Filters








30 Hits in 4.7 sec

MedGraph: Structural and Temporal Representation Learning of Electronic Medical Records [article]

Bhagya Hettige, Yuan-Fang Li, Weiqing Wang, Suong Le, Wray Buntine
2020 arXiv   pre-print
Electronic medical record (EMR) data contains historical sequences of visits of patients, and each visit contains rich information, such as patient demographics, hospital utilisation and medical codes,  ...  To address these limitations, we present MedGraph, a supervised EMR embedding method that captures two types of information: (1) the visit-code associations in an attributed bipartite graph, and (2) the  ...  Then, we consider the V -C attributed bipartite graph and learn visit and code similarities based on the graph structure proximity.  ... 
arXiv:1912.03703v3 fatcat:ymoqtgafpjelvpwhci34nirtyi

Leveraging graph-based hierarchical medical entity embedding for healthcare applications

Tong Wu, Yunlong Wang, Yue Wang, Emily Zhao, Yilian Yuan
2021 Scientific Reports  
Using real-world clinical data, we demonstrate the efficacy of over competitive baselines on diagnosis prediction, readmission prediction, as well as recommending doctors to patients based on their medical  ...  To embed doctors and patients, we adhere to the principle "it's what you do that defines you" and derive their embeddings based on their interactions with other types of entities through graph neural network  ...  For example, if learning the patient and doctor embeddings from the patient-doctor bipartite graph as the first step, we can only focus on preserving the edges between patient and doctor nodes as there  ... 
doi:10.1038/s41598-021-85255-w pmid:33712670 pmcid:PMC7955058 fatcat:7acvfsmikzagvbjery2cm52vyq

Temporal Cascade and Structural Modelling of EHRs for Granular Readmission Prediction [article]

Bhagya Hettige, Weiqing Wang, Yuan-Fang Li, Suong Le, Wray Buntine
2021 arXiv   pre-print
Predicting (1) when the next hospital admission occurs and (2) what will happen in the next admission about a patient by mining electronic health record (EHR) data can provide granular readmission predictions  ...  To supplement the patients with short visit sequences, a structural modelling technique with graph-based methods is used to construct the markers of the point process in MEDCAS.  ...  This demonstrates that the graph-based based code-sharing behaviour learning is very useful in this task.  ... 
arXiv:2102.02586v1 fatcat:miwtjppqijfcdldapmhgpi5n2u

Modeling and Interpreting Patient Subgroups in Hospital Readmission: Visual Analytical Approach [article]

Suresh K. Bhavnani, Weibin Zhang, Shyam Visweswaran, Mukaila Raji, Yong-Fang Kuo
2022 medRxiv   pre-print
These data were analyzed using: (1) bipartite networks to identify patient subgroups based on frequently co-occurring high-risk comorbidities; (2) multinomial logistic regression to classify patients into  ...  Such advances could improve the interpretability and predictive accuracy of patient subgroup models for reducing the risk of hospital readmission and beyond.  ...  biclustering, critical for gauging its significance; and (3) the use of a graph representation enabled the results to be visualized through a network.  ... 
doi:10.1101/2022.02.27.22271534 fatcat:lyp4x44zajh4fg3635lrpvoium

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

Cao Xiao, Edward Choi, Jimeng Sun
2018 JAMIA Journal of the American Medical Informatics Association  
Design/method: We searched PubMed and Google Scholar for papers on deep learning studies using EHR data published between January 1, 2010, and January 31, 2018.  ...  Results: We surveyed and analyzed multiple aspects of the 98 articles we found and identified the following analytics tasks: disease detection/classification, sequential prediction of clinical events,  ...  Results showed disease prediction tasks based on concept embedding outperformed those achieved using other feature learning strategies.  ... 
doi:10.1093/jamia/ocy068 pmid:29893864 fatcat:ne7weiw7xvc2lp7hfgkzltdnri

Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization [article]

Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh
2017 arXiv   pre-print
We demonstrate the capacity of our model on applications such as handwritten digit recognition, face recognition, document classification and patient readmission prognosis.  ...  The success of any machine learning system depends critically on effective representations of data.  ...  For each time of hospitalization, patient information is recorded into a database using the MySQL server of the hospital.  ... 
arXiv:1708.05603v1 fatcat:pss7kaqzibg43of2w63dhtuwem

Deep learning for healthcare: review, opportunities and challenges

Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, Joel T. Dudley
2017 Briefings in Bioinformatics  
Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health.  ...  Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or  ...  [61] used RBMs to learn representations from EHRs that revealed novel concepts and demonstrated better prediction accuracy on a number of diseases.  ... 
doi:10.1093/bib/bbx044 pmid:28481991 fatcat:oefjv547ivazzoal3qc77d7ti4

Applying Deep Learning to Individual and Community Health Monitoring Data: A Survey

Zhen-Jie Yao, Jie Bi, Yi-Xin Chen
2018 International Journal of Automation and Computing  
We focus on 7 application areas of deep learning, which are electronic health records (EHR), electrocardiography (ECG), electroencephalogram (EEG), community healthcare, data from wearable devices, drug  ...  analysis and genomics analysis.  ...  Acknowledgements This work was supported by US National Science Foundation (Nos. DBI-1356669 and III-1526012).  ... 
doi:10.1007/s11633-018-1136-9 fatcat:drp2ixw3dvb5thxxnuzl4vjqsu

FutureMatch: Learning to Match in Dynamic Environments

J. Dickerson, T. Sandholm
2014 Transplantation  
., "maximize graft survival of transplants over time") decided on by experts, then automatically (i) learns based on data how to make this objective concrete and (ii) learns the "means" to accomplish this  ...  of pairs based on features such as donor and patient blood types), translates these to weights, and performs a computationally feasible batch matching that incorporates dynamic, failure-aware considerations  ...  This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation grant number OCI-1053575; specifically, it used the Blacklight system  ... 
doi:10.1097/00007890-201407151-02249 fatcat:p2tq45qh4jgdznpehapjrhelwi

Deep Learning Methods for Cardiovascular Image

Yankun Cao, Zhi Liu, Pengfei Zhang, Yushuo Zheng, Yongsheng Song, Lizhen Cui
2019 Journal of Artificial Intelligence and Systems  
Cardiovascular disease is one of the most important diseases that endanger human health at present. It is very meaningful to diagnose and treat cardiovascular disease by means of in-depth learning.  ...  In order to make deep learning better applied to cardiovascular diseases, this paper first outlines the development and causes of cardiovascular diseases, then describes several theoretical models of deep  ...  Later, watershed technology based on morphology and segmentation technology based on deformation model are introduced.  ... 
doi:10.33969/ais.2019.11006 fatcat:egx5tibvm5dhriemz4dvx5ktsm

Towards Team-Centered Informatics: Accelerating Innovation in Multidisciplinary Scientific Teams Through Visual Analytics

Suresh K. Bhavnani, Shyam Visweswaran, Rohit Divekar, Allan R. Brasier
2018 Journal of Applied Behavioral Science  
Here, we explore the use of a visual analytical representation to help MTTs integrate molecular and clinical data with the goal of accelerating translational insights.  ...  However, such teams face numerous barriers in integrating multidisciplinary knowledge, which is further exacerbated by the explosion of molecular and clinical data generated from millions of patients.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health or the Patient-Centered Outcomes Research Institute.  ... 
doi:10.1177/0021886318794606 fatcat:vhdsfe6uzragnoi2uscds7ordq

Statistical Latent Space Approach for Mixed Data Modelling and Applications [article]

Tu Dinh Nguyen, Truyen Tran, Dinh Phung, Svetha Venkatesh
2017 arXiv   pre-print
We also integrate structured sparsity and distance metric learning into RBM-based models.  ...  Our proposed methods are applied in various applications including latent patient profile modelling in medical data analysis and representation learning for image retrieval.  ...  Predicting disease codes for future years enables hospitals to prepare finance, equipment and logistics for individual requirements of patients.  ... 
arXiv:1708.05594v1 fatcat:5wgecztyvnhu3lua6hawt5mday

Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data [article]

Benjamin Shickel, Parisa Rashidi
2020 arXiv   pre-print
Despite their increased predictive power, model transparency and human explainability remain a significant challenge due to the "black box" nature of modern deep learning models.  ...  Comparatively, less attention has been paid to interpreting deep learning frameworks using sequential data.  ...  A similar approach was taken by Zhang et al. 59 in their Patient2Vec system for predicting hospital readmission risk.  ... 
arXiv:2004.12524v1 fatcat:jwqe4xqvr5ambcpd6disgv5hfm

Deep Learning for Health Informatics

Daniele Ravi, Charence Wong, Fani Deligianni, Melissa Berthelot, Javier Andreu-Perez, Benny Lo, Guang-Zhong Yang
2017 IEEE journal of biomedical and health informatics  
This has also prompted increasing interests in the generation of analytical, data driven models based on machine learning in health informatics.  ...  The paper mainly focuses on key applications of deep learning in the fields of translational bioinformatics, medical imaging, pervasive sensing, medical informatics, and public health.  ...  [109] compared different models in their ability to predict hospital readmissions based on a large EHR database.  ... 
doi:10.1109/jbhi.2016.2636665 pmid:28055930 fatcat:24hfhfasljhehb2phndoyu5rnm

QSAR without borders

Eugene N. Muratov, Jürgen Bajorath, Robert P. Sheridan, Igor V. Tetko, Dmitry Filimonov, Vladimir Poroikov, Tudor I. Oprea, Igor I. Baskin, Alexandre Varnek, Adrian Roitberg, Olexandr Isayev, Stefano Curtalolo (+7 others)
2020 Chemical Society Reviews  
In graph-based approaches, chemical reactions and individual molecules (reactants and products) are represented as nodes of a large bipartite graph 166 used to optimize synthetic pathways.  ...  of readmissions; cluster 8 is associated with chronic kidney disease (CKD) and type 2 diabetes in patients aged 40-65, whereas cluster 9 has frequent readmissions, severe disease and high number of anticholinergic  ... 
doi:10.1039/d0cs00098a pmid:32356548 fatcat:l456rjoqbzgehkqa63uvqrv2gy
« Previous Showing results 1 — 15 out of 30 results