·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Fable won’t answer basic biology questions1h◆Microsoft, like, totally gets why students are booing AI-pilled graduation speakers2h◆The future of AI regulation is courting the strangest, most anxious bedfellows2h◆Google won’t just admit it’s feeding YouTube creators to its music AI2h◆‘AI-pilled’ firms spend $7,500 per employee each month on AI2h◆Microsoft restricts Claude Fable for employees over data retention concerns2h◆Google will save your Lens photos, Search Live recordings, and Translate audio for AI training3h◆How memory tools can make AI models worse3h◆Cybersecurity researchers aren’t happy about the guardrails on Anthropic’s Fable4h◆Datadog veterans launch AI coding startup Niteshift on a bet against Big AI lock-in4h◆The three hard-tech moonshots fueling SpaceX’s unbelievable IPO4h◆Warner Music acquires AI attribution startup Sureel AI5h◆Jedify raises $24M to help companies arm AI agents with context on their business6h◆Decart’s new world model can simulate hours of photorealistic driving — with some caveats6h◆Meta signs first AI data center deal in India with Reliance12h◆BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression15h◆Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning15h◆Integral Field Unit Spectroscopy with One Fiber15h◆AMEL: Accumulated Message Effects on LLM Judgments15h◆Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models15h◆Fable won’t answer basic biology questions1h◆Microsoft, like, totally gets why students are booing AI-pilled graduation speakers2h◆The future of AI regulation is courting the strangest, most anxious bedfellows2h◆Google won’t just admit it’s feeding YouTube creators to its music AI2h◆‘AI-pilled’ firms spend $7,500 per employee each month on AI2h◆Microsoft restricts Claude Fable for employees over data retention concerns2h◆Google will save your Lens photos, Search Live recordings, and Translate audio for AI training3h◆How memory tools can make AI models worse3h◆Cybersecurity researchers aren’t happy about the guardrails on Anthropic’s Fable4h◆Datadog veterans launch AI coding startup Niteshift on a bet against Big AI lock-in4h◆The three hard-tech moonshots fueling SpaceX’s unbelievable IPO4h◆Warner Music acquires AI attribution startup Sureel AI5h◆Jedify raises $24M to help companies arm AI agents with context on their business6h◆Decart’s new world model can simulate hours of photorealistic driving — with some caveats6h◆Meta signs first AI data center deal in India with Reliance12h◆BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression15h◆Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning15h◆Integral Field Unit Spectroscopy with One Fiber15h◆AMEL: Accumulated Message Effects on LLM Judgments15h◆Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models15h◆
News/Can Large Language Models Reliably Extract Physiology Index Values from Coronary Angiography Reports?
arxiv
PublishedApril 16, 2026 at 4:00 AM
▲bullish

Can Large Language Models Reliably Extract Physiology Index Values from Coronary Angiography Reports?

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.13077v1 Announce Type: new Abstract: Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured natural language, limiting its use in research. We investigate the use of Large Language Models (LL

Models mentioned
01
  • 01meta-llama logo
    Llama-3.1-70B
    meta-llama/Llama-3.1-70B
Related
04
  • arxiv25d
    Krause Synchronization Transformers
  • arxiv26d
    A Large Language Model Based Pipeline for Review of Systems Entity Recognition from Clinical Notes
  • arxivMay 8
    Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
  • arxivApr 10
    SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
04
  • 01
    Llama-3.1-70B
    meta-llama/Llama-3.1-70B
  • 02
    GPT-OSS
  • 03
    MedGemma
  • 04
    MedLlama
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#medical-text#language-models#information-extraction#portuguese-language

No replies yet. Be first.

Mentioned models
04
  • 01
    Llama-3.1-70B
    meta-llama/Llama-3.1-70B
  • 02
    GPT-OSS
  • 03
    MedGemma
  • 04
    MedLlama
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#medical-text#language-models#information-extraction#portuguese-language

Related coverage

More from ARXIV
arxivBiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression15harxivFisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning15harxivIntegral Field Unit Spectroscopy with One Fiber15harxivAMEL: Accumulated Message Effects on LLM Judgments15h
The Bubble Brief
WEEKLY

Read medical-text insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews