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.