Table 1.
Characteristics of the patients in the study
| Train | Validation | Test | ||||
| Total | Positives | Total | Positives | Total | Positives | |
| Cohort | ||||||
| Unique patients | 1 237 507 | 119 728 | 309 380 | 30 224 | 1 375 277 | 80 788 |
| Data points | 16 923 230 | 180 152 | 4 225 605 | 45 571 | 9 862 034 | 104 676 |
| Demographics | ||||||
| Sex (F) | 8 845 443 (52.3%) | 93 333 (51.8%) | 2 213 395 (52.4%) | 23 542 (51.7%) | 5 153 174 (52.3%) | 54 368 (51.9%) |
| Sex (M) | 8 077 787 (47.7%) | 86 819 (48.2%) | 2 012 210 (47.6%) | 22 029 (48.3%) | 4 708 860 (47.7%) | 50 308 (48.1%) |
| Age (mean) | 69.0±2.86 | 69.1±2.88 | 69.0±2.86 | 69.1±2.87 | 69.0±2.81 | 69.1±2.84 |
| Immigrant | 1 619 193 (9.57%) | 16 686 (9.26%) | 405 211 (9.59%) | 4007 (8.79%) | 1 071 959 (10.9%) | 10 878 (10.4%) |
| Non-immigrant | 15 304 037 (90.4%) | 163 466 (90.7%) | 3 820 394 (90.4%) | 41 564 (91.2%) | 8 790 075 (89.1%) | 93 798 (89.6%) |
| Geography | ||||||
| Rural | 2 479 688 (14.7%) | 29 056 (16.1%) | 616 941 (14.6%) | 7069 (15.5%) | 1 340 756 (13.6%) | 15 499 (14.8%)) |
| Income quintile | ||||||
| 1st quintile | 2 982 780 (17.6%) | 33 814 (18.8%) | 736 716 (17.4%) | 8612 (18.9%) | 1 842 945 (18.7%) | 20 940 (20.0%) |
| 2nd quintile | 3 335 222 (19.7%) | 36 536 (20.3%) | 835 276 (19.8%) | 8847 (19.4%) | 2 007 802 (20.4%) | 21 849 (20.9%) |
| 3rd quintile | 3 351 614 (19.8%) | 35 237 (19.6%) | 838 012 (19.8%) | 9043 (19.8%) | 1 997 302 (20.3%) | 21 266 (20.3%) |
| 4th quintile | 3 507 494 (20.7%) | 36 756 (20.4%) | 882 844 (20.9%) | 9421 (20.7%) | 1 913 979 (19.4%) | 19 838 (19.0%) |
| 5th quintile | 3 702 063 (21.9%) | 37 314 (20.7%) | 921 278 (21.8%) | 9521 (20.9%) | 2 084 008 (21.1%) | 20 613 (19.7%) |
| Education quintile | ||||||
| 1st quintile | 3 075 278 (18.2%) | 34 957 (19.4%) | 762 687 (18.0%) | 8779 (19.3%) | 1 706 122 (17.3%) | 19 391 (18.5%) |
| 2nd quintile | 3 385 511 (20.0%) | 37 128 (20.6%) | 841 692 (19.9%) | 9481 (20.8%) | 1 937 907 (19.7%) | 21 469 (20.5%) |
| 3rd quintile | 3 493 804 (20.6%) | 36 945 (20.5%) | 870 402 (20.6%) | 9190 (20.2%) | 2 030 870 (20.6%) | 21 454 (20.5%) |
| 4th quintile | 3 500 217 (20.7%) | 36 902 (20.5%) | 877 965 (20.8%) | 9299 (20.4%) | 2 084 940 (21.1%) | 21 550 (20.6%) |
| 5th quintile | 3 357 516 (19.8%) | 33 022 (18.3%) | 844 839 (20.0%) | 8485 (18.6%) | 2 034 100 (20.6%) | 20 045 (19.1%) |
| Comorbidities | ||||||
| Acute Myocardial Infarction | 709 309 (4.19%) | 9667 (5.37%) | 177 912 (4.21%) | 2507 (5.50%) | 416 924 (4.23%) | 5696 (5.44%) |
| Arrythmia | 1 530 096 (9.04%) | 18 798 (10.4%) | 382 872 (9.06%) | 4891 (10.7%) | 914 621 (9.27%) | 10 990 (10.5%) |
| Arthritis | 354 214 (2.09%) | 4455 (2.47%) | 89 539 (2.12%) | 1113 (2.44%) | 225 636 (2.29%) | 2719 (2.60%) |
| Asthma | 2 034 989 (12.0%) | 26 649 (14.8%) | 508 111 (12.0%) | 7.093 (15.6%) | 1 246 159 (12.6%) | 16 445 (15.7%) |
| Cancer | 2 198 985 (13.0%) | 25 044 (13.9%) | 546 554 (12.9%) | 6210 (13.6%) | 1 317 439 (13.4%) | 14 662 (14.0%) |
| Chronic heart failure | 838 537 (4.95%) | 14 327 (7.95%) | 210 965 (4.99%) | 3672 (8.06%) | 483 842 (4.91%) | 7974 (7.62%) |
| Colitis | 133 502 (0.79%) | 1575 (0.87%) | 32 232 (0.76%) | 389 (0.85%) | 88 715 (0.90%) | 1018 (0.97%) |
| Chronic Obstructive Pulmonary Disease | 2 910 066 (17.2%) | 40 751 (22.6%) | 726 976 (17.2%) | 10 396 (22.8%) | 1 726 397 (17.5%) | 23 837 (22.8%) |
| Coronary heart disease | 3 510 361 (20.7%) | 43 579 (24.2%) | 879 995 (20.8%) | 11 068 (24.3%) | 1 899 361 (19.3%) | 23 359 (22.3%) |
| Dementia | 344 161 (2.03%) | 4454 (2.47%) | 86 853 (2.06%) | 1158 (2.54%) | 206 300 (2.09%) | 2722 (2.60%) |
| Diabetes | 4 394 754 (26.0%) | 52 155 (29.0%) | 1 095 489 (25.9%) | 13 022 (28.6%) | 2 660 592 (27.0%) | 30 929 (29.5%) |
| Hypertension | 10 494 913 (62.0%) | 116 393 (64.6%) | 2 622 675 (62.1%) | 29 352 (64.4%) | 6 033 618 (61.2%) | 67 044 (64.0%) |
| Mental disorder* | 3 410 850 (20.2%) | 40 032 (22.2%) | 851 249 (20.1%) | 10 117 (22.2%) | 2 244 412 (22.8%) | 26 407 (25.2%) |
| Mood disorder | 7 786 874 (46.0%) | 85 908 (47.7%) | 1 943 700 (46.0%) | 21 771 (47.8%) | 4 801 635 (48.7%) | 52 944 (50.6%) |
| Osteoarthritis | 10 244 732 (60.5%) | 111 020 (61.6%) | 2 553 893 (60.4%) | 28 336 (62.2%) | 6 131 185 (62.2%) | 66 621 (63.6%) |
| Osteoporosis | 1 791 824 (10.6%) | 18 620 (10.3%) | 450 339 (10.7%) | 4656 (10.2%) | 1 032 043 (10.5%) | 10 525 (10.1%) |
| Renal failure | 727 558 (4.30%) | 10 545 (5.85%) | 180 987 (4.28%) | 2698 (5.92%) | 489 046 (4.96%) | 7004 (6.69%) |
| Stroke | 965 743 (5.71%) | 12 601 (6.99%) | 239 406 (5.67%) | 3122 (6.85%) | 547 368 (5.55%) | 7026 (6.71%) |
| Total (median) | 3 (2, 7) | 3 (2, 5) | 3 (2, 4) | 3 (2, 5) | 3 (2, 5) | 3 (2, 5) |
*History of mental health-related visit, excluding dementia, deliberate self-harm codes and mood disorder codes.
COPD, chronic obstructive pulmonary disease.