AI-quantified coronary inflammation explains why two major cardio trials failed, Topol says
EricTopol · x · 2026-11-08
At #AHA26, NEJM published two large secondary-prevention trials—an IL-6 antibody and an Lp(a) antisense oligonucleotide—neither showing benefit overall or in any subgroup. Eric Topol explains why:
- Blood markers don't correlate with coronary inflammation, which can now be quantified with AI; drugs should demonstrate they markedly reduce coronary inflammation before hundreds of millions are spent on large trials.
- Genetic, basic-science and observational evidence supports these interventions, but that doesn't translate to initiating them in the 7th decade of life with multiple co-morbidities for secondary prevention.
- More potent, durable Lp(a) blockers are in large trials, one in high-risk primary prevention—a cohort far more likely to benefit—but results won't read out until 2031.
- Coronary inflammation as a driver of events, and anti-inflammatory drug interventions to improve outcomes, remain a key research direction.
More from Research
- Near-identical neural net weights still diverge on ~3% of inputs after training — bravo_abad · 2026-11-08
- Removing negative-advantage samples drops robot zip-tie success from 86% to 60% — micoolcho · 2026-11-08
- DECIDE benchmark tests voice-agent decisions on 4,867 questions from 1,081 real calls, scoring 20 models — Aiden_Tech_Ai · 2026-11-08
- KV Cache Quantization Tested Across 35 Quants: 8-bit Is Essentially Free for Qwen3.8 27B — Hefty_Wolverine_553 · 2026-11-08
- YC amplifies demo of models handling semi-serious X-band phased-array design — ycombinator · 2026-11-08
- Analysis of 250k ICLR reviews finds 65% AI-written, scores collapsing to middle — TuhinChakr · 2026-11-08