scholarly journals Automatic Extraction of Adverse Drug Reactions from Summary of Product Characteristics

2021 ◽  
Vol 11 (6) ◽  
pp. 2663
Author(s):  
Zhengru Shen ◽  
Marco Spruit
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Adverse Drug Reactions ◽  
Language Processing ◽  
European Medicines Agency ◽  
Drug Reactions ◽  
Clinical Practices ◽  
Product Characteristics ◽  
Textual Information ◽  
Summary Of Product Characteristics

The summary of product characteristics from the European Medicines Agency is a reference document on medicines in the EU. It contains textual information for clinical experts on how to safely use medicines, including adverse drug reactions. Using natural language processing (NLP) techniques to automatically extract adverse drug reactions from such unstructured textual information helps clinical experts to effectively and efficiently use them in daily practices. Such techniques have been developed for Structured Product Labels from the Food and Drug Administration (FDA), but there is no research focusing on extracting from the Summary of Product Characteristics. In this work, we built a natural language processing pipeline that automatically scrapes the summary of product characteristics online and then extracts adverse drug reactions from them. Besides, we have made the method and its output publicly available so that it can be reused and further evaluated in clinical practices. In total, we extracted 32,797 common adverse drug reactions for 647 common medicines scraped from the Electronic Medicines Compendium. A manual review of 37 commonly used medicines has indicated a good performance, with a recall and precision of 0.99 and 0.934, respectively.

scholarly journals Early Detection of Adverse Drug Reactions in Social Health Networks: A Natural Language Processing Pipeline for Signal Detection (Preprint)

2018 ◽  
Author(s):  
Azadeh Nikfarjam ◽  
Julia D Ransohoff ◽  
Alison Callahan ◽  
Erik Jones ◽  
Brian Loew ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Adverse Drug Reactions ◽  
Language Processing ◽  
Signal Generation ◽  
Social Health ◽  
Drug Reactions ◽  
Health Networks ◽  
Health Concerns ◽  
Patient Reports

BACKGROUND Adverse drug reactions (ADRs) occur in nearly all patients on chemotherapy, causing morbidity and therapy disruptions. Detection of such ADRs is limited in clinical trials, which are underpowered to detect rare events. Early recognition of ADRs in the postmarketing phase could substantially reduce morbidity and decrease societal costs. Internet community health forums provide a mechanism for individuals to discuss real-time health concerns and can enable computational detection of ADRs. OBJECTIVE The goal of this study is to identify cutaneous ADR signals in social health networks and compare the frequency and timing of these ADRs to clinical reports in the literature. METHODS We present a natural language processing-based, ADR signal-generation pipeline based on patient posts on Internet social health networks. We identified user posts from the Inspire health forums related to two chemotherapy classes: erlotinib, an epidermal growth factor receptor inhibitor, and nivolumab and pembrolizumab, immune checkpoint inhibitors. We extracted mentions of ADRs from unstructured content of patient posts. We then performed population-level association analyses and time-to-detection analyses. RESULTS Our system detected cutaneous ADRs from patient reports with high precision (0.90) and at frequencies comparable to those documented in the literature but an average of 7 months ahead of their literature reporting. Known ADRs were associated with higher proportional reporting ratios compared to negative controls, demonstrating the robustness of our analyses. Our named entity recognition system achieved a 0.738 microaveraged F-measure in detecting ADR entities, not limited to cutaneous ADRs, in health forum posts. Additionally, we discovered the novel ADR of hypohidrosis reported by 23 patients in erlotinib-related posts; this ADR was absent from 15 years of literature on this medication and we recently reported the finding in a clinical oncology journal. CONCLUSIONS Several hundred million patients report health concerns in social health networks, yet this information is markedly underutilized for pharmacosurveillance. We demonstrated the ability of a natural language processing-based signal-generation pipeline to accurately detect patient reports of ADRs months in advance of literature reporting and the robustness of statistical analyses to validate system detections. Our findings suggest the important contributions that social health network data can play in contributing to more comprehensive and timely pharmacovigilance.

scholarly journals Developing A Deep Learning Natural Language Processing Algorithm For Automated Reporting Of Adverse Drug Reactions

2021 ◽  
Author(s):  
Christopher McMaster ◽  
Julia Chan ◽  
David FL Liew ◽  
Elizabeth Su ◽  
Albert G Frauman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Adverse Events ◽  
Natural Language ◽  
Adverse Drug Reactions ◽  
Language Processing ◽  
Processing Algorithm ◽  
Drug Reactions ◽  
Discharge Summaries ◽  
Natural Language Processing Algorithm

The detection of adverse drug reactions (ADRs) is critical to our understanding of the safety and risk-benefit profile of medications. With an incidence that has not changed over the last 30 years, ADRs are a significant source of patient morbidity, responsible for 5-10% of acute care hospital admissions worldwide. Spontaneous reporting of ADRs has long been the standard method of reporting, however this approach is known to have high rates of under-reporting, a problem that limits pharmacovigilance efforts. Automated ADR reporting presents an alternative pathway to increase reporting rates, although this may be limited by over-reporting of other drug-related adverse events. We developed a deep learning natural language processing algorithm to identify ADRs in discharge summaries at a single academic hospital centre. Our model was developed in two stages: first, a pre-trained model (DeBERTa) was further pre-trained on 150,000 unlabelled discharge summaries; secondly, this model was fine-tuned to detect ADR mentions in a corpus of 861 annotated discharge summaries. To ensure that our algorithm could differentiate ADRs from other drug-related adverse events, the annotated corpus was enriched for both validated ADR reports and confounding drug-related adverse events using. The final model demonstrated good performance with a ROC-AUC of 0.934 (95% CI 0.931 - 0.955) for the task of identifying discharge summaries containing ADR mentions.

An approach to neural network analysis of text information in the economic assessment of companies

2021 ◽  
Vol 20 (8) ◽  
pp. 1574-1594
Author(s):  
Aleksandr R. NEVREDINOV
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Text Analysis ◽  
Economic Assessment ◽  
Management Decision ◽  
Textual Information ◽  
Financial Condition ◽  
Analysis And Synthesis ◽  
Management Decision Making

Subject. When evaluating enterprises, maximum accuracy and comprehensiveness of analysis are important, although the use of various indicators of organization’s financial condition and external factors provide a sufficiently high accuracy of forecasting. Many researchers are increasingly focusing on the natural language processing to analyze various text sources. This subject is extremely relevant against the needs of companies to quickly and extensively analyze their activities. Objectives. The study aims at exploring the natural language processing methods and sources of textual information about companies that can be used in the analysis, and developing an approach to the analysis of textual information. Methods. The study draws on methods of analysis and synthesis, systematization, formalization, comparative analysis, theoretical and methodological provisions contained in domestic and foreign scientific works on text analysis, including for purposes of company evaluation. Results. I offer and test an approach to using non-numeric indicators for company analysis. The paper presents a unique model, which is created on the basis of existing developments that have shown their effectiveness. I also substantiate the use of this approach to analyze a company’s condition and to include the analysis results in models for overall assessment of the state of companies. Conclusions. The findings improve scientific and practical understanding of techniques for the analysis of companies, the ways of applying text analysis, using machine learning. They can be used to support management decision-making to automate the analysis of their own and other companies in the market, with which they interact.

scholarly journals 4349 Survey of Regulatory Reforms to Address Comprehension of Clinical Trial Results

2020 ◽  
Vol 4 (s1) ◽  
pp. 115-115
Author(s):  
Matthieu Kirkland ◽  
Christian Reyes ◽  
Nancy Pire-Smerkanich ◽  
Eunjoo Pacifici
Keyword(s):  
Clinical Trial ◽  
Natural Language Processing ◽  
Natural Language ◽  
Clinical Research ◽  
Language Processing ◽  
Reading Level ◽  
Medical Community ◽  
European Medicines Agency ◽  
Plain Language ◽  
Clinical Trial Results

OBJECTIVES/GOALS: Clinical research is the backbone of the medical community. However, there are few regulations to ensure clinical trial participants can understand their results, leading to volunteers feeling unvalued and unlikely to enroll in trials1. This study examines the need of lay summaries METHODS/STUDY POPULATION: To understand the current landscape of clinical trial summaries, literature searches were conducted using the University of Southern California Library database with keywords Title contains “lay language” OR “lay summary” AND any field contains “Trial” OR “clinical”, and Title contains “natural language processing” AND “clinical trial” OR “Summary”. Studies were deemed relevant if they discussed lay language summaries for health care realms or using Natural Language Processing (NLP) to increase comprehension. Papers published by the Center for Information and Study on Clinical Research Participation (CISCRP) were reviewed and their Associate Director was interviewed. RESULTS/ANTICIPATED RESULTS: Of 67 total results, 14 were determined to be relevant. Ten of the relevant results examined lay language summaries and their regulation and 4 were NLP studies. The European Medicines Agency set regulations mandating clinical trial summaries. However, researchers have difficulty validating to an appropriate reading level2. Difficulty and potential bias halted a U.S. mandate of lay summaries3. The nonprofit CISCRP has partnered with industry to develop unbiased clinical trial summaries resulting in all volunteers feeling appreciated and 91% understanding clinical trial results post summary1. Similarly, NLP software for annotating Electronic Health Records increased comprehension for 77% of patients4. DISCUSSION/SIGNIFICANCE OF IMPACT: In the U.S., a lack of regulations mandating lay summaries may be related to concerns by regulatory agencies that summaries in plain language may introduce bias3. Future looks into integration of NLP systems to clinical trials may create unbiased summaries and allow for FDA regulation.

scholarly journals Natural Language Processing Combined with ICD-9-CM Codes as a Novel Method to Study the Epidemiology of Allergic Drug Reactions

2020 ◽  
Vol 8 (3) ◽  
pp. 1032-1038.e1 ◽  
Author(s):  
Aleena Banerji ◽  
Kenneth H. Lai ◽  
Yu Li ◽  
Rebecca R. Saff ◽  
Carlos A. Camargo ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Drug Reactions ◽  
Novel Method
Sign in / Sign up

Export Citation Format

Share Document