Dataset Information

Mining FDA drug labels using an unsupervised learning technique--topic modeling.

ABSTRACT: BACKGROUND: The Food and Drug Administration (FDA) approved drug labels contain a broad array of information, ranging from adverse drug reactions (ADRs) to drug efficacy, risk-benefit consideration, and more. However, the labeling language used to describe these information is free text often containing ambiguous semantic descriptions, which poses a great challenge in retrieving useful information from the labeling text in a consistent and accurate fashion for comparative analysis across drugs. Consequently, this task has largely relied on the manual reading of the full text by experts, which is time consuming and labor intensive. METHOD: In this study, a novel text mining method with unsupervised learning in nature, called topic modeling, was applied to the drug labeling with a goal of discovering "topics" that group drugs with similar safety concerns and/or therapeutic uses together. A total of 794 FDA-approved drug labels were used in this study. First, the three labeling sections (i.e., Boxed Warning, Warnings and Precautions, Adverse Reactions) of each drug label were processed by the Medical Dictionary for Regulatory Activities (MedDRA) to convert the free text of each label to the standard ADR terms. Next, the topic modeling approach with latent Dirichlet allocation (LDA) was applied to generate 100 topics, each associated with a set of drugs grouped together based on the probability analysis. Lastly, the efficacy of the topic modeling was evaluated based on known information about the therapeutic uses and safety data of drugs. RESULTS: The results demonstrate that drugs grouped by topics are associated with the same safety concerns and/or therapeutic uses with statistical significance (P<0.05). The identified topics have distinct context that can be directly linked to specific adverse events (e.g., liver injury or kidney injury) or therapeutic application (e.g., antiinfectives for systemic use). We were also able to identify potential adverse events that might arise from specific medications via topics. CONCLUSIONS: The successful application of topic modeling on the FDA drug labeling demonstrates its potential utility as a hypothesis generation means to infer hidden relationships of concepts such as, in this study, drug safety and therapeutic use in the study of biomedical documents.

SUBMITTER: Bisgin H

PROVIDER: S-EPMC3236833 | biostudies-other | 2011

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Mining FDA drug labels using an unsupervised learning technique--topic modeling.

Bisgin Halil H Liu Zhichao Z Fang Hong H Xu Xiaowei X Tong Weida W

BMC bioinformatics 20111018

<h4>Background</h4>The Food and Drug Administration (FDA) approved drug labels contain a broad array of information, ranging from adverse drug reactions (ADRs) to drug efficacy, risk-benefit consideration, and more. However, the labeling language used to describe these information is free text often containing ambiguous semantic descriptions, which poses a great challenge in retrieving useful information from the labeling text in a consistent and accurate fashion for comparative analysis across ...[more]

PMID: 22166012

Similar Datasets

Project description:Background: Since the World Health Organization (WHO) declared the COVID-19 as a Public Health Emergency of International Concern (PHEIC) on January 31, 2020, governments have been enfaced with crisis for timely responses. The efficacy of these responses directly depends on the social behaviors of the target society. People react to these actions with respect to the information they received from different channels, such as news and social networks. Thus, analyzing news demonstrates a brief view of the information users received during the outbreak.Methods: The raw data used in this study is collected from official news channels of news wires and agencies in Telegram messenger, which exceeds 2,400,000 posts. The posts that are quoted by NCRC's members are collected, cleaned, and divided into sentences. The topic modeling and tracking are utilized in a two-stage framework, which is customized for this problem to separate miscellaneous sentences from those presenting concerns. The first stage is fed with embedding vectors of sentences where they are grouped by the Mapper algorithm. Sentences belonging to singleton nodes are labeled as miscellaneous sentences. The remained sentences are vectorized, adopting Tf-IDF weighting schema in the second stage and topically modeled by the LDA method. Finally, relevant topics are aligned to the list of policies and actions, named topic themes, that are set up by the NCRC.Results: Our results show that major concerns presented in about half of the sentences are (1) PCR lab. test, diagnosis, and screening, (2) Closure of the education system, and (3) awareness actions about washing hands and facial mask usage. Among the eight themes, intra-provincial travel and traffic restrictions, as well as briefing the national and provincial status, are under-presented. The timeline of concerns annotated by the preventive actions illustrates the changes in concerns addressed by NCRC. This timeline shows that although the announcements and public responses are not lagged behind the events, but cannot be considered as timely. Furthermore, the fluctuating series of concerns reveal that the NCRC has not a long-time response map, and members react to the closest announced policy/act.Conclusion: The results of our study can be used as a quantitative indicator for evaluating the availability of an on-time public response of Iran's NCRC during the first three months of the outbreak. Moreover, it can be used in comparative studies to investigate the differences between awareness acts in various countries. Results of our customized-design framework showed that about one-third of the discussions of the NCRC's members cover miscellaneous topics that must be removed from the data.

Project description:BackgroundGiven the significant impact on public health and drug development, drug safety has been a focal point and research emphasis across multiple disciplines in addition to scientific investigation, including consumer advocates, drug developers and regulators. Such a concern and effort has led numerous databases with drug safety information available in the public domain and the majority of them contain substantial textual data. Text mining offers an opportunity to leverage the hidden knowledge within these textual data for the enhanced understanding of drug safety and thus improving public health.MethodsIn this proof-of-concept study, topic modeling, an unsupervised text mining approach, was performed on the LiverTox database developed by National Institutes of Health (NIH). The LiverTox structured one document per drug that contains multiple sections summarizing clinical information on drug-induced liver injury (DILI). We hypothesized that these documents might contain specific textual patterns that could be used to address key DILI issues. We placed the study on drug-induced acute liver failure (ALF) which was a severe form of DILI with limited treatment options.ResultsAfter topic modeling of the "Hepatotoxicity" sections of the LiverTox across 478 drug documents, we identified a hidden topic relevant to Hy's law that was a widely-accepted rule incriminating drugs with high risk of causing ALF in humans. Using this topic, a total of 127 drugs were further implicated, 77 of which had clear ALF relevant terms in the "Outcome and management" sections of the LiverTox. For the rest of 50 drugs, evidence supporting risk of ALF was found for 42 drugs from other public databases.ConclusionIn this case study, the knowledge buried in the textual data was extracted for identification of drugs with potential of causing ALF by applying topic modeling to the LiverTox database. The knowledge further guided identification of drugs with the similar potential and most of them could be verified and confirmed. This study highlights the utility of topic modeling to leverage information within textual drug safety databases, which provides new opportunities in the big data era to assess drug safety.

Project description:PurposeImage quality of positron emission tomography (PET) is limited by various physical degradation factors. Our study aims to perform PET image denoising by utilizing prior information from the same patient. The proposed method is based on unsupervised deep learning, where no training pairs are needed.MethodsIn this method, the prior high-quality image from the patient was employed as the network input and the noisy PET image itself was treated as the training label. Constrained by the network structure and the prior image input, the network was trained to learn the intrinsic structure information from the noisy image and output a restored PET image. To validate the performance of the proposed method, a computer simulation study based on the BrainWeb phantom was first performed. A 68Ga-PRGD2 PET/CT dataset containing 10 patients and a 18F-FDG PET/MR dataset containing 30 patients were later on used for clinical data evaluation. The Gaussian, non-local mean (NLM) using CT/MR image as priors, BM4D, and Deep Decoder methods were included as reference methods. The contrast-to-noise ratio (CNR) improvements were used to rank different methods based on Wilcoxon signed-rank test.ResultsFor the simulation study, contrast recovery coefficient (CRC) vs. standard deviation (STD) curves showed that the proposed method achieved the best performance regarding the bias-variance tradeoff. For the clinical PET/CT dataset, the proposed method achieved the highest CNR improvement ratio (53.35% ± 21.78%), compared with the Gaussian (12.64% ± 6.15%, P = 0.002), NLM guided by CT (24.35% ± 16.30%, P = 0.002), BM4D (38.31% ± 20.26%, P = 0.002), and Deep Decoder (41.67% ± 22.28%, P = 0.002) methods. For the clinical PET/MR dataset, the CNR improvement ratio of the proposed method achieved 46.80% ± 25.23%, higher than the Gaussian (18.16% ± 10.02%, P < 0.0001), NLM guided by MR (25.36% ± 19.48%, P < 0.0001), BM4D (37.02% ± 21.38%, P < 0.0001), and Deep Decoder (30.03% ± 20.64%, P < 0.0001) methods. Restored images for all the datasets demonstrate that the proposed method can effectively smooth out the noise while recovering image details.ConclusionThe proposed unsupervised deep learning framework provides excellent image restoration effects, outperforming the Gaussian, NLM methods, BM4D, and Deep Decoder methods.

Dataset Information

Mining FDA drug labels using an unsupervised learning technique--topic modeling.

Publications

Mining FDA drug labels using an unsupervised learning technique--topic modeling.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets