Can Natural Language Processing Improve the Efficiency of Vaccine Adverse Event Report Review?

Tasks as needs: reframing the paradigm of clinical natural language processing research for real-world decision support

Electronic medical records are increasingly used to store patient information in hospitals and other clinical settings. There has been a corresponding proliferation of clinical natural language processing (cNLP) systems aimed at using text data in these records to improve clinical decision-making, in comparison to manual clinician search and clinical judgment alone. However, these systems have delivered marginal practical utility and are rarely deployed into healthcare settings, leading to proposals for technical and structural improvements. In this paper, we argue that this reflects a violation of Friedman's "Fundamental Theorem of Biomedical Informatics," and that a deeper epistemological change must occur in the cNLP field, as a parallel step alongside any technical or structural improvements. We propose that researchers shift away from designing cNLP systems independent of clinical needs, in which cNLP tasks are ends in themselves-"tasks as decisions"-and toward systems that are directly guided by the needs of clinicians in realistic decision-making contexts-"tasks as needs." A case study example illustrates the potential benefits of developing cNLP systems that are designed to more directly support clinical needs.

"Artificial Intelligence" for Pharmacovigilance: Ready for Prime Time?

There is great interest in the application of 'artificial intelligence' (AI) to pharmacovigilance (PV). Although US FDA is broadly exploring the use of AI for PV, we focus on the application of AI to the processing and evaluation of Individual Case Safety Reports (ICSRs) submitted to the FDA Adverse Event Reporting System (FAERS). We describe a general framework for considering the readiness of AI for PV, followed by some examples of the application of AI to ICSR processing and evaluation in industry and FDA. We conclude that AI can usefully be applied to some aspects of ICSR processing and evaluation, but the performance of current AI algorithms requires a 'human-in-the-loop' to ensure good quality. We identify outstanding scientific and policy issues to be addressed before the full potential of AI can be exploited for ICSR processing and evaluation, including approaches to quality assurance of 'human-in-the-loop' AI systems, large-scale, publicly available training datasets, a well-defined and computable 'cognitive framework', a formal sociotechnical framework for applying AI to PV, and development of best practices for applying AI to PV. Practical experience with stepwise implementation of AI for ICSR processing and evaluation will likely provide important lessons that will inform the necessary policy and regulatory framework to facilitate widespread adoption and provide a foundation for further development of AI approaches to other aspects of PV.

A Machine Learning-based Method for Question Type Classification in Biomedical Question Answering

Background and Objective: Biomedical question type classification is one of the important components of an automatic biomedical question answering system. The performance of the latter depends directly on the performance of its biomedical question type classification system, which consists of assigning a category to each question in order to determine the appropriate answer extraction algorithm. This study aims to automatically classify biomedical questions into one of the four categories: (1) yes/no, (2) factoid, (3) list, and (4) summary.

Methods: In this paper, we propose a biomedical question type classification method based on machine learning approaches to automatically assign a category to a biomedical question. First, we extract features from biomedical questions using the proposed handcrafted lexico-syntactic patterns. Then, we feed these features for machine- learning algorithms. Finally, the class label is predicted using the trained classifiers.

Results: Experimental evaluations performed on large standard annotated datasets of biomedical questions, provided by the BioASQ challenge, demonstrated that our method exhibits significant improved performance when compared to four baseline systems. The proposed method achieves a roughly 10-point increase over the best baseline in terms of accuracy. Moreover, the obtained results show that using handcrafted lexico-syntactic patterns as features’ provider of support vector machine (SVM) lead to the highest accuracy of 89.40%.

Conclusion: The proposed method can automatically classify BioASQ questions into one of the four categories: yes/no, factoid, list, and summary. Furthermore, the results demonstrated that our method produced the best classification performance compared to four baseline systems.

Development of an automated assessment tool for MedWatch reports in the FDA adverse event reporting system

Objective

As the US Food and Drug Administration (FDA) receives over a million adverse event reports associated with medication use every year, a system is needed to aid FDA safety evaluators in identifying reports most likely to demonstrate causal relationships to the suspect medications. We combined text mining with machine learning to construct and evaluate such a system to identify medication-related adverse event reports.

Methods

FDA safety evaluators assessed 326 reports for medication-related causality. We engineered features from these reports and constructed random forest, L1 regularized logistic regression, and support vector machine models. We evaluated model accuracy and further assessed utility by generating report rankings that represented a prioritized report review process.

Results

Our random forest model showed the best performance in report ranking and accuracy, with an area under the receiver operating characteristic curve of 0.66. The generated report ordering assigns reports with a higher probability of medication-related causality a higher rank and is significantly correlated to a perfect report ordering, with a Kendall's tau of 0.24 ( P  = .002).

Conclusion

Our models produced prioritized report orderings that enable FDA safety evaluators to focus on reports that are more likely to contain valuable medication-related adverse event information. Applying our models to all FDA adverse event reports has the potential to streamline the manual review process and greatly reduce reviewer workload.

Clinical information extraction applications: A literature review

BACKGROUND

With the rapid adoption of electronic health records (EHRs), it is desirable to harvest information and knowledge from EHRs to support automated systems at the point of care and to enable secondary use of EHRs for clinical and translational research. One critical component used to facilitate the secondary use of EHR data is the information extraction (IE) task, which automatically extracts and encodes clinical information from text.

OBJECTIVES

In this literature review, we present a review of recent published research on clinical information extraction (IE) applications.

METHODS

A literature search was conducted for articles published from January 2009 to September 2016 based on Ovid MEDLINE In-Process & Other Non-Indexed Citations, Ovid MEDLINE, Ovid EMBASE, Scopus, Web of Science, and ACM Digital Library.

RESULTS

A total of 1917 publications were identified for title and abstract screening. Of these publications, 263 articles were selected and discussed in this review in terms of publication venues and data sources, clinical IE tools, methods, and applications in the areas of disease- and drug-related studies, and clinical workflow optimizations.

CONCLUSIONS

Clinical IE has been used for a wide range of applications, however, there is a considerable gap between clinical studies using EHR data and studies using clinical IE. This study enabled us to gain a more concrete understanding of the gap and to provide potential solutions to bridge this gap.