YHacker Newsscreenshots

Screenshot of biograph.com: AI analysis of CT scans finds 42.9% of patients have coronary inflammation

First screen, captured 3 days ago.

AI analysis of CT scans finds 42.9% of patients have coronary inflammation

More from biograph.com →

Biograph press release announcing a U.S. study using Caristo's AI CaRi-Heart tool that found elevated coronary inflammation in 42.9% of asymptomatic low-risk adults.

What HN thinks

A $17,500 AI scan discovers that BMI exists, and the comments section prescribes itself statins.

Weak science, strong marketing
Commenters note the score only correlates robustly with BMI and not with calcium or blood biomarkers, making it look like a fancy BMI estimator wrapped in a subscription-health press release.
Cheaper tests already exist
Some argue hs-CRP, Lp-PLA2 and calcium scores already capture inflammation and risk cheaply, and the lack of correlation undermines the scan's validity.
Calcium scores miss soft plaque
A heart attack survivor points out CAC scores miss non-calcified vulnerable plaque that CCTA can detect, though others counter that screening guidelines target different populations.

Consensus: Most commenters are skeptical that this study shows anything useful beyond existing risk tools, with many viewing it as marketing for a pricey health service.

Recommended in the comments

hs-CRP test (other): A cheap, standardized way to get at inflammation-related cardiovascular risk.
Coronary CT angiography (other): The only non-invasive way to see soft, vulnerable plaque that calcium scores miss.
Rosuvastatin (product): Commenters started it in their 40s and reported no side effects and much-improved cholesterol.

Summarised by Claude from the comment thread 3 days ago.

Points: 74
Comments: 43
Best rank: #14
Posted: 2026-10-22 by brandonb
Category: Health

coronary-inflammation cardiology ct-angiography medical-ai caristo-diagnostics biograph preventive-health

All captures:

Full page

Full-page screenshot of biograph.com

Captured 3 days ago. Click for the whole screenshot.

Looks similar

Screenshot of biographic.com: Ping, You've Got Whale: AI detection system alerts ships of whales in their path

Ping, You've Got Whale: AI detection system alerts ships of whales in their path (biographic.com)

154 points by Geekette 1 year ago | 66 comments

Screenshot of folding-sky.com: New York could prohibit chatbot medical, legal, engineering advice

New York could prohibit chatbot medical, legal, engineering advice (folding-sky.com)

48 points by bluepeter 7 months ago | 50 comments

Screenshot of ciphercue.com: 301M Records Exposed: The HIPAA Breach Epidemic

301M Records Exposed: The HIPAA Breach Epidemic (ciphercue.com)

27 points by adulion 7 months ago | 10 comments

Screenshot of bloomberg.com: Drugmakers are set to pay 23andMe to access consumer DNA

Drugmakers are set to pay 23andMe to access consumer DNA (bloomberg.com)

306 points by htrp 3 years ago | 379 comments

Screenshot of reuters.com: Ubisoft co-founder Claude Guillemot has died in a plane crash

Ubisoft co-founder Claude Guillemot has died in a plane crash (reuters.com)

128 points by drayfield 4 months ago | 65 comments

Screenshot of today.ucsd.edu: AI helps unravel a cause of Alzheimer’s and identify a therapeutic candidate

AI helps unravel a cause of Alzheimer’s and identify a therapeutic candidate (today.ucsd.edu)

309 points by pedalpete 1 year ago | 154 comments

Related stories

Screenshot pending…

MIT Study Finds AI Use Reprograms the Brain, Leading to Cognitive Decline (publichealthpolicyjournal.com)

438 points by cainxinth 1 year ago | 432 comments

Article reporting on an MIT study claiming that using AI tools like ChatGPT alters brain activity and leads to cognitive decline.

llm chatgpt cognitive-decline neuroscience

Screenshot of oii.ox.ac.uk: Study identifies weaknesses in how AI systems are evaluated

Study identifies weaknesses in how AI systems are evaluated (oii.ox.ac.uk)

397 points by pseudolus 11 months ago | 186 comments

Oxford Internet Institute news item on a study finding that most of 445 LLM benchmarks lack rigorous methods and clear definitions of what they measure.

llm-benchmarks ai-evaluation oxford-internet-institute construct-validity

Screenshot of nature.com: AI tools are spotting errors in research papers

AI tools are spotting errors in research papers (nature.com)

555 points by kgwgk 1 year ago | 200 comments

Nature news article on a growing movement using AI and large language models to detect errors in research papers, sparked by a flawed black plastic utensils study.

large-language-models scientific-publishing peer-review research-integrity

Screenshot of theguardian.com: Google AI Overviews cite YouTube more than any medical site for health queries

Google AI Overviews cite YouTube more than any medical site for health queries (theguardian.com)

379 points by bookofjoe 9 months ago | 200 comments

Guardian news article reporting a German study finding Google AI Overviews cite YouTube more than any medical website for health queries.

google-ai-overviews google youtube health-misinformation

Screenshot of thelibre.news: FOSS infrastructure is under attack by AI companies

FOSS infrastructure is under attack by AI companies (thelibre.news)

803 points by todsacerdoti 1 year ago | 487 comments

LibreNews article by Niccolò Venerandi on how LLM scrapers from AI companies are overloading and taking down FOSS projects' infrastructure.

llm-scrapers ai-crawlers foss-infrastructure gnome

Screenshot of thecivilian.co.nz: AI companies in race to demonstrate their model most threatening to humanity

AI companies in race to demonstrate their model most threatening to humanity (thecivilian.co.nz)

388 points by ljewalsh 28 days ago | 304 comments

Satirical news article from The Civilian claiming AI companies are competing to show their models are the most existentially threatening to humanity.

satire ai-safety existential-risk ai-industry