Abstract:
BACKGROUND AND OBJECTIVE:Capturing the context of text is a challenging task in biomedical text summarization. The objective of this research is to show how contextualized embeddings produced by a deep bidirectional language model can be utilized to quantify the informative content of sentences in biomedical text summarization. METHODS:We propose a novel summarization method that utilizes contextualized embeddings generated by the Bidirectional Encoder Representations from Transformers (BERT) model, a deep learning model that recently demonstrated state-of-the-art results in several natural language processing tasks. We combine different versions of BERT with a clustering method to identify the most relevant and informative sentences of input documents. Using the ROUGE toolkit, we evaluate the summarizer against several methods previously described in literature. RESULTS:The summarizer obtains state-of-the-art results and significantly improves the performance of biomedical text summarization in comparison to a set of domain-specific and domain-independent methods. The largest language model not specifically pretrained on biomedical text outperformed other models. However, among language models of the same size, the one further pretrained on biomedical text obtained best results. CONCLUSIONS:We demonstrate that a hybrid system combining a deep bidirectional language model and a clustering method yields state-of-the-art results without requiring labor-intensive creation of annotated features or knowledge bases or computationally demanding domain-specific pretraining. This study provides a starting point towards investigating deep contextualized language models for biomedical text summarization.
journal_name
Comput Methods Programs Biomedjournal_title
Computer methods and programs in biomedicineauthors
Moradi M,Dorffner G,Samwald Mdoi
10.1016/j.cmpb.2019.105117subject
Has Abstractpub_date
2020-02-01 00:00:00pages
105117eissn
0169-2607issn
1872-7565pii
S0169-2607(19)31137-Xjournal_volume
184pub_type
杂志文章abstract::A personal computer program in BASIC for the two-factor factorial analysis of variance has been developed. The factorial design is based on and combined with previous one-way and two-way ANOVA programs. The performance of the program is tested on data obtained from 3 months' consumption of three proprietary antibiotic...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(93)90072-s
更新日期:1993-12-01 00:00:00
abstract:BACKGROUND:The large intra-patient variability in type 1 diabetic patients dramatically reduces the ability to achieve adequate blood glucose control. A novel methodology to identify different blood glucose dynamics profiles will allow therapies to be more accurate and tailored according to patient's conditions and to ...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2016.08.022
更新日期:2016-11-01 00:00:00
abstract::A flexible program for the IBM PC performing a number of calculations of relevance for the prescription of hemodialysis treatment has been developed. The program has a 'spreadsheet'-like user-friendly interface, and results may be presented graphically. The present implementation covers 89 algorithms/equations, all ba...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(90)90009-x
更新日期:1990-03-01 00:00:00
abstract:BACKGROUND AND OBJECTIVES:Surface rendering and physical models with constant parameters are often employed for cutting procedures in conventional surgical simulators. As a consequence, the internal structures of soft tissues cannot be rendered properly and haptic interaction is unrealistic. In order to improve both th...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2019.105270
更新日期:2020-02-01 00:00:00
abstract:BACKGROUND:Study of nanofluids has been enormously increased for the last couple of years. Regardless of some irregularity in the revealed outcomes and lacking consistency, yet the mechanisms of heat transport have been emerged as highly efficient. In the continuation of nanomaterials research, the investigators and an...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2019.105093
更新日期:2020-01-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:Automatic osteosarcoma tumor segmentation on computed tomography (CT) images is a challenging problem, as tumors have large spatial and structural variabilities. In this study, an automatic tumor segmentation method, which was based on a fully convolutional networks with multiple supervised sid...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2017.02.013
更新日期:2017-05-01 00:00:00
abstract::This paper describes an approach for deriving classification knowledge from databases, taking into account user preferences. These preferences especially concern the trade-off between different kinds of costs and performance indicators of the classification scheme to be developed. We analyze what knowledge, provided b...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(95)01658-g
更新日期:1995-09-01 00:00:00
abstract::Tokyo Hitachi Hospital, Hitachi Ltd., has used a hospital-wide PACS for over 1 year. The system runs a 100 Mb/s optical fiber network over the whole hospital including wards and outpatient clinic rooms, with 11 image workstations. The network links digital imaging modalities such as X-CT, MRI, computed radiography (CR...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(94)90190-2
更新日期:1994-05-01 00:00:00
abstract::This paper introduces temporal logics. Due to the eternal compromise between expressive adequacy and reasoning efficiency that must decided upon in any application, full (first order logic or modal logic based) temporal logics are frequently not suitable. This is especially true in real time expert systems, where a fi...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章,评审
doi:10.1016/0169-2607(96)01761-0
更新日期:1996-10-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:In most countries, the higher death rates are due to cardiovascular disease and stroke. These problems often derive from irregular blood flow and the circulatory system disorder. METHODS:In this paper, the blood flow is simulated in a created aneurysm in the artery upon using Lattice Boltzmann...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2019.105312
更新日期:2020-04-01 00:00:00
abstract::Finite element (FE) analysis is a valuable tool in musculoskeletal research. The demands associated with mesh development, however, often prove daunting. In an effort to facilitate anatomic FE model development we have developed an open-source software toolkit (IA-FEMesh). IA-FEMesh employs a multiblock meshing scheme...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2008.12.003
更新日期:2009-04-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:Complementary and alternative medicine techniques have shown their potential for the treatment and diagnosis of chronical diseases like diabetes, arthritis etc. On the same time digital image processing techniques for disease diagnosis is reliable and fastest growing field in biomedical. Propos...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2018.01.004
更新日期:2018-04-01 00:00:00
abstract::Gaze is a natural input for a Human Computer Interface (HCI) for disabled people, who have of course an acute need for a communication system. An efficient eye tracking procedure is presented providing a non-invasive method for real time detection of a subject eyes in a sequence of frames captured by low cost equipmen...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2009.03.010
更新日期:2009-10-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:In this paper an information theory based multiscale singular value decomposition (SVD) is proposed for multilead electrocardiogram (ECG) signal processing. The shrinkage of singular values for different multivariate multiscale matrices at wavelet scales is based on information content. It aims...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2016.01.010
更新日期:2016-06-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:In the last decade, RNA-sequencing technology has become method-of-choice and prefered to microarray technology for gene expression based classification and differential expression analysis since it produces less noisy data. Although there are many algorithms proposed for microarray data, the n...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2019.04.007
更新日期:2019-07-01 00:00:00
abstract::This research project sought to design and implement a computerized clinical decision support system (CDSS) that was able to identify patients who were at risk of pulmonary embolism (PE) and deep vein thrombosis (DVT), as well as produce reminders for prophylactic action for these diseases. The main purpose of the CDS...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2014.03.007
更新日期:2014-07-01 00:00:00
abstract:BACKGROUND:Over the years, medical image registration has been widely used in various fields. However, different application characteristics, such as scale, computational complexity, and optimization goals, can cause problems. Therefore, developing an optimization algorithm based on clustering calculation is crucial. ...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2020.105432
更新日期:2020-08-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:There is a huge amount of rare diseases, many of which have associated important disabilities. It is paramount to know in advance the evolution of the disease in order to limit and prevent the appearance of disabilities and to prepare the patient to manage the future difficulties. Rare disease ...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2018.07.007
更新日期:2018-10-01 00:00:00
abstract::How to distinguish 1 billion individuals by an identifier consisting of eight characters, allowing a reasonable amount of error detection or even error correction? Our solution of this problem is an optimal code over a 32-character alphabet that detects up to two errors and corrects one error as well as a transpositio...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2005.03.004
更新日期:2005-07-01 00:00:00
abstract::In modern molecular biology, high-throughput experiments allow the simultaneous study of expression levels of thousands of biopolymers such as mRNAs, miRNAs or proteins. A typical goal of such experiments is to find molecular signatures that can distinguish between different types of tissue or that can predict a thera...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2013.05.013
更新日期:2013-09-01 00:00:00
abstract::NONMEM is an extremely powerful tool for nonlinear mixed-effect modelling and simulation of pharmacokinetic and pharmacodynamic data. However, it is a console-based application whose output does not lend itself to rapid interpretation or efficient management. NONMEMory has been created to be a comprehensive project ma...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2005.02.003
更新日期:2005-06-01 00:00:00
abstract:BACKGROUND:The purpose of the study was to probe into the changes in life expectancy associated with schooling years found by the Organization for Economic Co-operation and Development (OECD). METHODS:The study was based on the OECD database from the period 2000 to 2006. The data of thirty countries were constructed t...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2013.11.016
更新日期:2014-03-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:Accurate and fast vessel segmentation from liver slices remain challenging and important tasks for clinicians. The algorithms from the literature are slow and less accurate. We propose fast parallel gradient based seeded region growing for vessel segmentation. Seeded region growing is tedious w...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2020.105430
更新日期:2020-08-01 00:00:00
abstract::This paper describes the use and potential use of mathematical modelling, computer simulation, real-time parameter identification and adaptive feedback control techniques in data-rich clinical environments. We consider a system to be operating in a data-rich environment when measurements of system inputs and outputs a...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(87)90049-6
更新日期:1987-09-01 00:00:00
abstract::The classical approach for extracting event-related potentials (ERPs) from the brain is ensemble averaging. For long latency ERPs this is not optimal, partly due to the time-delay in obtaining a response and partly because the latency and amplitude for the ERP components, like the P300, are variable and depend on cogn...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2009.12.006
更新日期:2010-09-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:Objective Structured Clinical Examination (OSCE) has been used in many areas of healthcare training over the years. However, it constantly needs to be upgraded and enhanced due to technological and teaching changes. We aim at implementing an integrative OSCE method which employs informatics via...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2017.11.006
更新日期:2018-05-01 00:00:00
abstract::Analysis of longitudinal data is one of the most challenging tasks in statistical modeling. In the analysis, it is often necessary to take into account nonlinear response to a set of parameters of interest and correlation between measurements taken from the same individual. In addition, between- and within-subject var...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/s0169-2607(97)00066-7
更新日期:1998-03-01 00:00:00
abstract::In this paper we discuss the SIMID tool for simulation of the spread of infectious disease, enabling spatio-temporal visualization of the dynamics of influenza outbreaks. SIMID is based on modern random network methodology and implemented within the R and GIS frameworks. The key advantage of SIMID is that it allows no...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2013.01.007
更新日期:2013-06-01 00:00:00
abstract::We have developed a new system to produce target movements for our particular purposes using a microcomputer and 9-bit digital-to-analog converter. A continuously changing sinusoidal wave was produced to examine the relationship between the frequencies of target movements and smooth pursuit. A random sinusoidal wave w...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/0169-2607(86)90057-x
更新日期:1986-12-01 00:00:00
abstract:BACKGROUND AND OBJECTIVE:Ever since its discovery, calcium imaging has proven its worth in discovering new insights into the mechanisms of cellular communication. Yet, the analysis of the data generated by calcium imaging experiments demands a large amount of time from researchers. Tools enabling automated and semi-aut...
journal_title:Computer methods and programs in biomedicine
pub_type: 杂志文章
doi:10.1016/j.cmpb.2019.104991
更新日期:2019-10-01 00:00:00