Cross-Level Matching Model for Information Retrieval

2020 ◽  
pp. 106-117
Author(s):  
Yifan Nie ◽  
Jian-Yun Nie
Keyword(s):  
Information Retrieval ◽  
Matching Model

scholarly journals An ensemble information retrieval method for the biomedical domain (Preprint)

2021 ◽  
Author(s):  
Zhiqiang Liu ◽  
Jingkun Feng ◽  
Zhihao Yang ◽  
Lei Wang
Keyword(s):  
Information Retrieval ◽  
Deep Learning ◽  
Text Classification ◽  
Query Expansion ◽  
Ensemble Method ◽  
Classification Model ◽  
Retrieval Performance ◽  
Matching Model ◽  
Ranking List ◽  
Initial Retrieval

BACKGROUND With the development of biomedicine, the number of biomedical documents has increased rapidly, which brings a great challenge for researchers retrieving the information they need. Information retrieval aims to meet this challenge by searching relevant documents from abundant documents based on the given query. However, sometimes the relevance of search results needs to be evaluated from multiple aspects in some specific retrieval tasks and thereby increases the difficulty of biomedical information retrieval. OBJECTIVE This study aims to find a more systematic method to retrieve relevant scientific literature for a given patient. METHODS In the initial retrieval stage, we supplement query terms through query expansion strategies and apply query boosting to obtain an initial ranking list of relevant documents. In the re-ranking phase, we employ a text classification model and relevance matching model to evaluate documents respectively from different dimensions, then we combine the outputs through logistic regression to re-rank all the documents from the initial ranking list. RESULTS The proposed ensemble method contributes to the improvement of biomedical retrieval performance. Comparing with the existing deep learning-based methods, experimental results show that our method achieves state-of-the-art performance on the data collection provided by TREC 2019 Precision Medicine Track. CONCLUSIONS In this paper, we propose a novel ensemble method based on deep learning. As shown in the experiments, the strategies we used in the initial retrieval phase such as query expansion and query boosting are effective. The application of the text classification model and the relevance matching model can better capture semantic context information and improve retrieval performance.

Patient trial matching using pseudo-siamese network.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14050-e14050
Author(s):  
Cao Xiao ◽  
Junyi Gao ◽  
Lucas Glass ◽  
Jimeng Sun
Keyword(s):  
Clinical Trials ◽  
Information Retrieval ◽  
Great Success ◽  
Accuracy Score ◽  
Matching Model ◽  
Exclusion Criteria ◽  
Dynamic Memory ◽  
Siamese Network ◽  
The Cross ◽  
Real World Datasets

e14050 Background: Clinical trials suffer from insufficient patient (pt) recruitment. The availability of electronic health records (EHR) and trial eligibility criteria (EC) is promising for data driven pt-trial matching. The objective is to find qualified pt given patients' EHR and trial EC in unstructured text EC. Pseudo-Siamese network is a novel subfield within information retrieval and has shown great success in the cross-modal information retrieval problems such as semantic image-text retrieval (e.g., match images with text descriptions). The objective is to find the match between pts and clinical trials using Pseudo-Siamese network based cross-modal retrieval. Our model addresses the following challenges: (1) How to match unstructured EC text with structured EHR where EC often encode more general disease concepts and EHR represent pt conditions using more specific medical codes. (2) How to capture pts' evolving health conditions. (3) How to explicitly handle the difference for inclusion and exclusion criteria. Methods: Our matching model addresses these challenges as follows: (1) we augment the medical codes in pts’ records with their textual descriptions and hierarchical taxonomies, such that concepts can be embedded in finer and more coarse levels for better concept alignment across pt data and ECs. (2) We include an attentive dynamic memory network that extracts the best matching and more recent pt EHR to match with ECs. (3) We introduce a composite loss term to maximize the similarity between pt records and inclusion criteria while minimizes the similarity between pt records and exclusion criteria. Results: We evaluated our model on a pt-trial match dataset on the ECs collected from 590 clinical trials from ClinicalTrials.gov. We also extract 83,371 pt claims data from IQVIA database collected (2002-2018), where each pt is eligible for at least one trial. We compared our model with leading pt-trial matching models. Our model significantly outperforms the best baseline model by 24.3% relatively higher accuracy score. We also tested these models in 34 oncology trials in 25 cancers. Results will be reported. Conclusions: Pseudo-Siamese network successfully solved the cross-modal information retrieval problems. We therefore propose a new pt-trial matching model based on Pseudo-Siamese network model. Experiments on real-world datasets demonstrated that our model significantly outperforms existing works in pt-trial matching for oncology trials.

Demonstration of the Use of Tape-Recorded Information from a High Vacuum Electron Microscope

1969 ◽  
Vol 27 ◽  
pp. 218-219
Author(s):  
Richard E. Hartman ◽  
Roberta S. Hartman ◽  
Peter L. Ramos
Keyword(s):  
Information Retrieval ◽  
Electron Microscope ◽  
Magnetic Tape ◽  
High Vacuum ◽  
Data Retrieval ◽  
Electronic Information ◽  
Electronic Data ◽  
Subsequent Processing ◽  
Continuous Record

We have long felt that some form of electronic information retrieval would be more desirable than conventional photographic methods in a high vacuum electron microscope for various reasons. The most obvious of these is the fact that with electronic data retrieval the major source of gas load is removed from the instrument. An equally important reason is that if any subsequent analysis of the data is to be made, a continuous record on magnetic tape gives a much larger quantity of data and gives it in a form far more satisfactory for subsequent processing.

Stain contamination and embedding in electron microscopy

1986 ◽  
Vol 44 ◽  
pp. 50-53
Author(s):  
Hilton H. Mollenhauer
Keyword(s):  
Electron Microscopy ◽  
Information Retrieval ◽  
Epoxy Resins ◽  
Image Contrast ◽  
Sample Preservation ◽  
Factors Associated ◽  
Amount Of Information ◽  
Electron Microscopical ◽  
Contrast Information

Many factors (e.g., resolution of microscope, type of tissue, and preparation of sample) affect electron microscopical images and alter the amount of information that can be retrieved from a specimen. Of interest in this report are those factors associated with the evaluation of epoxy embedded tissues. In this context, informational retrieval is dependant, in part, on the ability to “see” sample detail (e.g., contrast) and, in part, on tue quality of sample preservation. Two aspects of this problem will be discussed: 1) epoxy resins and their effect on image contrast, information retrieval, and sample preservation; and 2) the interaction between some stains commonly used for enhancing contrast and information retrieval.

Information and Dose in the Scanning Transmission Ion Microscope

1980 ◽  
Vol 38 ◽  
pp. 232-233
Author(s):  
Fox T. R. ◽  
R. Levi-Setti
Keyword(s):  
Information Retrieval ◽  
Electron Microscope ◽  
Elastic Scattering ◽  
Energy Loss ◽  
Cross Sections ◽  
Previous Analysis ◽  
Single Scattering ◽  
Screening Length ◽  
Relative Damage ◽  
Scanning Transmission

At an earlier meeting [1], we discussed information retrieval in the scanning transmission ion microscope (STIM) compared with the electron microscope at the same energy. We treated elastic scattering contrast, using total elastic cross sections; relative damage was estimated from energy loss data. This treatment is valid for “thin” specimens, where the incident particles suffer only single scattering. Since proton cross sections exceed electron cross sections, a given specimen (e.g., 1 μg/cm2 of carbon at 25 keV) may be thin for electrons but “thick” for protons. Therefore, we now extend our previous analysis to include multiple scattering. Our proton results are based on the calculations of Sigmund and Winterbon [2], for 25 keV protons on carbon, using a Thomas-Fermi screened potential with a screening length of 0.0226 nm. The electron results are from Crewe and Groves [3] at 30 keV.

Sign in / Sign up

Export Citation Format

Share Document