-
Mashup Score: 2
The current gold standard for evaluating generated chest x-ray (CXR) reports is through radiologist annotations. However, this process can be extremely time-consuming and costly, especially when…
Source: arXiv.orgCategories: General Medicine News, General HCPsTweet
-
Mashup Score: 2Uncovering Knowledge Gaps in Radiology Report Generation Models... - 5 month(s) ago
Recent advancements in artificial intelligence have significantly improved the automatic generation of radiology reports. However, existing evaluation methods fail to reveal the models’…
Source: arXiv.orgCategories: General Medicine News, General HCPsTweet-
Paper link: https://t.co/GBYJKQ4Fu7 Code & model available at: https://t.co/1gaSOCUhRi
-
-
Mashup Score: 2ReXrank: Radiology Report Generation Leaderboard - 6 month(s) ago
Open-source leaderboard for comparing and benchmarking AI models in radiology report generation.
Source: rexrank.azurewebsites.netCategories: General Medicine News, General HCPsTweet-
@XiaomanZhang99 @HarvardDBMI Website: https://t.co/7njam74Fmb
-
-
Mashup Score: 15Direct Preference Optimization for Suppressing Hallucinated Prior... - 8 month(s) ago
Recent advances in generative vision-language models (VLMs) have exciting potential implications for AI in radiology, yet VLMs are also known to produce hallucinations, nonsensical text, and other…
Source: arXiv.orgCategories: General Medicine News, General HCPsTweet-
5/ Huge congratulations to the amazing authors on this work: Oishi Banerjee (first author) with @HongYuZhou14, @subathraadithan, @StephenKwakMD, @_kaywu. Paper link: https://t.co/GlBS0trbgk
-
-
Mashup Score: 64
Nature Medicine – A large-scale study examined the heterogeneous effects of artificial intelligence (AI) assistance on 140 radiologists across 15 chest X-ray diagnostic tasks and found that…
Source: www.nature.comCategories: General Medicine News, General HCPsTweet-
What's the largest study of AI done with radiologists thus far? Our study on heterogeneity is with 140 radiologists (https://t.co/u4HrYSXwAs). Is anyone aware of other large studies actually *measuring* the effect of AI (not a perception study)?
-
-
Mashup Score: 6Guardrails for the use of generalist AI in cancer care - 10 month(s) ago
Nature Reviews Cancer – Generalist medical artificial intelligence (GMAI) models are gaining momentum in their applications for cancer treatment. In this Comment, Gilbert and Kather advocate for…
Source: www.nature.comCategories: General Medicine News, General HCPsTweet-
https://t.co/RjPZdABfkE
-
-
Mashup Score: 3Introducing Meta Llama 3: The most capable openly available LLM to date - 10 month(s) ago
Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model. In the coming months, we expect to share new capabilities, additional model sizes, and more.
Source: ai.meta.comCategories: General Medicine News, Future of MedicineTweet-
https://t.co/Vwe86m9bKS
-
-
Mashup Score: 74
New research shows radiologists and AI don’t always work well together
Source: hms.harvard.eduCategories: General Medicine News, General HCPsTweet-
Our work on radiologist performance being helped and hurt with AI featured in @harvardmed news. @HarvardDBMI https://t.co/6ePwv2EHar
-
-
Mashup Score: 74
New research shows radiologists and AI don’t always work well together
Source: hms.harvard.eduCategories: General Medicine News, General HCPsTweet-
Our work on radiologist performance being helped and hurt with AI featured in @harvardmed news. @HarvardDBMI https://t.co/6ePwv2EHar
-
-
Mashup Score: 151
Nature Medicine – A large-scale study examined the heterogeneous effects of artificial intelligence (AI) assistance on 140 radiologists across 15 chest X-ray diagnostic tasks and found that…
Source: www.nature.comCategories: General Medicine News, General HCPsTweet-
Who benefits from AI? Our new study with 140 radiologists in Nature Medicine challenges prevailing assumptions. We find years of experience, subspecialty and familiarity with AI tools fail to reliably predict the impact of AI assistance. https://t.co/u4HrYSXwAs
-
The bright spot is FineRadScore (https://t.co/5IARFJSlVh), a metric that uses GPT-4 to evaluate AI-generated reports. Though still imperfect, FineRadScore stays positively correlated with expert scores across all countries, suggesting that powerful LLMs can improve… https://t.co/1pdcmvO7Fb