21 |
NUIG at EmoInt-2017: BiLSTM and SVR ensemble to detect emotion intensity
|
|
|
|
BASE
|
|
Show details
|
|
22 |
El uso de tú y usted en el área metropolitana de Valencia. Un enfoque variacionista ; The use of tú y usted in the metropolitan area of Valencia. A variationist approach
|
|
Roselló Verdeguer, Jorge. - : Universidad de Alicante. Departamento de Filología Española, Lingüística General y Teoría de la Literatura, 2017
|
|
BASE
|
|
Show details
|
|
24 |
LINGUISTIC PARAMETERS OF THE CONCEPTS LIST AND CATALOG: LANGUAGE PROCESSING VERSION FOR COMPUTER SYSTEMS
|
|
NOSOV ANDREY V.. - : Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования «Пермский государственный национальный исследовательский университет», 2016
|
|
BASE
|
|
Show details
|
|
25 |
Comparing C-tests and Yes/No vocabulary size tests as predictors of receptive language skills
|
|
|
|
In: Language testing 33 (2016) 4, S. 555-575 (2016)
|
|
BASE
|
|
Show details
|
|
26 |
Frequency and predictability effects on event-related potentials during reading
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Conducting sparse feature selection on arbitrarily long phrases in text corpora with a focus on interpretability
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Untangling synchronic and diachronic variation : verb agreement in Palmerston English
|
|
|
|
BASE
|
|
Show details
|
|
30 |
Short persistent sleep duration is associated with poor receptive vocabulary performance in middle childhood
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Analysis of categorical response data: Use logistic regression rather than endpoint-difference scores of discriminant analysis (L)
|
|
|
|
In: Journal of the Acoustical Society of America (2015)
|
|
BASE
|
|
Show details
|
|
32 |
Efficient and sparse feature selection for biomedical text classification via the elastic net: Application to ICU risk stratification from nursing notes.
|
|
|
|
Abstract:
Sparsity is often a desirable property of statistical models, and various feature selection methods exist so as to yield sparser and interpretable models. However, their application to biomedical text classification, particularly to mortality risk stratification among intensive care unit (ICU) patients, has not been thoroughly studied.To develop and characterize sparse classifiers based on the free text of nursing notes in order to predict ICU mortality risk and to discover text features most strongly associated with mortality.We selected nursing notes from the first 24h of ICU admission for 25,826 adult ICU patients from the MIMIC-II database. We then developed a pair of stochastic gradient descent-based classifiers with elastic-net regularization. We also studied the performance-sparsity tradeoffs of both classifiers as their regularization parameters were varied.The best-performing classifier achieved a 10-fold cross-validated AUC of 0.897 under the log loss function and full L2 regularization, while full L1 regularization used just 0.00025% of candidate input features and resulted in an AUC of 0.889. Using the log loss (range of AUCs 0.889-0.897) yielded better performance compared to the hinge loss (0.850-0.876), but the latter yielded even sparser models.Most features selected by both classifiers appear clinically relevant and correspond to predictors already present in existing ICU mortality models. The sparser classifiers were also able to discover a number of informative - albeit nonclinical - features.The elastic-net-regularized classifiers perform reasonably well and are capable of reducing the number of features required by over a thousandfold, with only a modest impact on performance.
|
|
Keyword:
Biological Sciences; Biomedical Engineering; Data Mining; Elastic net; Electronic Health Records; Feature selection; Humans; ICU; Information and Computing Sciences; Intensive Care Units; Machine learning; Medical and Health Sciences; Medical Informatics; Medical Informatics Applications; Nurses; Regression Analysis; Risk Assessment; Risk stratification; Text mining
|
|
URL: https://escholarship.org/uc/item/91f5766j
|
|
BASE
|
|
Hide details
|
|
33 |
An empirical estimate of the precision of likelihood ratios from a forensic-voice-comparison system
|
|
|
|
In: Forensic Science International (2015)
|
|
BASE
|
|
Show details
|
|
34 |
Factors Underlying Attitude towards Agriculture as Predictors of Willingness to Enrol in the Subject by Senior Secondary Students in Botswana
|
|
|
|
In: http://mcser.org/journal/index.php/jesr/article/viewFile/5632/5435/ (2015)
|
|
BASE
|
|
Show details
|
|
35 |
Creating A Framework For Success For High School African American Males: A Policy Advocacy Document
|
|
|
|
In: Dissertations (2015)
|
|
BASE
|
|
Show details
|
|
36 |
Differentiation of competence and affect self-perceptions in elementary school students. Extending empirical evidence ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Aspects of speech-language abilities are influenced by MECP2 mutation type in girls with Rett syndrome
|
|
|
|
In: Research outputs 2014 to 2021 (2015)
|
|
BASE
|
|
Show details
|
|
38 |
A decade of evolving composites: regression- and meta-analysis
|
|
|
|
BASE
|
|
Show details
|
|
39 |
Comparing C-tests and Yes/No vocabulary size tests as predictors of receptive language skills
|
|
|
|
In: Language testing (2015), S. 1-21 (2015)
|
|
BASE
|
|
Show details
|
|
40 |
Differentiation of competence and affect self-perceptions in elementary school students. Extending empirical evidence
|
|
|
|
In: European journal of psychology of education 30 (2015) 4, S. 405-419 (2015)
|
|
BASE
|
|
Show details
|
|
|
|