Network meta-analysis
SF-36 physical component summary change
Overweight or obesity without diabetes (adults)
weeks 20 to 130 (target week 52)Hypothetical (as if everyone stayed on treatment)Each dose separatelyMean difference
2
Randomized trials
5
Treatments
2,979
Participants
6
Trial arms
In plain language
Across 2 trials with 2,979 participants, 0 of 4 treatments had a clearly better result than placebo on SF-36 physical component summary change, and for 4 the evidence could not tell them apart from placebo. The most favorable estimate was for Tirzepatide subcutaneous once weekly, maximum tolerated dose: 10 or 15 mg: mean difference 3.93 points (95% credible interval -4.38 to 12.06).
Higher values favor the treatment. "Clearly" means the 95% credible interval excludes no difference. These are averages across trials; they do not say how any one person will respond. Not medical advice.
Network of trials
Each circle is a treatment; each line joins treatments that were randomized against each other in at least one trial.
Effects compared with Placebo
Mean difference in points. Higher values favor the treatment.
| Treatment | Bayesian MD (95% CrI) | 95% prediction interval | Frequentist MD (95% CI) | Verdict |
|---|---|---|---|---|
| Tirzepatide subcutaneous once weekly, maximum tolerated dose: 10 or 15 mg TIRZ_SC_MTD_QW | 3.93 (-4.38 to 12.06) | -8.30 to 15.57 | 4.00 (2.89 to 5.11) | Unclear |
| Tirzepatide 15 mg subcutaneous once weekly TIRZ_SC_15MG_QW | 2.51 (-5.40 to 10.36) | -9.15 to 14.02 | 2.56 (1.89 to 3.23) | Unclear |
| Tirzepatide 10 mg subcutaneous once weekly TIRZ_SC_10MG_QW | 1.95 (-6.22 to 9.84) | -9.90 to 13.06 | 2.01 (1.34 to 2.68) | Unclear |
| Tirzepatide 5 mg subcutaneous once weekly TIRZ_SC_5MG_QW | 1.79 (-6.09 to 9.60) | -10.17 to 13.42 | 1.85 (1.18 to 2.52) | Unclear |
Ranking
How likely each treatment is to be among the best. Rankings ignore the size of differences and their certainty, so read them with the effects above.
League table
Every treatment against every other: mean difference of the row treatment versus the column treatment, posterior median and 95% credible interval. Green: row clearly better; red: row clearly worse.
| Row versus column | PLACEBO | TIRZ_SC_MTD_QW | TIRZ_SC_15MG_QW | TIRZ_SC_10MG_QW | TIRZ_SC_5MG_QW |
|---|---|---|---|---|---|
| PLACEBO | PLACEBO | -3.93 -12.06 to 4.38 | -2.51 -10.36 to 5.40 | -1.95 -9.84 to 6.22 | -1.79 -9.60 to 6.09 |
| TIRZ_SC_MTD_QW | 3.93 -4.38 to 12.06 | TIRZ_SC_MTD_QW | 1.44 -9.72 to 12.18 | 1.96 -9.23 to 13.50 | 2.17 -9.58 to 13.19 |
| TIRZ_SC_15MG_QW | 2.51 -5.40 to 10.36 | -1.44 -12.18 to 9.72 | TIRZ_SC_15MG_QW | 0.56 -7.52 to 8.76 | 0.70 -7.38 to 8.92 |
| TIRZ_SC_10MG_QW | 1.95 -6.22 to 9.84 | -1.96 -13.50 to 9.23 | -0.56 -8.76 to 7.52 | TIRZ_SC_10MG_QW | 0.19 -8.39 to 8.23 |
| TIRZ_SC_5MG_QW | 1.79 -6.09 to 9.60 | -2.17 -13.19 to 9.58 | -0.70 -8.92 to 7.38 | -0.19 -8.23 to 8.39 | TIRZ_SC_5MG_QW |
Heterogeneity, fit and convergence
Bayesian random effects (primary)
Frequentist check (netmeta)
Inconsistency
Do trials comparing two treatments directly agree with the indirect evidence through other treatments?
No comparison here has both direct and indirect evidence, so inconsistency cannot be checked by node splitting; the between designs Q above is the global check.
Small study effects
A comparison adjusted funnel plot: each point is one trial comparison, centered on its own network estimate. Asymmetry can signal that small trials with unfavorable results are missing.
Fewer than ten trial comparisons, too few to judge funnel plot asymmetry.
Comparability of the trials
Checked across designs (the set of treatments each trial compares) for eligibility, outcome definition and assessment, and the baseline factors above. Flags point to possible intransitivity; notes describe variation that is not tied to design.
- FlagOutcome assessment, definition: confounded with design: not stated 1, SF-36v2 physical component summary score at week 72 1
- NoteData handling, input conversions: n_randomized 4
| Trial | time weeks | analysis set | definition | instrument | adjudicated | proportion method | intercurrent events (discontinuation) | intercurrent events (rescue) | blinding | funding | start year | Eligibility |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SURMOUNT-1 | 72 | modified_itt | not stated | SF-36v2 | not stated | not stated | hypothetical | not stated | double_blind | industry | 2019 | age 18 or older; BMI 30 or more, or 27 or more with a weight related complication; no diabetes |
| SURMOUNT-3 | 72 | modified_itt | SF-36v2 physical component summary score at week 72 | SF-36v2 | not stated | not stated | hypothetical | not stated | double_blind | industry | 2021 | age 18 or older; BMI 30 or more, or 27 or more with comorbidity; no diabetes; at least 5 percent loss in lead in |
Trial data
What each trial contributes. Arm rows give the arm value with its standard error, or events over participants; contrast rows give the mean difference on the analysis scale against the trial's first row. Flags mark converted, combined or approximated inputs.
| Trial | Arm | Treatment | Week | Data | Value | SE | Events / N | Flags | Source |
|---|---|---|---|---|---|---|---|---|---|
| SURMOUNT-1 | A1 | PLACEBO | 72 | arm, change | 1.620 | 0.250 | 643 | n_randomized | R0006704:Table 2 |
| SURMOUNT-1 | A2 | TIRZ_SC_5MG_QW | 72 | arm, change | 3.470 | 0.230 | 630 | n_randomized | R0006704:Table 2 |
| SURMOUNT-1 | A3 | TIRZ_SC_10MG_QW | 72 | arm, change | 3.630 | 0.230 | 636 | n_randomized | R0006704:Table 2 |
| SURMOUNT-1 | A4 | TIRZ_SC_15MG_QW | 72 | arm, change | 4.180 | 0.230 | 630 | n_randomized | R0006704:Table 2 |
| SURMOUNT-3 | A1 | TIRZ_SC_MTD_QW | 72 | arm, final | 55.800 | 0.400 | 231 | R0016199:Table 1 | |
| SURMOUNT-3 | A2 | PLACEBO | 72 | arm, final | 51.800 | 0.400 | 209 | R0016199:Table 1 |
Rerun this analysis yourself
Remove treatments or trials and refit the frequentist and Bayesian models in your browser, with the same methods as the published analysis.