Skip to main content
. Author manuscript; available in PMC: 2020 Apr 1.
Published in final edited form as: Am J Epidemiol. 2019 Apr 1;188(4):709–723. doi: 10.1093/aje/kwy265

Table 4.

Empirical Example 1: Results from Disease Risk Scorea-Adjusted Analyses using Different Combinations of Confounding Adjustment Method and Data-Sharing Approach, AGB vs RYGBb

Confounding adjustment method & data-sharing approach Effectiveness outcome, change in body mass indexc Safety outcomed
<5% ≥5% ≥10% ≥20% ≥30% Re-hospitalization Re-intervention
OR 95% CI OR 95% CI OR 95% CI OR 95% CI OR 95% CI OR 95% CI OR 95% CI
Stratification
 Pooled individual-level 3.95 3.26, 4.79 0.15 0.10, 0.23 0.12 0.09, 0.15 0.08 0.07, 0.10 0.07 0.05, 0.10 0.86 0.63, 1.15 0.81 0.58, 1.09
 Risk-set 3.95 3.26, 4.79 0.15 0.10, 0.23 0.12 0.09, 0.15 0.08 0.07, 0.10 0.07 0.05, 0.10 0.86 0.63, 1.15 0.81 0.58, 1.09
 Summary-table 3.95 3.26, 4.79 0.15 0.10, 0.23 0.12 0.09, 0.15 0.08 0.07, 0.10 0.07 0.05, 0.10 0.86 0.63, 1.15 0.81 0.58, 1.09
 Effect-estimate, fixed-effect 3.93 3.25, 4.76 0.14 0.09, 0.21 0.11 0.09, 0.14 0.08 0.07, 0.10 0.09 0.06, 0.12 0.95 0.70, 1.28 0.83 0.62, 1.12
 Effect-estimate, random-effects 3.73 1.52, 9.12 0.16 0.08, 0.34 0.11 0.04, 0.28 0.07 0.03, 0.12 0.04 0.01, 0.16 0.85 0.30, 2.36 0.75 0.46, 1.21
 Measure of heterogeneity, Qe 25.49 <.0001 2.46 0.2922 11.25 0.0036 10.50 0.0052 8.27 0.0159 12.04 0.0024 3.29 0.1930
Matching
 Pooled individual-level 3.99 3.10, 5.15 0.08 0.02, 0.24 0.11 0.06, 0.18 0.08 0.06, 0.10 0.08 0.06, 0.12 0.86 0.57, 1.30 0.93 0.61, 1.42
 Risk-set 3.99 3.10, 5.15 0.08 0.02, 0.24 0.11 0.06, 0.18 0.08 0.06, 0.10 0.08 0.06, 0.12 0.86 0.57, 1.30 0.93 0.61, 1.42
 Summary-table 3.99 3.10, 5.15 0.08 0.02, 0.24 0.11 0.06, 0.18 0.08 0.06, 0.10 0.08 0.06, 0.12 0.86 0.57, 1.30 0.93 0.61, 1.42
 Effect-estimate, fixed-effect 3.93 3.06, 5.05 0.08 0.02, 0.26 0.11 0.06, 0.18 0.08 0.06, 0.10 0.09 0.06, 0.13 0.89 0.61, 1.27 0.95 0.63, 1.44
 Effect-estimate, random-effects 3.42 1.06, 10.98 0.08 0.02, 0.26 0.11 0.06, 0.18 0.06 0.04, 0.11 0.05 0.01, 0.16 0.79 0.38, 1.67 0.79 0.34, 1.83
 Measure of heterogeneity, Qe 20.91 <.0001 0.00 0.9985 0.21 0.8981 3.32 0.1898 7.47 0.0239 4.11 0.1275 5.51 0.0633
HR 95% CI HR 95% CI HR 95% CI HR 95% CI HR 95% CI HR 95% CI HR 95% CI
Stratification
 Pooled individual-level 2.23 2.01, 2.48 0.51 0.47, 0.56 0.34 0.31, 0.38 0.17 0.14, 0.19 0.09 0.07, 0.13 0.83 0.63, 1.08 0.79 0.59, 1.05
 Risk-set 2.23 2.00, 2.47 0.51 0.47, 0.56 0.34 0.31, 0.38 0.17 0.14, 0.19 0.09 0.07, 0.13 0.82 0.63, 1.08 0.79 0.59, 1.05
 Summary-table 3.35 2.98, 3.79 0.41 0.38, 0.46 0.36 0.33, 0.39 0.22 0.19, 0.25 0.12 0.08, 0.17 0.81 0.61, 1.07 0.78 0.56, 1.03
 Effect-estimate, fixed-effect 2.31 2.08, 2.57 0.52 0.47, 0.57 0.34 0.31, 0.38 0.17 0.15, 0.20 0.11 0.08, 0.14 0.94 0.72, 1.23 0.81 0.61, 1.08
 Effect-estimate, random-effects 2.28 1.17, 4.42 0.54 0.38, 0.75 0.34 0.26, 0.45 0.14 0.09, 0.22 0.06 0.02, 0.18 0.81 0.34, 1.96 0.75 0.49, 1.14
 Measure of heterogeneity, Qe 28.81 <.0001 14.65 0.0007 8.62 0.0134 7.96 0.0186 7.06 0.0292 12.00 0.0025 2.99 0.2232
Matching
 Pooled individual-level 2.41 2.03, 2.85 0.49 0.43, 0.55 0.34 0.30, 0.39 0.16 0.14, 0.19 0.10 0.07, 0.13 0.85 0.59, 1.22 0.90 0.61, 1.32
 Risk-set 2.41 2.03, 2.85 0.49 0.43, 0.56 0.34 0.30, 0.39 0.16 0.14, 0.19 0.10 0.07, 0.13 0.85 0.59, 1.22 0.90 0.61, 1.32
 Summary-table 3.75 3.16, 4.46 0.39 0.35, 0.44 0.37 0.32, 0.42 0.22 0.18, 0.26 0.12 0.08, 0.17 0.85 0.58, 1.24 0.89 0.59, 1.32
 Effect-estimate, fixed-effect 2.36 1.99, 2.80 0.49 0.43, 0.55 0.34 0.30, 0.39 0.16 0.14, 0.20 0.11 0.08, 0.15 0.88 0.61, 1.27 0.92 0.62, 1.36
 Effect-estimate, random-effects 2.22 0.88, 5.59 0.52 0.36, 0.74 0.35 0.24, 0.50 0.13 0.08, 0.21 0.05 0.01, 0.20 0.79 0.40, 1.55 0.79 0.37, 1.67
 Measure of heterogeneity, Qe 21.66 <.0001 9.16 0.0102 7.95 0.0187 6.67 0.0356 6.90 0.0317 4.17 0.1242 5.07 0.0792

Note: AGB= Adjusted gastric banding; RYGB= Roux-en-Y gastric bypass; OR= odds ratio; CI= confidence interval; HR= hazard ratio

a

The disease risk score was estimated using Cox proportional hazards regression on patients receiving Roux-en-Y gastric bypass procedure.

b

There were 584 (6.2%) patients who underwent AGB and 8,777 (93.8%) patients who underwent RYGB.

c

The incidences for <5%, ≥5%, ≥10%, ≥20%, and ≥30% change in body mass index were 68.0%, 93.7%, 76.5%, 31.2%, and 6.8%, respectively, for the AGB users; 32.9%, 99.1%, 96.8%, 83.8%, and 47.7%, respectively, for the RYGB users. These effectiveness outcomes were defined as the occurrence of the outcomes of interest closet to the end of the first post-procedure year so the incidences for <5% change in body mass index and ≥5% change in body mass index do not sum up to 100%.

d

The incidences for re-hospitalization and re-intervention were 9.9% and 9.3%, respectively, for the AGB users, and 11.7% and 11.6%, respectively, for the RYGB users.

e

Q is a measure of heterogeneity among the three data-contributing sites. The summary statistic and p-value from Cochran’s Q test are shown here.