no code implementations • 15 May 2022 • Yikuan Li, Mohammad Mamouei, Shishir Rao, Abdelaali Hassaine, Dexter Canoy, Thomas Lukasiewicz, Kazem Rahimi, Gholamreza Salimi-Khorshidi
Most machine learning (ML) models are developed for prediction only; offering no option for causal interpretation of their predictions or parameters/properties.
1 code implementation • 7 Feb 2022 • Shishir Rao, Mohammad Mamouei, Gholamreza Salimi-Khorshidi, Yikuan Li, Rema Ramakrishnan, Abdelaali Hassaine, Dexter Canoy, Kazem Rahimi
The rise of "doubly robust" non-parametric tools coupled with the growth of deep learning for capturing rich representations of multimodal data, offers a unique opportunity to develop and test such models for causal inference on comprehensive electronic health records (EHR).
no code implementations • 27 Jul 2021 • Jose Roberto Ayala Solares, Yajie Zhu, Abdelaali Hassaine, Shishir Rao, Yikuan Li, Mohammad Mamouei, Dexter Canoy, Kazem Rahimi, Gholamreza Salimi-Khorshidi
In this study, we aim to (1) train some of the most prominent disease embedding techniques on a comprehensive EHR data from 3. 1 million patients, (2) employ qualitative and quantitative evaluation techniques to assess these embeddings, and (3) provide pre-trained disease embeddings for transfer learning.
no code implementations • 21 Jun 2021 • Yikuan Li, Mohammad Mamouei, Gholamreza Salimi-Khorshidi, Shishir Rao, Abdelaali Hassaine, Dexter Canoy, Thomas Lukasiewicz, Kazem Rahimi
Capturing the whole history of medical encounters is expected to lead to more accurate predictions, but the inclusion of records collected for decades and from multiple resources can inevitably exceed the receptive field of the existing deep learning architectures.
no code implementations • 17 Feb 2021 • Yikuan Li, Shishir Rao, Mohammad Mamouei, Gholamreza Salimi-Khorshidi, Dexter Canoy, Abdelaali Hassaine, Thomas Lukasiewicz, Kazem Rahimi
In this study, we propose two methods, namely, model distillation and variable selection, to untangle hidden patterns learned by an established deep learning model (BEHRT) for risk association identification.
no code implementations • 27 Jan 2021 • Shishir Rao, Yikuan Li, Rema Ramakrishnan, Abdelaali Hassaine, Dexter Canoy, John Cleland, Thomas Lukasiewicz, Gholamreza Salimi-Khorshidi, Kazem Rahimi
Predicting the incidence of complex chronic conditions such as heart failure is challenging.
no code implementations • 23 Mar 2020 • Yikuan Li, Shishir Rao, Abdelaali Hassaine, Rema Ramakrishnan, Yajie Zhu, Dexter Canoy, Gholamreza Salimi-Khorshidi, Thomas Lukasiewicz, Kazem Rahimi
In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for more comprehensive uncertainty estimation.
no code implementations • 27 Feb 2020 • Danijela Horak, Simiao Yu, Gholamreza Salimi-Khorshidi
Automatic evaluation of the goodness of Generative Adversarial Networks (GANs) has been a challenge for the field of machine learning.
no code implementations • 27 Jan 2020 • Vincent Moens, Simiao Yu, Gholamreza Salimi-Khorshidi
This paper shows that most of the existing convolutional architectures define, at initialisation, a specific feature importance landscape that conditions their capacity to attend to different locations of the images later during training or even at test time.
1 code implementation • 22 Jul 2019 • Yikuan Li, Shishir Rao, Jose Roberto Ayala Solares, Abdelaali Hassaine, Dexter Canoy, Yajie Zhu, Kazem Rahimi, Gholamreza Salimi-Khorshidi
Today, despite decades of developments in medicine and the growing interest in precision healthcare, vast majority of diagnoses happen once patients begin to show noticeable signs of illness.
no code implementations • 19 Jul 2019 • Abdelaali Hassaine, Dexter Canoy, Jose Roberto Ayala Solares, Yajie Zhu, Shishir Rao, Yikuan Li, Mariagrazia Zottoli, Kazem Rahimi, Gholamreza Salimi-Khorshidi
Multimorbidity, or the presence of several medical conditions in the same individual, has been increasing in the population, both in absolute and relative terms.