# Two Studies, One Comparison, Two Answers

By Nora Bissett, Pricing Editor (https://glpwatchdog.org/authors/nora-bissett) | Published: 2026-08-19 | Updated: 2026-10-30

Canonical page: https://glpwatchdog.org/research/two-studies-one-comparison-two-answers

> One real-world study found no cardiovascular difference between the two drugs. Another found semaglutide 29% better. Working out why they disagree is more useful than either answer.

## Key points

- HR 1.06 in one study, 0.71 in the other, for the same two drugs and the same kind of outcome.
- The second study's effect grew to 0.43 once people who stopped were excluded. That is a warning, not a confirmation.
- The stronger study first reproduced the known randomized results before extending, a rare calibration step.
- Different populations: type 2 diabetes versus overweight or obesity with heart disease and no diabetes.

Two real-world studies published in 2026 compared semaglutide against tirzepatide on cardiovascular outcomes. One found **no meaningful difference**. The other found semaglutide reduced major cardiovascular events by **29%**.[1][2] Both used large databases and careful matching. Working out why they disagree is more useful than either answer.

## The two results

*Two real-world comparisons of the same two drugs on cardiovascular endpoints.*

| Study | Population | Result |
| --- | --- | --- |
| Trial-emulation study | Type 2 diabetes | Tirzepatide vs semaglutide, HR 1.06 (95% CI 0.95–1.18) — comparable |
| Claims-database study | Overweight or obesity with cardiovascular disease, **without** diabetes | Semaglutide vs tirzepatide, HR 0.71 (p=0.046) and 0.78 (p=0.040) |

## Reason one: they studied different people

This is the most straightforward explanation and possibly sufficient on its own. One study looked at people with type 2 diabetes. The other looked at people with overweight or obesity and established atherosclerotic cardiovascular disease but *no* diabetes.

Those groups have different baseline risks, different reasons for being prescribed either drug, and different competing causes of cardiovascular events. There is no rule that two drugs must rank identically in both.

## Reason two: one result is marginal

The p-values in the claims study are 0.046 and 0.040. Those clear the conventional threshold by a hair. A finding at p=0.046 is one that would frequently not replicate, and it should be read as “possibly something” rather than as a demonstration.

## Reason three, and the one to learn from

The claims study also ran a per-protocol analysis, censoring patients when they had a gap in therapy of more than 30 days. In that analysis the hazard ratio moved from 0.71 to **0.43**, and from 0.78 to 0.57. The paper reports that far more dramatic effect as support for its main result.

> An effect that grows sharply once you exclude the people who stopped is a warning sign, not a confirmation.

Excluding people who discontinue removes a specific kind of patient: the ones who could not tolerate the drug, could not afford it, got sicker, or were hospitalized. The people who leave systematically have worse trajectories than the people who stay. Removing them makes any drug look better, and it makes the drug with better persistence look better still.

Persistence can differ sharply between GLP-1 drugs and formulations. [A UK cohort measured it](https://glpwatchdog.org/research/most-people-never-reach-the-dose) and found discontinuation ran from 36.9% to 55.8% depending on the drug, though tirzepatide was not among them. A comparison that censors on discontinuation is partly measuring that.

## Which to believe

The trial-emulation study has the stronger methodology. Before extending to a broader population, it first *reproduced* the reference randomized trials, checking that its methods recovered the known answers on every individual endpoint except all-cause mortality in one trial. Only then did it apply those methods to new questions.[1]

That is calibration, and it is rare. Most observational studies ask you to trust their design; this one demonstrated it against a known answer first. Its conclusion, comparable cardiovascular benefit between the two drugs in clinical practice, is the one we would weight more heavily.

> **None of this makes the second study worthless.** It asked a different question in a different population, and the possibility that the drugs differ in people without diabetes is still open. What it does not support is choosing between the two drugs on cardiovascular grounds today. Pooling studies like these does not settle it either: [a meta-analysis of 323,439 patients](https://glpwatchdog.org/research/when-pooling-studies-hides-the-answer) found no significant cardiovascular difference between tirzepatide and the GLP-1 drugs it competes with, and the studies it combined disagreed with each other almost completely.For weight, the comparison runs the other way, as [real-world weight data](https://glpwatchdog.org/research/who-responds-in-the-real-world) shows.

## Frequently asked questions

### Is semaglutide better than tirzepatide for the heart?

The evidence disagrees with itself. A trial-emulation study in type 2 diabetes found no meaningful difference, at a hazard ratio of 1.06. A claims study in people with overweight or obesity and cardiovascular disease but no diabetes found semaglutide 29% better, at marginal significance.

### Why would two large studies disagree?

Three reasons here: they studied different populations, one result sits barely over the significance threshold at p=0.046, and that study's result grew much larger in a per-protocol analysis that excludes people who stopped taking the drug.

### What is wrong with excluding people who stopped?

They are not random. People who discontinue are disproportionately those who could not tolerate the drug, could not afford it, or got sicker. Removing them flatters any drug, and flatters the drug with better persistence most.

### Which study should I trust?

The trial-emulation one has the better methodology, because it first reproduced the known results of the reference randomized trials before extending to new questions. That calibration step is rare and it is what makes its conclusion of comparable cardiovascular benefit more credible.

### Should this affect which drug I take?

Not on cardiovascular grounds. The better-designed evidence says the two are comparable there. Weight loss is a different question, where real-world data favors tirzepatide, and tolerability differs between them as well.

## References

1. Krüger N, Schneeweiss S, Desai RJ, et al. Cardiovascular outcomes of semaglutide and tirzepatide for patients with type 2 diabetes in clinical practice. Nature Medicine. 2026. PMID: 41207920. https://pubmed.ncbi.nlm.nih.gov/41207920/
2. Wilson L, Zhao Z, Divino V, et al. Semaglutide and tirzepatide effects on cardiovascular outcomes in people with overweight or obesity in the real world. Diabetes, Obesity and Metabolism. 2026. PMID: 41491349. https://pubmed.ncbi.nlm.nih.gov/41491349/

---

Cite as: GLP Watchdog, Nora Bissett, "Two Studies, One Comparison, Two Answers", published 2026-08-19, updated 2026-10-30. https://glpwatchdog.org/research/two-studies-one-comparison-two-answers

Canonical HTML page: https://glpwatchdog.org/research/two-studies-one-comparison-two-answers

Medical disclaimer: Nothing here is medical advice. We report on this subject; we do not treat anyone. Whether to begin a medication, supplement, or treatment, whether to adjust it, and whether to stop are questions for a clinician licensed to answer them, who knows your history.
