Our concept extraction Python package, MicrobEx, is designed to be reused and adapted to individual institutions as an upstream process for other clinical applications, such as machine learning studies, clinical decision support, and disease surveillance systems.
Machine learning in medicine leverages the wealth of healthcare data to extract knowledge, facilitate clinical decision-making, and ultimately improve care delivery.
After adversarial training was proposed, a series of works focus on improving the compunational efficiency of adversarial training for deep neural networks (DNNs).
Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices.
We apply genetically motivated constrained tensor factorization to group pathways in a way that reflects molecular mechanism interactions.
Domain knowledge is important to understand both the lexical and relational associations of words in natural language text, especially for domain-specific tasks like Natural Language Inference (NLI) in the medical domain, where due to the lack of a large annotated dataset such knowledge cannot be implicitly learned during training.
Graph Neural Network (GNN) aggregates the neighborhood of each node into the node embedding and shows its powerful capability for graph representation learning.
Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval, clinical report auto-generation.
However, we propose two methods to estimate the source location in this paper under the fault model: hitting set approach and feature selection method, which only utilize the noisy data set at the fusion center for estimation of the source location without knowing the sensor parameters.
In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class.
Distributed representations of medical concepts have been used to support downstream clinical tasks recently.
We combine this information into a tensor of patients, counts of their genetic variants, and the membership of these genes in pathways.
Based on which, we further find that there is redundancy among the dimensions of latent variable, and the lengths and sentence patterns of the responses can be strongly correlated to each dimension of the latent variable.
Predicting patient mortality is an important and challenging problem in the healthcare domain, especially for intensive care unit (ICU) patients.
Distributed representations have been used to support downstream tasks in healthcare recently.
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness.
Ranked #4 on Link Prediction on FB15k-237 (MR metric)
In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy labels on some classes ("easy" classes), but more surprisingly, it also suffers from significant under learning on some other classes ("hard" classes).
Ranked #29 on Image Classification on Clothing1M
The problem of missing values in multivariable time series is a key challenge in many applications such as clinical data mining.
no code implementations • 10 Apr 2019 • Zhen-Xing Xu, Jingyuan Chou, Xi Sheryl Zhang, Yuan Luo, Tamara Isakova, Prakash Adekkanattu, Jessica S. Ancker, Guoqian Jiang, Richard C. Kiefer, Jennifer A. Pacheco, Luke V. Rasmussen, Jyotishman Pathak, Fei Wang
Sub-phenotype III is with average age 65. 07$ \pm 11. 32 $ years, and was characterized moderate loss of kidney excretory function and thus more likely to develop stage II AKI (SCr $1. 69\pm 0. 32$ mg/dL, eGFR $93. 97\pm 56. 53$ mL/min/1. 73$m^2$).
no code implementations • 2 Apr 2019 • Prakash Adekkanattu, Guoqian Jiang, Yuan Luo, Paul R. Kingsbury, Zhen-Xing Xu, Luke V. Rasmussen, Jennifer A. Pacheco, Richard C. Kiefer, Daniel J. Stone, Pascal S. Brandt, Liang Yao, Yizhen Zhong, Yu Deng, Fei Wang, Jessica S. Ancker, Thomas R. Campion, Jyotishman Pathak
While the NLP system showed high precision and recall measurements for four target concepts (aortic valve regurgitation, left atrium size at end systole, mitral valve regurgitation, tricuspid valve regurgitation) across all sites, we found moderate or poor results for the remaining concepts and the NLP system performance varied between individual sites.
In this study, we construct a graph to associate 4 types of medical entities, i. e., patients, encounters, lab tests, and medications, and applied a graph neural network to learn node embeddings for medication recommendation and lab test imputation.
However, most of the existing approaches for image representation ignore the relations between images and consider each input image independently.
no code implementations • 15 Nov 2018 • Yizhen Zhong, Luke Rasmussen, Yu Deng, Jennifer Pacheco, Maureen Smith, Justin Starren, Wei-Qi Wei, Peter Speltz, Joshua Denny, Nephi Walton, George Hripcsak, Christopher G. Chute, Yuan Luo
Good classification accuracy with simple features demonstrated the attribution coherence and the feasibility of automatic identification of design patterns.
We also developed a utility to convert an inline annotation format to stand-off annotations to enable the reuse of clinical text datasets with inline annotations.
We developed data-driven prediction models to estimate the risk of new AKI onset.
We used the simulation data to verify the effectiveness of this method, and then we applied it to ICU mortality risk prediction and demonstrated its superiority over other conventional supervised NMF methods.
In this paper, we recognize that novel classes should be different from each other, and propose distribution networks for open set learning that can model different novel classes based on probability distributions.
However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue.
We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus.
Ranked #6 on Text Classification on R52
Clinical text classification is an important problem in medical natural language processing.
Ranked #2 on Clinical Note Phenotyping on I2B2 2008: Obesity
Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants.
This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping.
Our model can accurately and efficiently identify distant recurrences in breast cancer by combining features extracted from unstructured clinical narratives and structured clinical data.
Parkinson's Disease (PD) is one of the most prevalent neurodegenerative diseases that affects tens of millions of Americans.
In order to elicit heterogeneous agents' private information and incentivize agents with different capabilities to act in the principal's best interest, we design an optimal joint incentive mechanism and prediction algorithm called COPE (COst and Prediction Elicitation), the analysis of which offers several valuable engineering insights.
In this paper, we present a study on the characteristics and classification of IBM sales questions.