Akshay Goel
@AkshayGoelMD
Followers
300
Following
212
Media
10
Statuses
143
Physician-Engineer | Health AI @ Google Research
New York, NY
Joined July 2009
🚀 Excited to share two open-source releases today from our team at @GoogleResearch . • 𝐋𝐚𝐧𝐠𝐄𝐱𝐭𝐫𝐚𝐜𝐭 – Gemini-powered information extraction .• 𝐑𝐚𝐝𝐄𝐱𝐭𝐫𝐚𝐜𝐭 – Radiology reporting demo. Try RadExtract → #LangExtract #Gemini (1/4)
1
10
36
Great video on #LangExtract from @Sam_Witteveen — Loved the demo at the end :) . Thanks for making this Sam!.
0
1
3
RT @_kmbro: @googledevs @AkshayGoelMD For anyone who is interested -- I ported this to typescript and added an ability to use OpenAI not ju….
npmjs.com
A TypeScript library for extracting structured and grounded information from text using LLMs. Latest version: 1.1.0, last published: 4 days ago. Start using langextract in your project by running...
0
3
0
Great video by @MervinPraison on #LangExtract. Mervin, thank you for taking the time to make this!.
0
1
1
Wow! This is the first time I've seen LangExtract working with a different language, let alone a different character set! 🎉. #LangExtract #Gemini @GoogleResearch @GoogleDeepMind.
这个用来分析长篇纯文字的内容, 提取关键词确实有点快, 后续可以用来筛选 比如:客户体验 / 市场调研 / 新闻资讯提取公司名、股价预测、风险信号, 确实可以一试.
0
0
0
RT @iamxmm20: 这个用来分析长篇纯文字的内容, 提取关键词确实有点快, 后续可以用来筛选 比如:客户体验 / 市场调研 / 新闻资讯提取公司名、股价预测、风险信号, 确实可以一试.
0
1
0
@GoogleResearch @googledevs Special thanks to collaborators at @GoogleResearch, @GoogleForHealth, and @GoogleDeepMind. LangExtract leverages the latest advances in Gemini 2.5. Excited to see how the community applies this to new information-extraction use cases! (4/4). #LangExtract #Gemini #HealthAI (4/4).
0
0
0
@GoogleResearch @googledevs Explore the code, examples, and API docs on GitHub → . @LangExtract #GitHub #Python #NLP #OpenSource (3/4).
github.com
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. - google/langextract
1
0
0
@GoogleResearch For more background on LangExtract, see the blog post at: . . #LangExtract @googledevs (2/4).
developers.googleblog.com
1
0
1
Excited to see the 𝐑𝐚𝐝𝐄𝐱𝐭𝐫𝐚𝐜𝐭 radiology demo launch today! Congrats to the team on this release with 𝐋𝐚𝐧𝐠𝐄𝐱𝐭𝐫𝐚𝐜𝐭. #LangExtract #RadExtract #Radiology #AIinMedicine.
Valuable insights are often locked in unstructured text like clinical notes. That’s why we’re excited to introduce LangExtract, our new open-source library designed to turn unstructured text into structured, traceable data. Read about LangExtract here:
1
0
3
Excited to see LangExtract open sourced today! Congrats to the team on this launch and looking forward to what developers build with it. #LangExtract #Gemini #Python.
✨Announcing LangExtract! ✨. Our new open-source Python library for information extraction, powered by #Gemini. ✅ Turn text into structured data .✅ Trace every insight to its source .✅ Visualize results instantly. Explore the blog by @AkshayGoelMD and Atilla:
1
0
5
RT @EHuanglu: RIP Photoshop. Gemini 2.0 now can edit image by talking to it , it's insane. Here’s how it works:
0
950
0
Interesting list of predictions here!. Re: #2: IMO, to meaningfully reduce fatigue, reports will need to minimize false positives and shift from pure text to being grounded in diagnostic images—removing context-switching fatigue.
Hot off the press, part of @radiology_rsna journal's centennial: The Future of AI and Informatics in Radiology: 10 Predictions
1
1
2
Congratulations to the team on this incredible work!. The release of the CT Foundation tool is a step toward making AI model development for 3D CT volumes more accessible and efficient.
Announcing CT Foundation, a new medical imaging embedding tool that accepts a computed tomography (CT) volume as input and returns a small, information-rich numerical embedding that can be used to rapidly train models. Learn more and try it out yourself →
0
1
1
Excited to share work @GoogleHealth presented today at #ML4H2023 @SymposiumML4H and published in #PMLR. 🌟 LLMs Accelerate Annotation for Medical Information Extraction.📄 Paper: #Google #GoogleResearch #GoogleHealth #NeurIPS #ML4H #LLM #NLP.
proceedings.mlr.press
The unstructured nature of clinical notes within electronic health records often conceals vital patient-related information, making it challenging to access ...
0
2
34
RT @Tomography_MDPI: 💃Newly published hot paper:.Clinical Quality Control of #MRI Total #Kidney Volume Measurements in #Autosomal Dominant….
0
4
0
RT @WCMRadiology: In @jmri_ismrm, H. Dev, C. Zhu, @sharbatdara1, @ImranRazaaaa, S. Wang, D. Romano, @AkshayGoelMD, K. Teichman, M. Moghadam….
onlinelibrary.wiley.com
Background Total kidney volume (TKV) is an important biomarker for assessing kidney function, especially for autosomal dominant polycystic kidney disease (ADPKD). However, TKV measurements from a...
0
2
0
RT @sharbatdara1: Congrats to our team for publishing this amazing article. @WCMRadiology @MolecularWCM @rogosin @AkshayGoelMD @jmri_ismrm….
onlinelibrary.wiley.com
Background Total kidney volume (TKV) is an important biomarker for assessing kidney function, especially for autosomal dominant polycystic kidney disease (ADPKD). However, TKV measurements from a...
0
2
0
RT @sharbatdara1: So honored and thrilled to receive this award from @RSNA. Thank you for recognizing the importance of our research! Many….
0
2
0
Exciting to see things like the Hydra config management make it into course lecture notes now! 🎉. Btw: If you are using your custom config management solution for ML, you should check out asap!.
hydra.cc
A framework for elegantly configuring complex applications
We're halfway through #HarvardCS197: AI Research Experiences!. We've covered language models, Python practices, reading AI papers, PyTorch, Lightning, Weights & Biases, Hydra, and research Idea generation. My lecture notes (~13hrs) are publicly available:
0
0
1