Author : Alexandros Karargyris, Renato Umeton, Micah J. Sheller, Alejandro Aristizabal, Johnu George, Anna Wuest, Sarthak Pati, Hasan Kassem, Maximilian Zenk, Ujjwal Baid, Prakash Narayana Moorthy, Alexander Chowdhury, Junyi Guo, Sahil Nalawade, Jacob Rosenthal, David Kanter, Maria Xenochristou, Daniel J. Beutel, Verena Chung, Timothy Bergquist, James Eddy, Abubakar Abid, Lewis Tunstall, Omar Sanseviero, Dimitrios Dimitriadis, Yiming Qian, Xinxing Xu, Yong Liu, Rick Siow Mong Goh, Srini Bala, Victor Bittorf, Sreekar Reddy Puchala, Biagio Ricciuti, Soujanya Samineni, Eshna Sengupta, Akshay Chaudhari, Cody Coleman, Bala Desinghu, Gregory Diamos, Debo Dutta, Diane Feddema, Grigori Fursin, Xinyuan Huang, Satyananda Kashyap, Nicholas Lane, Indranil Mallick, FeTS Consortium, BraTS-2020 Consortium, AI4SafeChole Consortium, Pietro Mascagni, Virendra Mehta, Cassiano Ferro Moraes, Vivek Natarajan, Nikola Nikolov, Nicolas Padoy, Gennady Pekhimenko, Vijay Janapa Reddi, G. Anthony Reina, Pablo Ribalta, Abhishek Singh, Jayaraman J. Thiagarajan, Jacob Albrecht, Thomas Wolf, Geralyn Miller, Huazhu Fu, Prashant Shah, Daguang Xu, Poonam Yadav, David Talby, Mark M. Awad, Jeremy P. Howard, Michael Rosenthal, Luigi Marchionni, Massimo Loda, Jason M. Johnson, Spyridon Bakas & Peter Mattson 

Blog: https://mlcommons.org/en/news/medperf-nature-mi/?linkId=8899300 
Paper Link : https://www.nature.com/articles/s42256-023-00652-2

MedPerf Official Page: https://www.medperf.org/

 

- AI 모델의 일반화를 위해 다양한 데이터 기관에서 데이터의 유출없이 Federated evaluation을 목적으로하는 협의체 및 플랫폼MedPerf 발표

- 많은 기업, 병원, 대학들이 협력하는 ' MLCommons Medical Working Group'에서 주도

'MEDICAL & HEALTHCARE AI' 카테고리의 다른 글

[북마크] Artificial Intelligence in U.S. Health Care Delivery (Nikhil R. Sahni, NEJM 2023)  (0) 2023.07.28
[요약] Detecting shortcut learning for fair medical AI using shortcut testing (Alexander Brown, Nature Communications 2023)  (0) 2023.07.23
[요약] Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians (Krishnamurthy Dvijotham, Nature Medicine 2023)  (0) 2023.07.19
[북마크] Leveraging Large Language Models for Generating Responses to Patient Messages (Siru Liu, medRxiv 2023)  (0) 2023.07.17
[북마크] Large language model AI chatbots require approval as medical devices (Stephen Gilbert, Nature Medicine 2023; Comment)  (0) 2023.07.01

Author : Krishnamurthy (Dj) Dvijotham, Jim Winkens, Melih Barsbey, Sumedh Ghaisas, Robert Stanforth, Nick Pawlowski, Patricia Strachan, Zahra Ahmed, Shekoofeh Azizi, Yoram Bachrach, Laura Culp, Mayank Daswani, Jan Freyberg, Christopher Kelly, Atilla Kiraly, Timo Kohlberger, Scott McKinney, Basil Mustafa, Vivek Natarajan, Krzysztof Geras, Jan Witowski, Zhi Zhen Qin, Jacob Creswell, Shravya Shetty, Marcin Sieniek, Terry Spitz, Greg Corrado, Pushmeet Kohli, Taylan Cemgil & Alan Karthikesalingam
Paper Link : https://www.nature.com/articles/s41591-023-02437-x

Blog: https://www.deepmind.com/blog/codoc-developing-reliable-ai-tools-for-healthcare

Code: https://github.com/deepmind/codoc

 

- By Google DeepMind and Google Research

- Pretrained AI와 의료진의 협업으로 효과적인 Clinical decision making을 하는 방법 (CoDoc) 에 대한 연구

- "언제 AI를 사용하고 언제 의료진이 판단할것인가?"

- Pretrained AI의 confidence score를 바탕으로 Deferral AI model이 AI의 판단을 그대로 쓸지, 의료진에 넘길지(Defer)를 결정

- 딥러닝 모델은 X.

- 협력 결과로서의 판단이 Sensitivity와 Specificity를 최적화 하는 방향으로 설계된 Advantage function을 계산

- Advantage function이 0보다 크면 의료진에 판단을 넘기고, 0보다 작으면 AI모델의 판단을 그대로 사용

- Advantage function은 Kernel Density Estimation방법을 사용하여 근사한 확률로 계산

- UK mammography 데이터셋을 사용한 시뮬레이션 결과 (즉, prospective trial은 아님), CoDoc를 사용하면 True Positive와 False Negative의 변화 없이 False Positive가 25% 감소.

- 또한 의료진의 판단업무를 2/3 줄여줌 (66% 적은 workload) 

'MEDICAL & HEALTHCARE AI' 카테고리의 다른 글

[요약] Detecting shortcut learning for fair medical AI using shortcut testing (Alexander Brown, Nature Communications 2023)  (0) 2023.07.23
[요약] Federated benchmarking of medical artificial intelligence with MedPerf (Alexandros Karargyris, Nature Macine Intelligence 2023)  (0) 2023.07.19
[북마크] Leveraging Large Language Models for Generating Responses to Patient Messages (Siru Liu, medRxiv 2023)  (0) 2023.07.17
[북마크] Large language model AI chatbots require approval as medical devices (Stephen Gilbert, Nature Medicine 2023; Comment)  (0) 2023.07.01
[북마크] NYUTron: Health system-scale language models are all-purpose prediction engines (Lavender Yao Jiang, Nature 2023)  (0) 2023.06.08

Author : Siru Liu, Allison B McCoy, Aileen P Wright, Babatunde Carew, Julian Z Genkins, Sean S Huang, Josh F Peterson, Bryan Steitz, Adam Wright
Paper Link : https://www.medrxiv.org/content/10.1101/2023.07.14.23292669v1

'MEDICAL & HEALTHCARE AI' 카테고리의 다른 글

[요약] Federated benchmarking of medical artificial intelligence with MedPerf (Alexandros Karargyris, Nature Macine Intelligence 2023)  (0) 2023.07.19
[요약] Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians (Krishnamurthy Dvijotham, Nature Medicine 2023)  (0) 2023.07.19
[북마크] Large language model AI chatbots require approval as medical devices (Stephen Gilbert, Nature Medicine 2023; Comment)  (0) 2023.07.01
[북마크] NYUTron: Health system-scale language models are all-purpose prediction engines (Lavender Yao Jiang, Nature 2023)  (0) 2023.06.08
[북마크] Almanac: Retrieval-Augmented Language Models for Clinical Medicine (Cyril Zakka, Arxiv2023)  (0) 2023.06.08

Author : Stephen Gilbert, Hugh Harvey, Tom Melvin, Erik Vollebregt & Paul Wicks 
Paper Link : https://www.nature.com/articles/s41591-023-02412-6
 

'MEDICAL & HEALTHCARE AI' 카테고리의 다른 글

[요약] Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians (Krishnamurthy Dvijotham, Nature Medicine 2023)  (0) 2023.07.19
[북마크] Leveraging Large Language Models for Generating Responses to Patient Messages (Siru Liu, medRxiv 2023)  (0) 2023.07.17
[북마크] NYUTron: Health system-scale language models are all-purpose prediction engines (Lavender Yao Jiang, Nature 2023)  (0) 2023.06.08
[북마크] Almanac: Retrieval-Augmented Language Models for Clinical Medicine (Cyril Zakka, Arxiv2023)  (0) 2023.06.08
[요약] Med-PaLM: Large Language Models Encode Clinical Knowledge (Karan Singhal, Nature 2023)  (0) 2022.12.30

구글 딥마인드의 LLM활용 로보틱스 논문이 한번에 여러개 나와,

네이버 클라우드 하정우 박사님께서 운영하시는 Weekly AI ArXiv에서 정말 가볍게 소개.

https://github.com/jungwoo-ha/WeeklyArxivTalk/issues/87#issuecomment-1606018653

 

[20230625] Weekly AI ArXiv 만담 시즌2 - 21회차 · Issue #87 · jungwoo-ha/WeeklyArxivTalk

Zoom webinar: https://navercorp.zoom.us/j/92208940283 News 6.25 73주년 순국선열들의 희생에 감사드립니다. Conferences EMNLP 2023 deadline: 모두 수고하셨습니다. CVPR 2023: 모두들 의미있는 학회 보내셨나요~ Best Paper: V

github.com

 

 

 

 

https://saytap.github.io/

 

SayTap: Language to Quadrupedal Locomotion

Use foot contact pattern to bridge LLM and low-level controller.

saytap.github.io

 

https://www.deepmind.com/blog/robocat-a-self-improving-robotic-agent?utm_source=twitter&utm_medium=social&utm_campaign=robocat 

 

RoboCat: A self-improving robotic agent

Robots are quickly becoming part of our everyday lives, but they’re often only programmed to perform specific tasks well. While harnessing recent advances in AI could lead to robots that could help in many more ways, progress in building general-purpose

www.deepmind.com

https://language-to-reward.github.io/

 

Language to Reward for Robotic Skill Synthesis

Project page for Language to Reward for Robotic Skill Synthesis.

language-to-reward.github.io

 

https://sites.google.com/view/agile-catching

'AI & RL > Foundation Model' 카테고리의 다른 글

[북마크] Formal Algorithms for Transformers (DeepMind, 2022)  (0) 2022.07.25
[요약] Do Prompt-Based Models Really Understand the Meaning of their Prompts? (Albert Webson, NAACL 2022)  (0) 2022.04.26
[북마크] Visual Prompting: Modifying Pixel Space to Adapt Pre-trained Models (방효진 님, ArXiv 2022)  (0) 2022.04.03

+ Recent posts

티스토리툴바