no code implementations • 10 Apr 2024 • Yingbo Ma, Suraj Kolla, Zhenhong Hu, Dhruv Kaliraman, Victoria Nolan, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Jeremy A. Balch, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel
To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries.
no code implementations • 9 Apr 2024 • Yonggi Park, Yuanfang Ren, Benjamin Shickel, Ziyuan Guan, Ayush Patela, Yingbo Ma, Zhenhong Hu, Tyler J. Loftus, Parisa Rashidi, Tezcan Ozrazgat-Baslanti, Azra Bihorac
Federated learning models achieved comparable AUROC performance to central learning models, except for prolonged ICU stay, where the performance of federated learning models was slightly higher than central learning models at UFH GNV center, but slightly lower at UFH JAX center.
no code implementations • 6 Mar 2024 • Yingbo Ma, Suraj Kolla, Dhruv Kaliraman, Victoria Nolan, Zhenhong Hu, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel
The breadth, scale, and temporal granularity of modern electronic health records (EHR) systems offers great potential for estimating personalized and contextual patient health trajectories using sequential deep learning.
3 code implementations • 9 May 2021 • Avik Pal, Yingbo Ma, Viral Shah, Christopher Rackauckas
While we can control the computational cost by choosing the number of layers in standard architectures, in NDEs the number of neural network evaluations for a forward pass can depend on the number of steps of the adaptive ODE solver.
4 code implementations • 9 May 2021 • Shashi Gowda, Yingbo Ma, Alessandro Cheli, Maja Gwozdz, Viral B. Shah, Alan Edelman, Christopher Rackauckas
We showcase how this can be used to optimize term construction and give a 113x acceleration on general symbolic transformations.
1 code implementation • 29 Mar 2021 • Suyong Kim, Weiqi Ji, Sili Deng, Yingbo Ma, Christopher Rackauckas
We first show the challenges of learning neural ODE in the classical stiff ODE systems of Robertson's problem and propose techniques to mitigate the challenges associated with scale separations in stiff systems.
no code implementations • 7 Oct 2020 • Ranjan Anantharaman, Yingbo Ma, Shashi Gowda, Chris Laughman, Viral Shah, Alan Edelman, Chris Rackauckas
Modern design, control, and optimization often requires simulation of highly nonlinear models, leading to prohibitive computational costs.
7 code implementations • 13 Jan 2020 • Christopher Rackauckas, Yingbo Ma, Julius Martensen, Collin Warner, Kirill Zubov, Rohit Supekar, Dominic Skinner, Ali Ramadhan, Alan Edelman
In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets."
5 code implementations • 6 Feb 2019 • Chris Rackauckas, Mike Innes, Yingbo Ma, Jesse Bettencourt, Lyndon White, Vaibhav Dixit
We show high-level functionality for defining neural ordinary differential equations (neural networks embedded into the differential equation) and describe the extra models in the Flux model zoo which includes neural stochastic differential equations.
1 code implementation • 5 Dec 2018 • Christopher Rackauckas, Yingbo Ma, Vaibhav Dixit, Xingjian Guo, Mike Innes, Jarrett Revels, Joakim Nyberg, Vijay Ivaturi
In this manuscript we investigate the performance characteristics of Discrete Local Sensitivity Analysis implemented via Automatic Differentiation (DSAAD) against continuous adjoint sensitivity analysis.
Numerical Analysis