Adverse Drug Event Reporting

Edlavitch, Stanley A.

doi:10.1001/archinte.1988.00380070017005

Cited by 33 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In postmarketing surveillance, ADEs are discovered by patients and physicians using the Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). These traditional methods are limited by the number of participants [10], underreporting [11], and missing patterns of drug exposure [12]; for example, underreporting is a known issue in FAERS and may occur due to several reasons. First, the objective and content of the report in FAERS change over time, which may confuse physicians and the general public.…”

Section: Introductionmentioning

confidence: 99%

Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning

Li¹,

Liu²,

Yu³

2018

JMIR Med Inform

View full text Add to dashboard Cite

BackgroundPharmacovigilance and drug-safety surveillance are crucial for monitoring adverse drug events (ADEs), but the main ADE-reporting systems such as Food and Drug Administration Adverse Event Reporting System face challenges such as underreporting. Therefore, as complementary surveillance, data on ADEs are extracted from electronic health record (EHR) notes via natural language processing (NLP). As NLP develops, many up-to-date machine-learning techniques are introduced in this field, such as deep learning and multi-task learning (MTL). However, only a few studies have focused on employing such techniques to extract ADEs.ObjectiveWe aimed to design a deep learning model for extracting ADEs and related information such as medications and indications. Since extraction of ADE-related information includes two steps—named entity recognition and relation extraction—our second objective was to improve the deep learning model using multi-task learning between the two steps.MethodsWe employed the dataset from the Medication, Indication and Adverse Drug Events (MADE) 1.0 challenge to train and test our models. This dataset consists of 1089 EHR notes of cancer patients and includes 9 entity types such as Medication, Indication, and ADE and 7 types of relations between these entities. To extract information from the dataset, we proposed a deep-learning model that uses a bidirectional long short-term memory (BiLSTM) conditional random field network to recognize entities and a BiLSTM-Attention network to extract relations. To further improve the deep-learning model, we employed three typical MTL methods, namely, hard parameter sharing, parameter regularization, and task relation learning, to build three MTL models, called HardMTL, RegMTL, and LearnMTL, respectively.ResultsSince extraction of ADE-related information is a two-step task, the result of the second step (ie, relation extraction) was used to compare all models. We used microaveraged precision, recall, and F1 as evaluation metrics. Our deep learning model achieved state-of-the-art results (F1=65.9%), which is significantly higher than that (F1=61.7%) of the best system in the MADE1.0 challenge. HardMTL further improved the F1 by 0.8%, boosting the F1 to 66.7%, whereas RegMTL and LearnMTL failed to boost the performance.ConclusionsDeep learning models can significantly improve the performance of ADE-related information extraction. MTL may be effective for named entity recognition and relation extraction, but it depends on the methods, data, and other factors. Our results can facilitate research on ADE detection, NLP, and machine learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning

Li¹,

Liu²,

Yu³

2018

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

Computerized Surveillance of Adverse Drug Events in Hospital Patients

Classen¹

1991

JAMA

495

203

View full text Add to dashboard Cite

Objective: To develop a new method to improve the detection and characterization of adverse drug events (ADEs) in hospital patients. Design: Prospective study of all patients admitted to our hospital over an 18 month period. Setting: LDS Hospital, Salt Lake City, Utah, a 520-bed tertiary care center affiliated with the University of Utah School of Medicine, Salt Lake City. Patients: We developed a computerized ADE monitor, and computer programs were written using an integrated hospital information system to allow for multiple source detection of potential ADEs occurring in hospital patients. Signals of potential ADEs, both voluntary and automated, included sudden medication stop orders, antidote ordering, and certain abnormal laboratory values. Each day a list of all potential ADEs from these sources was generated, and a pharmacist reviewed the medical records of all patients with possible ADEs for accuracy and causality. Verified ADEs were characterized as mild, moderate, or severe and as type A (dose-dependent or predictable) or type B (idiosyncratic or allergic) reactions, and causality was further measured using a standardized scoring method. Outcome measure: The number and characterization of ADEs detected. Results: Over 18 months we monitored 36 653 hospitalized patients. There were 731 verified ADEs identified in 648 patients, 701 ADEs were characterized as moderate or severe, and 664 were classified as type A reactions. During this same period only nine ADEs were identified using traditional detection methods. Physicians, pharmacists, and nurses voluntarily reported 92 of the 731 ADEs detected using this automated system. The other 631 ADEs were detected from automated signals, the most common of which were diphenhydramine hydrochloride and naloxone hydrochloride use, high serum drug levels, leukopenia, and the use of phytonadione and antidiarrheals. The most common symptoms and signs were pruritus, nausea and/or vomiting, rash, and confusion-lethargy. The most common drug classes involved were analgesics, anti-infectives, and cardiovascular agents. Conclusion: We believe that screening for ADEs with a computerized hospital information system offers a potential method for improving the detection and characterization of these events in hospital patients.

show abstract

The Safety of Medical Products

Fletcher

Shaw²

2005

The Textbook of Pharmaceutical Medicine

View full text Add to dashboard Cite

Adverse Drug Event Reporting

Cited by 33 publications

References 12 publications

Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning

Extraction of Information Related to Adverse Drug Events from Electronic Health Record Notes: Design of an End-to-End Model Based on Deep Learning

Computerized Surveillance of Adverse Drug Events in Hospital Patients

The Safety of Medical Products

Contact Info

Product

Resources

About