Hui Li
University at Buffalo
12 Papers
42 Citations
Hui Li is an academic researcher from University at Buffalo. The author has contributed to research in topics: Health care & Bone mineral. The author has an hindex of 6, co-authored 12 publications. Previous affiliations of Hui Li include State University of New York System.
Chat about Author
Papers
A deep learning approach to link prediction in dynamic networks
TL;DR: Wang et al. as discussed by the authors proposed a novel deep learning framework, i.e., Conditional Temporal Restricted Boltzmann Machine (ctRBM), which predicts links based on individual transition variance as well as influence introduced by local neighbors.
Identifying informative risk factors and predicting bone disease progression via deep belief networks.
TL;DR: A general framework based on the heterogeneous electronic health records (EHRs) for the risk factor (RF) analysis that can be used for informative RF selection and the prediction of osteoporosis is developed.
40
Prediction and informative risk factor selection of bone diseases
TL;DR: A disease memory (DM) framework can successfully predict the bone disease and select the informative RFs that are beneficial and useful to aid clinical decision support and stable and promising performance on evaluation metrics confirms the effectiveness of the model.
22
Bone disease prediction and phenotype discovery using feature representation over electronic health records
Hui Li,Xiaoyi Li,Xiaowei Jia,Murali Ramanathan,Aidong Zhang +4 more
- 09 Sep 2015
TL;DR: A 2-layer deep graphical model to use EHR with minimal human supervision which derives a new representation of medical objects by embedding them in a low-dimensional vector space that not only improves the risk prediction accuracy but also presents clinically meaningful risk factor grouping for bone diseases.
13
A generative framework for prediction and informative risk factor selection of bone diseases
Hui Li,Xiaoyi Li,Yuan Zhang,Murali Ramanathan,Aidong Zhang +4 more
- 01 Dec 2013
TL;DR: Several empirical results on a real bone disease data set show that the proposed framework can successfully predict bone diseases and select informative risk factors that are beneficial and useful to guide clinical decisions.
11