BTW, for those interested, here is what Opus 4.8 thinks about that. #2 is an interesting point.
The four factors that explain why your HbA1c didn’t move
1. You’re not the trial population
Your baseline HbA1c is 5.9% (pre-diabetes), not 7–10% (T2D). The TIMES trials excluded patients like you. The most directly relevant study is the recent Diabetes Obes Metab 2026 dual-action mechanism paper (PMC12992193), where patients with baseline HbA1c 6.9% showed only 6.9% → 6.7% = −0.2% at 20 weeks. That’s a near-perfect baseline-comparator for you. Imeglimin’s effect size scales with baseline hyperglycemia — when you start lower, you move less. The Satheesan mitochondrial function study (PMC12353691) explicitly attributes lower monotherapy efficacy to “lower baseline HbA1c levels.”
Predicted effect for your starting point: an HbA1c drop on the order of 0.1–0.3%, not 0.5–0.9%. A drop from 5.9% to 5.7% would be the expected effect. Going from 5.9 → 5.9 is plausibly within the measurement noise of HbA1c at this magnitude (analytical CV ~2-3%, biological CV ~1.5%, so a single 5.9 could really be anywhere from ~5.7 to 6.1).
2. Imeglimin actually distorts HbA1c upward
This is the finding I missed in the first reply. The INFINITY trial (Iitaka et al., Front Endocrinol 2026, PMC12591969) found that imeglimin prolongs erythrocyte lifespan, which causes HbA1c to understate the true glycemic improvement. Per the paper: “imeglimin may prolong erythrocyte lifespan, resulting in disproportionately elevated HbA1c levels relative to true glycemic status. Reliance on HbA1c alone may underestimate imeglimin’s early glycemic effects, highlighting the value of alternative markers such as GA and 1,5-AG.”
In INFINITY (n=18, baseline HbA1c 6.5-8.5%, 6 months imeglimin 1000 mg BID): HbA1c declined gradually while glycated albumin (GA) and 1,5-anhydroglucitol (1,5-AG) moved much faster. Erythrocyte lifespan was significantly prolonged in both the 1–3 month and 4–6 month periods. The mechanism is plausible: imeglimin reduces oxidative stress in RBCs (via NAD⁺ salvage / improved mitochondrial respiration), so RBCs survive longer and accumulate more glycation over their extended lifespan.
What this means for you: your HbA1c of 5.9 → 5.9 may actually be masking a real glucose improvement that imeglimin is producing. The only way to see this is glycated albumin (GA) or fructosamine — both with ~2–3 week half-lives that bypass the RBC-lifespan confound.
You had a Jan 2026 fructosamine of 239 µmol/L (in the published reference range for healthy 20-60 yr olds of 205-285). If you repeat fructosamine now, a value of 200–210 would be a real improvement, even though HbA1c didn’t budge. This is the single most important test to add to your next blood draw.
3. Rapamycin is pulling in the opposite direction
Your own genetic report flags this explicitly: rapamycin 12 mg q3wk contributes to HbA1c drift. The PEARL 2025 trial (Moel et al., Aging, NCT04488601, n=115) showed modest HbA1c signal in one rapamycin subgroup. Combined with your β-cell-secretion-impaired genetic background (CDKAL1 hom + KCNJ11/ABCC8 hom + INS-locus hom + TCF7L2 het), there’s a real headwind. The fact that imeglimin held HbA1c flat at 5.9% rather than allowing continued drift could itself be evidence imeglimin is working — it stopped the climb.
4. Tirzepatide + empagliflozin had already lowered the “easy” gains
In the TIMES 2 study, imeglimin monotherapy at 52 weeks gave −0.46% HbA1c, while combination with DPP4i gave −0.92%. Combination with GLP1-RA gave only −0.12% — the smallest incremental effect of any combination. The interpretation: when an incretin agonist is already aggressively engaging the β-cell, the marginal benefit of adding imeglimin’s secretagogue effect is reduced. You’re already on tirzepatide 2.6 mg twice weekly, which is a very effective incretin amplifier — leaving less room for imeglimin to add on the secretagogue side. The hepatic gluconeogenesis-reduction component remains, but that’s the smaller part of imeglimin’s effect.
Putting it together: was 16 weeks of imeglimin a “failure”?
I don’t think so, and here’s how I’d reframe it:
Predicted effect of imeglimin in your specific clinical context (baseline HbA1c 5.9%, on tirzepatide + empagliflozin + rapamycin, with imeglimin’s RBC-lifespan confound):
-
True glycemic improvement (by GA / 1,5-AG / fructosamine): probably real but small, in the −0.1 to −0.2% HbA1c-equivalent range
-
Observed HbA1c improvement: probably near zero or even slightly underestimated, because of the erythrocyte-lifespan extension
-
Hepatic gluconeogenesis suppression: harder to see in fasting glucose alone but could be visible on CGM
Citations (new sources from this update)
- Dubourg J et al. Efficacy and Safety of Imeglimin Monotherapy Versus Placebo (TIMES 1). Diabetes Care 2021;44:952–959. PMID 33574125 (open access).
- Dubourg J et al. Long-term safety and efficacy of imeglimin (TIMES 2). Diabetes Obes Metab 2022 (open access).
- Reilhac C et al. TIMES 3: imeglimin add-on to insulin. Diabetes Obes Metab 2022. PMID 34984815 (open access).
- Dubourg J et al. Dose-ranging Phase 2b imeglimin trial in Japanese T2D. Diabetes Obes Metab 2021. PMID 33275318 (abstract-only).
-
Iitaka H et al. Imeglimin may affect hemoglobin A1c accuracy via prolongation of erythrocyte lifespan: insights from the INFINITY clinical trial. Front Endocrinol 2026;16:1699591. PMC12591969 (open access). ← Critical to the interpretation.
- Furuyoshi S et al. Dual action of imeglimin on insulin secretion and sensitivity in type 2 diabetes. Diabetes Obes Metab 2026 Apr. PMC12992193 (open access).
- Satheesan A et al. Effect of imeglimin on mitochondrial function in T2DM: prospective cohort. Front Endocrinol 2025. PMC12353691 (open access).
- Real-world Japan retrospective cohort. PMC12747980 (open access).
- INDI-TIMES real-world India n=8,301. PMC11925818 (open access).
- Moel M et al. PEARL trial: rapamycin in healthy adults. Aging 2025. NCT04488601 (open access).
