo_tm_24hr) AS NUMERIC) as numeric), 4) END AS uo_mlkghr_24hr
 -- time of earliest UO measurement that was used to calculate the rate
-, ROUND( CAST( uo_tm_6hr as numeric),2) AS uo_tm_6hr
-, ROUND( CAST( uo_tm_12hr as numeric),2) AS uo_tm_12hr
-, ROUND( CAST( uo_tm_24hr as numeric),2) AS uo_tm_24hr
+, ROUND( CAST( uo_tm_6hr as numeric), 2) AS uo_tm_6hr
+, ROUND( CAST( uo_tm_12hr as numeric), 2) AS uo_tm_12hr
+, ROUND( CAST( uo_tm_24hr as numeric), 2) AS uo_tm_24hr
 from ur_stg ur
 LEFT JOIN mimiciv_derived.weight_durations wd
     ON ur.stay_id = wd.stay_id

mimic-iv/concepts/postgres/measurement/vitalsign.sql

@@ -17,7 +17,7 @@ select
   , ROUND( CAST( 
       AVG(case when itemid in (223761) and valuenum > 70 and valuenum < 120 then (valuenum-32)/1.8 -- converted to degC in valuenum call
               when itemid in (223762) and valuenum > 10 and valuenum < 50  then valuenum else null end)
-     as numeric),2) as temperature
+     as numeric), 2) as temperature
   , MAX(CASE WHEN itemid = 224642 THEN value ELSE NULL END) AS temperature_site
   , AVG(case when itemid in (220277) and valuenum > 0 and valuenum <= 100 then valuenum else null end) as spo2
   , AVG(case when itemid in (225664,220621,226537) and valuenum > 0 then valuenum else null end) as glucose