The effects of natural language processing on cross-institutional portability of influenza case detection for disease surveillance

@article{Ferraro2017TheEO,
  title={The effects of natural language processing on cross-institutional portability of influenza case detection for disease surveillance},
  author={Jeffrey P. Ferraro and Ye Ye and Per H. Gesteland and Peter J. Haug and Fuchiang R Tsui and Gregory F. Cooper and Rudy Van Bree and Thomas Ginter and Andrew J. Nowalk and Michael M. Wagner},
  journal={Applied clinical informatics},
  year={2017},
  volume={8 2},
  pages={
          560-580
        }
}
OBJECTIVES This study evaluates the accuracy and portability of a natural language processing (NLP) tool for extracting clinical findings of influenza from clinical notes across two large healthcare systems. Effectiveness is evaluated on how well NLP supports downstream influenza case-detection for disease surveillance. METHODS We independently developed two NLP parsers, one at Intermountain Healthcare (IH) in Utah and the other at University of Pittsburgh Medical Center (UPMC) using local… 

Figures and Tables from this paper

Semantics Enhanced Deep Learning Medical Text Classifier
TLDR
This work incorporates the semantics from ontologies into a loss function of a deep learning text classifier that could enable researchers in clinical settings to embrace and leverage the full potential of clinical NLP tools given the reduced effort required to achieve the desired performance.
Development and Evaluation of a Fully Automated Surveillance System for Influenza-Associated Hospitalization at a Multihospital Health System in Northeast Ohio
TLDR
Surveillance for IAH can be entirely automated at multihospital health systems, saving time, and money while improving case detection.
Detecting Social and Behavioral Determinants of Health with Structured and Free-Text Clinical Data
TLDR
It is suggested that combining clinical free-text notes and structured data provide the best approach in classifying patient SBDH status, which is most challenging among S BDH with low prevalence and high lexical diversity.
Transferability of neural network clinical deidentification systems
TLDR
This article investigates the transferability of a state-of-the-art neural clinical deidentification system, NeuroNER, across a variety of datasets, when it is modified architecturally for domain generalization andWhen it is trained strategically for domain transfer.
Consensus Development of a Modern Ontology of Emergency Department Presenting Problems-The Hierarchical Presenting Problem Ontology (HaPPy).
TLDR
This work presents the HierArchical Presenting Problem ontologY (HaPPy), a polyhierarchical ontology containing 692 unique concepts, 2,118 synonyms, and 30,613 nonvisible descriptions to correct misspellings and nonstandard terminology.
Artificial intelligence and machine learning in emergency medicine: a narrative review
TLDR
This review describes fundamental concepts of machine learning and presents clinical applications for triage, risk stratification specific to disease, medical imaging, and emergency department operations and barriers to safe implementation of AI.
Review helpfulness as a function of Linguistic Indicators
Online reviews are playing an important role in customer’s decision making procedure for buying any product online. As buying products online is becoming customer’s first choice while shopping. It is
Transferability of Neural Network-based De-identification Systems
TLDR
The investigated transferability of neural network-based de-identification sys-tems with and without domain generalization found transferability from a single external source gave inconsistent re-sults, and external sources were useful even in cases where in-domain training data were available.

References

SHOWING 1-10 OF 61 REFERENCES
Evaluating Natural Language Processing Applications Applied to Outbreak and Disease Surveillance
Much of the pre-existing electronic data that could be harnessed for early outbreak detection is in free-text format. Natural language processing (NLP) techniques may be useful to biosurveillance by
Research and applications: Influenza detection from emergency department reports using natural language processing and Bayesian network classifiers
TLDR
Using a three-component evaluation method, this study demonstrated how one could elucidate the relative contributions of components under an integrated framework and encourages researchers to improve NLP accuracy, use a machine-parameterized classifier, and apply feature selection methods.
Natural Language Processing : Can it Help Detect Cases and Characterize Outbreaks ?
TLDR
An error analysis of an NL Pbased ILI case detection application previously applied to the VA textual clinical records is described, which found that free-text processing of clinical no tes brings information about disease symptoms that complements and enhances detection.
Comparison of Natural Language Processing Biosurveillance Methods for Identifying Influenza From Encounter Notes
TLDR
Because case-defining signs and symptoms of influenza are commonly available in health records, the investigators believe that the national strategy for biosurveillance should be changed to incorporate data from the whole health record.
Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions
TLDR
This issue of JAMIA focuses on natural language processing (NLP) techniques for clinical-text information extraction and shared tasks like the i2b2/VA Challenge, a shared-task challenge co-sponsored by the Veteran's Administration for the last 2 years.
Natural Language Processing for Biosurveillance
TLDR
A modest but solid foundation has been laid for natural Language processing of clinical text for the purpose of biosurveillance, with the main focus being on chief complaints.
Detection of Patients with Influenza Syndrome Using Machine-Learning Models Learned from Emergency Department Reports
TLDR
7 machine learning algorithms with an expert constructed Bayesian network on detection of patients with influenza syndrome achieved high AUROC values and EBMC is the best fitted.
Improving performance of natural language processing part-of-speech tagging on clinical narratives through domain adaptation
TLDR
ClinAdapt successfully boosts POS tagging performance through domain adaptation requiring a modest amount of annotated clinical data, to reduce pipeline error propagation leading to better overall results on complex processing tasks.
Using Natural Language Processing on the Free Text of Clinical Documents to Screen for Evidence of Homelessness Among US Veterans
TLDR
An effective and rapid lifecycle of using an off-the-shelf NLP tool for screening targets of interest from medical records is demonstrated.
...
1
2
3
4
5
...