This function is useful for verifying that raw or residual phenotype risk scores of diagnosed individuals (cases) tend to be higher than scores of undiagnosed individuals (controls).
Usage
getDxStatus(
demos,
icdOccurrences,
minUniqueAges = 2L,
diseaseDxIcdMap = phers::diseaseDxIcdMap
)Arguments
- demos
A data.table having one row per person in the cohort. Must have a column
person_id.- icdOccurrences
A data.table of occurrences of ICD codes for each person in the cohort. Must have columns
person_id,icd,flag, andoccurrence_age.- minUniqueAges
Integer indicating the minimum number of unique ICD code entry ages required to classify a person as a case. Persons with at least one, but fewer than
minUniqueAgesentry ages, are assigned as neither cases nor controls.- diseaseDxIcdMap
A data.table of the mapping between diseases and the corresponding ICD codes that indicate a diagnosis. Must have columns
disease_id,icd, andflag. Default is diseaseDxIcdMap.
Value
A data.table with columns person_id, disease_id, and dx_status
(1 indicates a case, 0 indicates a control, -1 indicates neither).
Examples
library('data.table')
icdSample1 = merge(icdSample, demoSample[, .(person_id, dob)], by = 'person_id')
icdSample1[, occurrence_age := as.numeric((entry_date - dob)/365.25)]
#> person_id icd flag entry_date dob occurrence_age
#> 1: 1 365 9 2014-03-10 1925-05-24 88.796699
#> 2: 1 366 9 2014-11-07 1925-05-24 89.459259
#> 3: 1 734 9 2014-05-28 1925-05-24 89.012989
#> 4: 1 759.82 9 2014-02-15 1925-05-24 88.733728
#> 5: 2 441 9 2011-10-10 1976-06-05 35.346012
#> 6: 2 524.0 9 2012-11-04 1976-06-05 36.416511
#> 7: 2 718.4 9 2014-10-28 1976-06-05 38.395977
#> 8: 2 759.82 9 2014-12-29 1976-06-05 38.565724
#> 9: 2 759.82 9 2015-10-03 1976-06-05 39.326847
#> 10: 3 366 9 2005-09-28 1942-07-02 63.239370
#> 11: 3 734 9 2007-03-17 1942-07-02 64.704120
#> 12: 4 441 9 2019-10-15 1986-03-22 33.566328
#> 13: 5 331.9 9 2011-03-08 1969-07-01 41.684307
#> 14: 5 362.07 9 2011-06-07 1969-07-01 41.933451
#> 15: 5 369.25 9 2011-05-06 1969-07-01 41.845840
#> 16: 5 812.10 9 2011-03-26 1969-07-01 41.733588
#> 17: 6 811.11 9 2014-04-27 2001-01-10 13.291612
#> 18: 6 958.3 9 2005-06-14 2001-01-10 4.423713
#> 19: 6 V33.1 9 2004-12-14 2001-01-10 3.925424
#> 20: 7 062.8 9 2010-10-13 1973-11-05 36.938331
#> 21: 7 607.83 9 2010-10-13 1973-11-05 36.938331
#> 22: 7 712.17 9 2010-10-13 1973-11-05 36.938331
#> 23: 7 785.52 9 2010-10-13 1973-11-05 36.938331
#> 24: 7 788.30 9 2010-10-13 1973-11-05 36.938331
#> 25: 8 077 9 2017-03-30 2009-06-02 7.824870
#> 26: 8 256 9 2017-03-01 2009-06-02 7.745473
#> 27: 9 391.1 9 2013-05-17 2001-04-29 12.049971
#> 28: 9 756.13 9 2014-05-14 2001-04-29 13.041073
#> 29: 10 711.81 9 2011-06-20 2002-01-17 9.420733
#> 30: 11 361.04 9 2016-10-03 2013-03-27 3.522563
#> 31: 11 775.9 9 2016-11-23 2013-03-27 3.662194
#> 32: 11 960.6 9 2016-10-13 2013-03-27 3.549942
#> 33: 12 480.9 9 2017-12-10 1951-03-13 66.745830
#> 34: 12 916.2 9 2017-12-10 1951-03-13 66.745830
#> 35: 12 V18.51 9 2017-12-10 1951-03-13 66.745830
#> 36: 13 534.61 9 2014-07-09 2010-11-26 3.615044
#> 37: 13 773.5 9 2016-08-27 2010-11-26 5.750567
#> 38: 14 020.5 9 2014-03-01 1980-11-03 33.321550
#> 39: 14 982.0 9 2014-03-01 1980-11-03 33.321550
#> 40: 15 031.0 9 2012-05-06 1995-03-19 17.133533
#> 41: 15 202.15 9 2012-05-06 1995-03-19 17.133533
#> 42: 15 404.1 9 2012-05-06 1995-03-19 17.133533
#> 43: 15 404.10 9 2012-05-06 1995-03-19 17.133533
#> 44: 15 758.31 9 2012-05-06 1995-03-19 17.133533
#> 45: 16 641.81 9 2015-01-13 1947-03-28 67.797530
#> 46: 16 642.00 9 2015-01-13 1947-03-28 67.797530
#> 47: 17 224.2 9 2016-12-28 1991-07-14 25.459982
#> 48: 17 296.36 9 2017-04-16 1991-07-14 25.758408
#> 49: 17 441.4 9 2016-04-13 1991-07-14 24.750879
#> 50: 17 690.8 9 2014-12-02 1991-07-14 23.387429
#> 51: 17 904.6 9 2014-10-06 1991-07-14 23.231372
#> 52: 18 363.20 9 2011-02-11 1976-05-19 34.734167
#> 53: 18 368.12 9 2011-04-08 1976-05-19 34.887487
#> 54: 18 410.5 9 2011-06-15 1976-05-19 35.073661
#> 55: 18 772.12 9 2011-06-14 1976-05-19 35.070923
#> 56: 19 110.1 9 2010-06-29 1938-02-27 72.332488
#> 57: 19 747.41 9 2008-09-28 1938-02-27 70.583001
#> 58: 19 803.44 9 2004-02-26 1938-02-27 65.994363
#> 59: 19 821.1 9 2007-11-10 1938-02-27 69.698675
#> 60: 19 952.14 9 2010-08-08 1938-02-27 72.442002
#> 61: 20 268.9 9 2018-03-07 2006-09-25 11.447654
#> 62: 20 534.2 9 2017-02-15 2006-09-25 10.393582
#> 63: 20 663.40 9 2019-07-01 2006-09-25 12.764560
#> 64: 20 755.11 9 2017-05-10 2006-09-25 10.623561
#> person_id icd flag entry_date dob occurrence_age
icdSample1[, `:=`(entry_date = NULL, dob = NULL)]
#> person_id icd flag occurrence_age
#> 1: 1 365 9 88.796699
#> 2: 1 366 9 89.459259
#> 3: 1 734 9 89.012989
#> 4: 1 759.82 9 88.733728
#> 5: 2 441 9 35.346012
#> 6: 2 524.0 9 36.416511
#> 7: 2 718.4 9 38.395977
#> 8: 2 759.82 9 38.565724
#> 9: 2 759.82 9 39.326847
#> 10: 3 366 9 63.239370
#> 11: 3 734 9 64.704120
#> 12: 4 441 9 33.566328
#> 13: 5 331.9 9 41.684307
#> 14: 5 362.07 9 41.933451
#> 15: 5 369.25 9 41.845840
#> 16: 5 812.10 9 41.733588
#> 17: 6 811.11 9 13.291612
#> 18: 6 958.3 9 4.423713
#> 19: 6 V33.1 9 3.925424
#> 20: 7 062.8 9 36.938331
#> 21: 7 607.83 9 36.938331
#> 22: 7 712.17 9 36.938331
#> 23: 7 785.52 9 36.938331
#> 24: 7 788.30 9 36.938331
#> 25: 8 077 9 7.824870
#> 26: 8 256 9 7.745473
#> 27: 9 391.1 9 12.049971
#> 28: 9 756.13 9 13.041073
#> 29: 10 711.81 9 9.420733
#> 30: 11 361.04 9 3.522563
#> 31: 11 775.9 9 3.662194
#> 32: 11 960.6 9 3.549942
#> 33: 12 480.9 9 66.745830
#> 34: 12 916.2 9 66.745830
#> 35: 12 V18.51 9 66.745830
#> 36: 13 534.61 9 3.615044
#> 37: 13 773.5 9 5.750567
#> 38: 14 020.5 9 33.321550
#> 39: 14 982.0 9 33.321550
#> 40: 15 031.0 9 17.133533
#> 41: 15 202.15 9 17.133533
#> 42: 15 404.1 9 17.133533
#> 43: 15 404.10 9 17.133533
#> 44: 15 758.31 9 17.133533
#> 45: 16 641.81 9 67.797530
#> 46: 16 642.00 9 67.797530
#> 47: 17 224.2 9 25.459982
#> 48: 17 296.36 9 25.758408
#> 49: 17 441.4 9 24.750879
#> 50: 17 690.8 9 23.387429
#> 51: 17 904.6 9 23.231372
#> 52: 18 363.20 9 34.734167
#> 53: 18 368.12 9 34.887487
#> 54: 18 410.5 9 35.073661
#> 55: 18 772.12 9 35.070923
#> 56: 19 110.1 9 72.332488
#> 57: 19 747.41 9 70.583001
#> 58: 19 803.44 9 65.994363
#> 59: 19 821.1 9 69.698675
#> 60: 19 952.14 9 72.442002
#> 61: 20 268.9 9 11.447654
#> 62: 20 534.2 9 10.393582
#> 63: 20 663.40 9 12.764560
#> 64: 20 755.11 9 10.623561
#> person_id icd flag occurrence_age
dxStatus = getDxStatus(demoSample, icdSample1)