Table 2.
Incidence rate, rate ratio, and cumulative incidence of the outcome in each time zero setting method
| Time-zero setting method | Group | Number of patients | Number of events | Person-years | Incidence rate per 1000 person-year (95% CI) | Rate ratio (95% CI) | Cumulative incidence at 1 year follow-up (95% CI) |
|---|---|---|---|---|---|---|---|
| SED vs SED (naïve approach) | Non-use | 24,767 | 4040 | 42,590 | 94.9 (91.9–97.8) | – | 0.124 (0.119–0.128) |
| Treatment | 10,929 | 1641 | 28,367 | 57.8 (55.0–60.6) | 0.61 (0.58–0.65) | 0.070 (0.065–0.075) | |
| SED vs SED (cloning method)a | Non-use | – | – | – | – | – | 0.100 (0.096–0.103) |
| Treatment | – | – | – | – | – | 0.101 (0.097–0.104) | |
| TI vs SED | Non-use | 23,935 | 3208 | 41,952 | 76.5 (73.8–79.1) | – | 0.098 (0.094–0.103) |
| Treatment | 10,929 | 1641 | 23,746 | 69.1 (65.8–72.5) | 0.90 (0.85–0.96) | 0.087 (0.081–0.092) | |
| TI vs Random | Non-use | 21,860 | 1133 | 21,960 | 51.6 (48.6–54.6) | – | 0.054 (0.050–0.058) |
| Treatment | 10,929 | 1641 | 23,746 | 69.1 (65.8–72.5) | 1.34 (1.24–1.44) | 0.087 (0.081–0.092) | |
| TI vs Matched (random order) | Non-use | 10,929 | 1620 | 16,076 | 100.8 (95.9–105.7) | – | 0.122 (0.115–0.129) |
| Treatment | 10,929 | 1641 | 23,746 | 69.1 (65.8–72.5) | 0.69 (0.64–0.73) | 0.087 (0.081–0.092) | |
| TI vs Matched (systematic order) | Non-use | 10,929 | 1441 | 19,961 | 72.2 (68.5–75.9) | – | 0.090 (0.084–0.096) |
| Treatment | 10,929 | 1641 | 23,746 | 69.1 (65.8–72.5) | 0.96 (0.89–1.03) | 0.087 (0.081–0.092) |
SED versus SED (naïve approach): time zero set at SED for both groups (naïve approach)
SED versus SED (cloning method): time zero set at SED for both groups (cloning method)
TI versus SED: time zero set at treatment initiation for the treatment group and SED for the non-use group
TI versus Random: time zero set at treatment initiation for the treatment group and at a randomly sampled hospital visit date for the non-use group
TI versus Matched (random order): time zero set at treatment initiation for the treatment group and at the matched date for the non-use group (matching in random order)
Treatment initiation versus Matched (systematic order): time zero set at treatment initiation for the treatment group and at the matched date for the non-use group (matching in systematic order)
CI confidence interval, HR hazard ratio, SED study entry date (the date of the first prescription of a glucose-lowering agent plus the diagnostic record of type 2 diabetes in the same month), TI treatment initiation (first prescription date of lipid-lowering agents)
aThe calculation of incidence rate and crude incidence rate ratio was not applicable in SED versus SED (cloning method), due to the use of an artificial population. Thus, only the cumulative incidence at 1 year follow-up was estimated