Prediction of adverse drug reactions based on knowledge graph embedding

Abstract Background Adverse drug reactions (ADRs) are an important concern in the medication process and can pose a substantial economic burden for patients and hospitals. Because of the limitations of clinical trials, it is difficult to identify all possible ADRs of a drug before it is marketed. We developed a new model based on data mining technology to predict potential ADRs based on available drug data. Method Based on the Word2Vec model in Nature Language Processing, we propose a new knowledge graph embedding method that embeds drugs and ADRs into their respective vectors and builds a logistic regression classification model to predict whether a given drug will have ADRs. Result First, a new knowledge graph embedding method was proposed, and comparison with similar studies showed that our model not only had high prediction accuracy but also was simpler in model structure. In our experiments, the AUC of the classification model reached a maximum of 0.87, and the mean AUC was 0.863. Conclusion In this paper, we introduce a new method to embed knowledge graph to vectorize drugs and ADRs, then use a logistic regression classification model to predict whether there is a causal relationship between them. The experiment showed that the use of knowledge graph embedding can effectively encode drugs and ADRs. And the proposed ADRs prediction system is also very effective.

Download Full-text

Automatic Extraction of Adverse Drug Reactions from Summary of Product Characteristics

Applied Sciences ◽

10.3390/app11062663 ◽

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.

Download Full-text

Effects of the number of drugs used on the prevalence of adverse drug reactions in children

Scientific Reports ◽

10.1038/s41598-020-78358-3 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Mayuko Sugioka ◽

Tomoya Tachi ◽

Takashi Mizui ◽

Aisa Koyama ◽

Azusa Murayama ◽

...

Keyword(s):

Logistic Regression ◽

Adverse Drug Reactions ◽

Multiple Logistic Regression Analysis ◽

Circulatory System ◽

Control Measures ◽

Medical Attention ◽

Concomitant Disease ◽

Multiple Logistic Regression ◽

Drug Reactions ◽

Circulatory System Diseases

AbstractIn pediatric individuals, polypharmacy would increase the prevalence of adverse drug reactions (ADRs). However, there is no report on the ADR increase adjusted for the influence of concomitant disease types. We conducted a retrospective study in pediatric patients to determine whether polypharmacy is a risk factor for ADR development, after the adjustment. Patients aged 1–14 years on medication who visited Gifu Municipal Hospital (Gifu, Japan) were included. We evaluated patient characteristics, ADR causality, ADR classification and severity, and ADR-causing drugs. We examined the association between ADR prevalence and number of drugs used. We performed multiple logistic regression analyses to investigate risk factors for ADR development. Of 1330 patients, 3.5% sought medical attention for ADRs. ADR causality was most often assessed as “possible,” with gastrointestinal ADRs being the most common. Grade 1 ADRs were the most and antibiotics were the most common suspected ADR-inducing drug. The multiple logistic regression analysis showed that ≥ 2 or ≥ 4 drug use, neoplasms, mental and behavioral disorders, and circulatory system diseases significantly increased ADR prevalence. Polypharmacy increased the prevalence of ADR resulting in hospital visits in children, after adjusting for the influence of disease types. Therefore, proactive polypharmacy control measures are necessary for children.

Download Full-text

Bayesian model selection in logistic regression for the detection of adverse drug reactions

Biometrical Journal ◽

10.1002/bimj.201500098 ◽

2016 ◽

Vol 58 (6) ◽

pp. 1376-1389 ◽

Cited By ~ 2

Author(s):

Matthieu Marbac ◽

Pascale Tubert-Bitter ◽

Mohammed Sedki

Keyword(s):

Logistic Regression ◽

Model Selection ◽

Adverse Drug Reactions ◽

Bayesian Model ◽

Bayesian Model Selection ◽

Drug Reactions

Download Full-text

Author Correction: Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records

Scientific Reports ◽

10.1038/s41598-018-22521-4 ◽

2018 ◽

Vol 8 (1) ◽

Author(s):

Daniel M. Bean ◽

Honghan Wu ◽

Ehtesham Iqbal ◽

Olubanke Dzahini ◽

Zina M. Ibrahim ◽

...

Keyword(s):

Electronic Health Records ◽

Adverse Drug Reactions ◽

Knowledge Graph ◽

Drug Reactions ◽

Health Records ◽

Electronic Health

Download Full-text

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

10.2196/preprints.11264 ◽

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.

Download Full-text

An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding

Applied Sciences ◽

10.3390/app10082651 ◽

2020 ◽

Vol 10 (8) ◽

pp. 2651

Author(s):

Su Jeong Choi ◽

Hyun-Je Song ◽

Seong-Bae Park

Keyword(s):

Knowledge Base ◽

Language Processing ◽

Graph Embedding ◽

Knowledge Bases ◽

Knowledge Graph ◽

Data Sets ◽

Complete Knowledge ◽

Proposed Model ◽

Ranking Task ◽

Low Dimensional

Knowledge bases such as Freebase, YAGO, DBPedia, and Nell contain a number of facts with various entities and relations. Since they store many facts, they are regarded as core resources for many natural language processing tasks. Nevertheless, they are not normally complete and have many missing facts. Such missing facts keep them from being used in diverse applications in spite of their usefulness. Therefore, it is significant to complete knowledge bases. Knowledge graph embedding is one of the promising approaches to completing a knowledge base and thus many variants of knowledge graph embedding have been proposed. It maps all entities and relations in knowledge base onto a low dimensional vector space. Then, candidate facts that are plausible in the space are determined as missing facts. However, any single knowledge graph embedding is insufficient to complete a knowledge base. As a solution to this problem, this paper defines knowledge base completion as a ranking task and proposes a committee-based knowledge graph embedding model for improving the performance of knowledge base completion. Since each knowledge graph embedding has its own idiosyncrasy, we make up a committee of various knowledge graph embeddings to reflect various perspectives. After ranking all candidate facts according to their plausibility computed by the committee, the top-k facts are chosen as missing facts. Our experimental results on two data sets show that the proposed model achieves higher performance than any single knowledge graph embedding and shows robust performances regardless of k. These results prove that the proposed model considers various perspectives in measuring the plausibility of candidate facts.

Download Full-text

Development and validation of a clinical instrument to predict risk of an adverse drug reactions in hospitalized patients

PLoS ONE ◽

10.1371/journal.pone.0243714 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0243714

Author(s):

Sara Iasmin Vieira Cunha Lima ◽

Rand Randall Martins ◽

Valdjane Saldanha ◽

Vivian Nogueira Silbiger ◽

Isabelle Cristina Clemente dos Santos ◽

...

Keyword(s):

Blood Pressure ◽

Logistic Regression ◽

Adverse Drug Reactions ◽

Past History ◽

Conditional Logistic Regression ◽

Hospitalized Patients ◽

Main Diagnosis ◽

Drug Reactions ◽

Clinical Tool ◽

Drugs Prescription

Objective Development and internal validation of a clinical tool for assessment of the risk of adverse drug reactions (ADR) in hospitalized patients. Methodology Nested case-control study in an open cohort of all patients admitted to a general hospital. Cases of ADR were matched to two controls. Eighty four patient variables collected at the time of the ADR were analyzed by conditional logistic regression. Multivariate logistic regression with clustering of cases in a random sample of 2/3 of the cases and respective controls, with baseline odds-ratio corrected with an estimate of ADR incidence, was used to obtain regression coefficients for each risk factor and to develop a risk score. The clinical tool was validated in the remaining 1/3 observations. The study was approved by the institution’s research ethics committee. Results In the 8060 hospitalized patients, ADR occurred in 343 (5.31%), who were matched to 686 controls. Fourteen variables were identified as independent risk factors of ADR: female, past history of ADR, heart rate ≥72 bpm, systolic blood pressure≥148 mmHg, diastolic blood pressure <79 mmHg, diabetes mellitus, serum urea ≥ 67 mg/dL, serum sodium ≥141 mmol/L, serum potassium ≥4.9 mmol/L, main diagnosis of neoplasia, prescription of ≥3 ATC class B drugs, prescription of ATC class R drugs, prescription of intravenous drugs and ≥ 6 oral drugs. In the validation sample, the ADR risk tool based on those variables showed sensitivity 61%, specificity 73% and area under the ROC curve 0.73. Conclusion We report a clinical tool for ADR risk stratification in patients hospitalized in general wards based on 14 variables.

Download Full-text

TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/268 ◽

2019 ◽

Cited By ~ 9

Author(s):

Shihui Yang ◽

Jidong Tian ◽

Honglun Zhang ◽

Junchi Yan ◽

Hao He ◽

...

Keyword(s):

Large Scale ◽

State Of The Art ◽

Graph Embedding ◽

Knowledge Graph ◽

Additional Parameter ◽

Nonlinear Functions ◽

Embedding Method ◽

Low Dimension

Knowledge graph embedding, which projects the symbolic relations and entities onto low-dimension continuous spaces, is essential to knowledge graph completion. Recently, translation-based embedding models (e.g. TransE) have aroused increasing attention for their simplicity and effectiveness. These models attempt to translate semantics from head entities to tail entities with the relations and infer richer facts outside the knowledge graph. In this paper, we propose a novel knowledge graph embedding method named TransMS, which translates and transmits multidirectional semantics: i) the semantics of head/tail entities and relations to tail/head entities with nonlinear functions and ii) the semantics from entities to relations with linear bias vectors. Our model has merely one additional parameter α than TransE for each triplet, which results in its better scalability in large-scale knowledge graph. Experiments show that TransMS achieves substantial improvements against state-of-the-art baselines, especially the Hit@10s of head entity prediction for N-1 relations and tail entity prediction for 1-N relations improved by about 27.1% and 24.8% on FB15K database respectively.

Download Full-text

Tenofovir Based First Line Therapy in Newly Diagnosed Case of HIV Infection: An Experience from a Tertiary Care Hospital in India

10.21203/rs.3.rs-31873/v1 ◽

2020 ◽

Author(s):

Arkapal Bandyopadhyay ◽

Sarika Palepu ◽

Bhavna Saini ◽

Rakesh Chandra Chaurasia ◽

Rakesh Kumar Yadav

Keyword(s):

Logistic Regression ◽

Hiv Infection ◽

Adverse Drug Reactions ◽

Cd4 Count ◽

Outcome Variable ◽

Newly Diagnosed ◽

Drug Reactions ◽

First Line ◽

First Line Therapy ◽

Line Therapy

Abstract Introduction: India has a huge burden of HIV/AIDS infection. Tenofovir based first line therapy is the preferred treatment for newly diagnosed cases with HIV infection. Methodology: The present prospective study was done among newly diagnosed cases of HIV infection. The patients were followed up for a period of 6 months from the day of enrolment. Sociodemographic parameters, CD4 counts and adverse drug reactions were analysed at baseline and after 6 months. Bi-variate and multi-variate logistic regression was performed with the outcome variable as occurrence of adverse drug reactions. Result: In this study, 67 patients were enrolled with mean age 32.75 (± 14.39) years. Mean CD4 count at start of treatment was 241.5/mm3. Mean difference in CD4 count was 383.05/mm3 (SD = 274.9). Dizziness, tingling, numbness of extremities and muscle cramps were most common adverse effects. On multi-variate logistic regression, occurrence of ADRs was seen to be significantly higher only in illiterate patients. Conclusion: The present study highlights the importance of long-term follow-up of the patients on antiretroviral therapy. Adequate monitoring of the treatment parameters is of utmost importance.

Download Full-text