Accès ouvert déclaré
2026
preprint
Towards Federated Learning Across Biobanks: Prototype Software from the 2026 Carnegie Mellon University–NVIDIA Hackathon
Hieu Ngo, Mariona Jaramillo Civill, Arnav Kharbanda, Srikant Sarangi, Sean Davis, Seohyun Lee, Espen Hagen, Mrunali Abhijit Thokadiwala, Yosen Lin, Jędrzej Kubica, Peter Lawson, Jialan Ma, Jeffrey Wang, Md. Zillur Rahman, Enamul Hoq, Qiyu Yang, Prashnna Gyawali, Caiwei Maggie Zhang, Pu Kao, Dhruv Gor, Vibha Acharya, James Mu, Peiran Jiang, Yiman Wu, Ioannis Christofilogiannis, Tyler Jay Yang, Aryan Sharan Guda, Abraham G. Moller, Qianqian Liang, Shivank Sadasivan, Telaprolu Kumar Koushik, Suratha Sriram, Ushta Samal, Shreya Nandakumar, Aastha Shah, Beryl Rabindran, Rahaf M. Ahmad, Mengying Hu, Alina Devkota, Jacob Thrasher, Zheqian Zhu, Aditya Kumar Karna, Jiayan Zhou, Anna Boeva, Arun Sujatha Bharath Raj, Jasmine Baker, Derek Mu, Isha Parikh, Zhenghao Xiao, Nikita Rajesh, Melanie Gainey, Yuan-Ting Hsieh, Heena Dalal, Sihyun Park, Pravesh Parekh, Ben Busby, Huajin Wang, Amrit Gaire, Samarpan Mohanty, KUSHAL KOIRALA, Zhaoyi You, Bhanvi Paliwal, Andrew Scouten, Chantera Lazard, Holger R. Roth, Sumeet Kothare, Diya Patidar, Robert Loughnan, Yajushi Khurana, Chunduru Sri Abhijit, Jiayi Zhao, Kyulin Kim, Konstantinos Koukoutegos, Jeff Winchell, Jiahao He, Shreyan Balaji Nalwad, Adam Kehl, Sanjnaa Sridhar, Seungjin Han, Jingyao Chen
0Citations signalées, ce qui n’est pas une note de qualité
0Institutions déclarées
0Pays d’affiliation déclarés
Le résumé fourni par la source
The Carnegie Mellon University-NVIDIA Federated Learning Hackathon for Biomedical Applications (January 7-9, 2026) convened researchers from academia, government, and industry to implement federated frameworks for disease subtyping, genetic association studies, and multimodal clinical prediction using NVIDIA FLARE. This preprint presents ten projects spanning genome-wide association analyses, histopathology harmonization, pangenome construction, ancestry deconvolution, rare disease stratification, cancer subtyping, polygenic risk score aggregation, and multimodal fusion. These proofs of principle collectively demonstrate both the versatility of federated learning for biomedical applications and the technical considerations required for successful deployment.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
Aucun DOI disponible pour le contrôle Crossref.
Les sujets associés
Biomedical and Engineering EducationCancer Genomics and DiagnosticsSocial Media in Health Education