High-throughput framework for genetic analyses of adverse drug reactions using electronic health records.
Ontology highlight
ABSTRACT:
SUBMITTER: Zheng NS
PROVIDER: S-EPMC8195357 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:High-throughput genetic analyses of drug intolerances using electronic health records
| PRJNA683675 | ENA
Project description:Unknown adverse reactions to drugs available on the market present a significant health risk and limit accurate judgement of the cost/benefit trade-off for medications. Machine learning has the potential to predict unknown adverse reactions from current knowledge. We constructed a knowledge graph containing four types of node: drugs, protein targets, indications and adverse reactions. Using this graph, we developed a machine learning algorithm based on a simple enrichment test and first demonstrated this method performs extremely well at classifying known causes of adverse reactions (AUC 0.92). A cross validation scheme in which 10% of drug-adverse reaction edges were systematically deleted per fold showed that the method correctly predicts 68% of the deleted edges on average. Next, a subset of adverse reactions that could be reliably detected in anonymised electronic health records from South London and Maudsley NHS Foundation Trust were used to validate predictions from the model that are not currently known in public databases. High-confidence predictions were validated in electronic records significantly more frequently than random models, and outperformed standard methods (logistic regression, decision trees and support vector machines). This approach has the potential to improve patient safety by predicting adverse reactions that were not observed during randomised trials.
| S-EPMC5703951 | biostudies-literature
Project description:ObjectiveElectronic health records (EHRs) contain information to detect adverse drug reactions (ADRs), as they contain comprehensive clinical information. A major challenge of using comprehensive information involves confounding. We propose a novel data-driven method to identify ADR signals accurately by adjusting for confounders.Materials and methodsWe focused on two serious ADRs, rhabdomyolysis and pancreatitis, and used information in 264,155 unique patient records. We identified an ADR using established criteria, selected potential confounders, and then used penalized logistic regressions to estimate confounder-adjusted ADR associations. A reference standard was created to evaluate and compare the precision of the proposed method and four others.ResultsPrecision was 83.3% for rhabdomyolysis and 60.8% for pancreatitis when using the proposed method, and we identified several drug safety signals that are interesting for further clinical review.DiscussionThe proposed method effectively estimated ADR associations after adjusting for confounders. A main cause of error was probably due to the nature of the dataset in that a substantial number of patients had a single visit only and, therefore, it was not possible to determine correctly the appropriate sequence of events for them. It is likely that performance will be improved with use of EHR data that contain more longitudinal records.ConclusionsThis data-driven method is effective in controlling for confounding, resulting in either a higher or similar precision when compared with four comparators, has the unique ability to provide insight into confounders for each specific medication-ADR pair, and can be easily adapted to other EHR systems.
| S-EPMC3932454 | biostudies-literature
Project description:Pharmacogenomics aims to tailor pharmacological treatment to each individual by considering associations between genetic polymorphisms and adverse drug effects (ADEs). With technological advances, pharmacogenomic research has evolved from candidate gene analyses to genome-wide association studies. Here, we integrate deep whole-genome sequencing (WGS) information with drug prescription and ADE data from Estonian electronic health record (EHR) databases to evaluate genome- and pharmacome-wide associations on an unprecedented scale. We leveraged WGS data of 2240 Estonian Biobank participants and imputed all single-nucleotide variants (SNVs) with allele counts over 2 for 13,986 genotyped participants. Overall, we identified 41 (10 novel) loss-of-function and 567 (134 novel) missense variants in 64 very important pharmacogenes. The majority of the detected variants were very rare with frequencies below 0.05%, and 6 of the novel loss-of-function and 99 of the missense variants were only detected as single alleles (allele count = 1). We also validated documented pharmacogenetic associations and detected new independent variants in known gene-drug pairs. Specifically, we found that CTNNA3 was associated with myositis and myopathies among individuals taking nonsteroidal anti-inflammatory oxicams and replicated this finding in an extended cohort of 706 individuals. These findings illustrate that population-based WGS-coupled EHRs are a useful tool for biomarker discovery.
| S-EPMC6460570 | biostudies-literature
Project description:AimsA systematic review of the literature published in English over 10?years was undertaken in order to describe the use of electronic healthcare data in the identification of potential adverse drug reactions (ADRs) in children.MethodsMEDLINE and EMBASE were searched using MESH headings and text words. Titles, keywords and abstracts were checked for age <18 years, potential ADRs and electronic healthcare data. Information extracted included age, data source, pharmacovigilance method, medicines and ADRs. Studies were quality assessed.ResultsFrom 14 804 titles, 314 had a full text review and 71 were included in the final review. Fifty were published in North America, 10 in Scandinavia. Study size ranged from less than 1000 children to more than 10 million. Sixty per cent of studies used data from one source. Comparative observational studies were most commonly reported (66.2%) with 15% using passive surveillance. Electronic healthcare data set linkage and the quality of the data source were poorly reported. ADRs were classified using the International Classification of Disease (ICD10). Multi-system reactions were most commonly studied, followed by central nervous system and mental and behavioural disorders. Vaccines were most frequently prescribed followed by corticosteroids, general anaesthetics and antidepressants.ConclusionsRoutine electronic healthcare records were increasingly reported to be used for pharmacovigilance in children. This growing and important health protection activity could be enhanced by consistent reporting of studies to improve the identification, interpretation and generalizability of the evidence base.
| S-EPMC4594727 | biostudies-literature
Project description:MotivationPedigree analysis is a longstanding and powerful approach to gain insight into the underlying genetic factors in human health, but identifying, recruiting and genotyping families can be difficult, time consuming and costly. Development of high throughput methods to identify families and foster downstream analyses are necessary.ResultsThis paper describes simple methods that allowed us to identify 173 368 family pedigrees with high probability using basic demographic data available in most electronic health records (EHRs). We further developed and validate a novel statistical method that uses EHR data to identify families more likely to have a major genetic component to their diseases risk. Lastly, we showed that incorporating EHR-linked family data into genetic association testing may provide added power for genetic mapping without additional recruitment or genotyping. The totality of these results suggests that EHR-linked families can enable classical genetic analyses in a high-throughput manner.Availability and implementationPseudocode is provided as supplementary information.ContactHEBBRING.SCOTT@marshfieldresearch.org.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC5860602 | biostudies-literature
Project description:BackgroundAdverse drug reactions (ADRs) are estimated to be the fifth cause of hospital death. Up to 50% are potentially preventable and a significant number are recurrent (reADRs). Clinical decision support systems have been used to prevent reADRs using structured reporting concerning the patient's ADR experience, which in current clinical practice is poorly performed. Identifying ADRs directly from free text in electronic health records (EHRs) could circumvent this.AimTo develop strategies to identify ADRs from free-text notes in electronic hospital health records.MethodsIn stage I, the EHRs of 10 patients were reviewed to establish strategies for identifying ADRs. In stage II, complete EHR histories of 45 patients were reviewed for ADRs and compared to the strategies programmed into a rule-based model. ADRs were classified using MedDRA and included in the study if the Naranjo causality score was ≥1. Seriousness was assessed using the European Medicine Agency's important medical event list.ResultsIn stage I, two main search strategies were identified: keywords indicating an ADR and specific prepositions followed by medication names. In stage II, the EHRs contained a median of 7.4 (range 0.01-18) years of medical history covering over 35 000 notes. A total of 318 unique ADRs were identified of which 63 were potentially serious and 179 (sensitivity 57%) were identified by the rule. The method falsely identified 377 ADRs (positive predictive value 32%). However, it also identified an additional eight ADRs.ConclusionTwo key strategies were developed to identify ADRs from hospital EHRs using free-text notes. The results appear promising and warrant further study.
| S-EPMC9292762 | biostudies-literature
Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.
| S-EPMC6300887 | biostudies-other
Project description:ObjectiveWe identified the methods used and determined the roles of electronic health records (EHRs) in detecting and assessing adverse drug events (ADEs) in the ambulatory setting.MethodsWe performed a systematic literature review by searching PubMed and Google Scholar for studies on ADEs detected in the ambulatory setting involving any EHR use published before June 2017. We extracted study characteristics from included studies related to ADE detection methods for analysis.ResultsWe identified 30 studies that evaluated ADEs in an ambulatory setting with an EHR. In 27 studies, EHRs were used only as the data source for ADE identification. In two studies, the EHR was used as both a data source and to deliver decision support to providers during order entry. In one study, the EHR was a source of data and generated patient safety reports that researchers used in the process of identifying ADEs. Methods of identification included manual chart review by trained nurses, pharmacists, and/or physicians; prescription review; computer monitors; electronic triggers; International Classification of Diseases codes; natural language processing of clinical notes; and patient phone calls and surveys. Seven studies provided examples of search phrases, laboratory values, and rules used to identify ADEs.ConclusionThe majority of studies examined used EHRs as sources of data for ADE detection. This retrospective approach is appropriate to measure incidence rates of ADEs but not adequate to detect preventable ADEs before patient harm occurs. New methods involving computer monitors and electronic triggers will enable researchers to catch preventable ADEs and take corrective action.
| S-EPMC6382497 | biostudies-literature
Project description:ObjectiveThis article summarizes the preparation, organization, evaluation, and results of Track 2 of the 2018 National NLP Clinical Challenges shared task. Track 2 focused on extraction of adverse drug events (ADEs) from clinical records and evaluated 3 tasks: concept extraction, relation classification, and end-to-end systems. We perform an analysis of the results to identify the state of the art in these tasks, learn from it, and build on it.Materials and methodsFor all tasks, teams were given raw text of narrative discharge summaries, and in all the tasks, participants proposed deep learning-based methods with hand-designed features. In the concept extraction task, participants used sequence labelling models (bidirectional long short-term memory being the most popular), whereas in the relation classification task, they also experimented with instance-based classifiers (namely support vector machines and rules). Ensemble methods were also popular.ResultsA total of 28 teams participated in task 1, with 21 teams in tasks 2 and 3. The best performing systems set a high performance bar with F1 scores of 0.9418 for concept extraction, 0.9630 for relation classification, and 0.8905 for end-to-end. However, the results were much lower for concepts and relations of Reasons and ADEs. These were often missed because local context is insufficient to identify them.ConclusionsThis challenge shows that clinical concept extraction and relation classification systems have a high performance for many concept types, but significant improvement is still required for ADEs and Reasons. Incorporating the larger context or outside knowledge will likely improve the performance of future systems.
| S-EPMC7489085 | biostudies-literature