Using text-mining techniques in electronic patient records to identify ADRs from medicine use

Monitoring Adverse Drug Events in Web Forums: Evaluation of a Pipeline and Use Case Study

BACKGROUND

To mitigate safety concerns, regulatory agencies must make informed decisions regarding drug usage and adverse drug events (ADEs). The primary pharmacovigilance data stem from spontaneous reports by health care professionals. However, underreporting poses a notable challenge within the current system. Explorations into alternative sources, including electronic patient records and social media, have been undertaken. Nevertheless, social media's potential remains largely untapped in real-world scenarios.

OBJECTIVE

The challenge faced by regulatory agencies in using social media is primarily attributed to the absence of suitable tools to support decision makers. An effective tool should enable access to information via a graphical user interface, presenting data in a user-friendly manner rather than in their raw form. This interface should offer various visualization options, empowering users to choose representations that best convey the data and facilitate informed decision-making. Thus, this study aims to assess the potential of integrating social media into pharmacovigilance and enhancing decision-making with this novel data source. To achieve this, our objective was to develop and assess a pipeline that processes data from the extraction of web forum posts to the generation of indicators and alerts within a visual and interactive environment. The goal was to create a user-friendly tool that enables regulatory authorities to make better-informed decisions effectively.

METHODS

To enhance pharmacovigilance efforts, we have devised a pipeline comprising 4 distinct modules, each independently editable, aimed at efficiently analyzing health-related French web forums. These modules were (1) web forums' posts extraction, (2) web forums' posts annotation, (3) statistics and signal detection algorithm, and (4) a graphical user interface (GUI). We showcase the efficacy of the GUI through an illustrative case study involving the introduction of the new formula of Levothyrox in France. This event led to a surge in reports to the French regulatory authority.

RESULTS

Between January 1, 2017, and February 28, 2021, a total of 2,081,296 posts were extracted from 23 French web forums. These posts contained 437,192 normalized drug-ADE couples, annotated with the Anatomical Therapeutic Chemical (ATC) Classification and Medical Dictionary for Regulatory Activities (MedDRA). The analysis of the Levothyrox new formula revealed a notable pattern. In August 2017, there was a sharp increase in posts related to this medication on social media platforms, which coincided with a substantial uptick in reports submitted by patients to the national regulatory authority during the same period.

CONCLUSIONS

We demonstrated that conducting quantitative analysis using the GUI is straightforward and requires no coding. The results aligned with prior research and also offered potential insights into drug-related matters. Our hypothesis received partial confirmation because the final users were not involved in the evaluation process. Further studies, concentrating on ergonomics and the impact on professionals within regulatory agencies, are imperative for future research endeavors. We emphasized the versatility of our approach and the seamless interoperability between different modules over the performance of individual modules. Specifically, the annotation module was integrated early in the development process and could undergo substantial enhancement by leveraging contemporary techniques rooted in the Transformers architecture. Our pipeline holds potential applications in health surveillance by regulatory agencies or pharmaceutical companies, aiding in the identification of safety concerns. Moreover, it could be used by research teams for retrospective analysis of events.

Extracting adverse drug events from clinical Notes: A systematic review of approaches used

BACKGROUND

An adverse drug event (ADE) is any unfavorable effect that occurs due to the use of a drug. Extracting ADEs from unstructured clinical notes is essential to biomedical text extraction research because it helps with pharmacovigilance and patient medication studies.

OBJECTIVE

From the considerable amount of clinical narrative text, natural language processing (NLP) researchers have developed methods for extracting ADEs and their related attributes. This work presents a systematic review of current methods.

METHODOLOGY

Two biomedical databases have been searched from June 2022 until December 2023 for relevant publications regarding this review, namely the databases PubMed and Medline. Similarly, we searched the multi-disciplinary databases IEEE Xplore, Scopus, ScienceDirect, and the ACL Anthology. We adopted the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement guidelines and recommendations for reporting systematic reviews in conducting this review. Initially, we obtained 5,537 articles from the search results from the various databases between 2015 and 2023. Based on predefined inclusion and exclusion criteria for article selection, 100 publications have undergone full-text review, of which we consider 82 for our analysis.

RESULTS

We determined the general pattern for extracting ADEs from clinical notes, with named entity recognition (NER) and relation extraction (RE) being the dual tasks considered. Researchers that tackled both NER and RE simultaneously have approached ADE extraction as a "pipeline extraction" problem (n = 22), as a "joint task extraction" problem (n = 7), and as a "multi-task learning" problem (n = 6), while others have tackled only NER (n = 27) or RE (n = 20). We further grouped the reviews based on the approaches for data extraction, namely rule-based (n = 8), machine learning (n = 11), deep learning (n = 32), comparison of two or more approaches (n = 11), hybrid (n = 12) and large language models (n = 8). The most used datasets are MADE 1.0, TAC 2017 and n2c2 2018.

CONCLUSION

Extracting ADEs is crucial, especially for pharmacovigilance studies and patient medications. This survey showcases advances in ADE extraction research, approaches, datasets, and state-of-the-art performance in them. Challenges and future research directions are highlighted. We hope this review will guide researchers in gaining background knowledge and developing more innovative ways to address the challenges.

Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review

INTRODUCTION

Pharmacovigilance programs protect patient health and safety by identifying adverse event signals through postmarketing surveillance of claims data and spontaneous reports. Electronic health records (EHRs) provide new opportunities to address limitations of traditional approaches and promote discovery-oriented pharmacovigilance.

METHODS

To evaluate the current state of EHR-based medication safety signal identification, we conducted a scoping literature review of studies aimed at identifying safety signals from routinely collected patient-level EHR data. We extracted information on study design, EHR data elements utilized, analytic methods employed, drugs and outcomes evaluated, and key statistical and data analysis choices.

RESULTS

We identified 81 eligible studies. Disproportionality methods were the predominant analytic approach, followed by data mining and regression. Variability in study design makes direct comparisons difficult. Studies varied widely in terms of data, confounding adjustment, and statistical considerations.

CONCLUSION

Despite broad interest in utilizing EHRs for safety signal identification, current efforts fail to leverage the full breadth and depth of available data or to rigorously control for confounding. The development of best practices and application of common data models would promote the expansion of EHR-based pharmacovigilance.

Drug_SNSMiner: standard pharmacovigilance pipeline for detection of adverse drug reaction using SNS data

As society continues to age, it is becoming increasingly important to monitor drug use in the elderly. Social media data have been used for monitoring adverse drug reactions. The aim of this study was to determine whether social network studies (SNS) are useful sources of drug side effects information. We propose a method for utilizing SNS data to plot the known side effects of geriatric drugs in a dosing map. We developed a lexicon of drug terms associated with side effects and mapped patterns from social media data. We confirmed that well-known side effects may be obtained by utilizing SNS data. Based on these results, we propose a pharmacovigilance pipeline that can be extended to unknown side effects. We propose the standard analysis pipeline Drug_SNSMiner for monitoring side effects using SNS data and evaluated it as a drug prescription platform for the elderly. We confirmed that side effects may be monitored from the consumer's perspective based on SNS data using only drug information. SNS data were deemed good sources of information to determine ADRs and obtain other complementary data. We established that these learning data are invaluable for AI requiring the acquisition of ADR posts on efficacious drugs.

Harnessing the Power of Electronic Health Records and Genomics for Drug Discovery

A long-standing recognition that information from human genetics studies has the potential to accelerate drug discovery has led to decades of research on how to leverage genetic and phenotypic information for drug discovery. Established simple and advanced statistical methods that allow the simultaneous analysis of genotype and clinical phenotype data by genome- and phenome-wide analyses, colocalization analyses with quantitative trait loci data from transcriptomics and proteomics data sets from different tissues, and Mendelian randomization are essential tools for drug development in the postgenomic era. Numerous studies have demonstrated how genomic data provide opportunities for the identification of new drug targets, the repurposing of drugs, and drug safety analyses. With an increase in the number of biobanks that enable linking in-depth omics data with rich repositories of phenotypic traits via electronic health records, more powerful ways for the evaluation and validation of drug targets will continue to expand across different disciplines of clinical research.

Application of Natural Language Processing (NLP) in Detecting and Preventing Suicide Ideation: A Systematic Review

(1) Introduction: Around a million people are reported to die by suicide every year, and due to the stigma associated with the nature of the death, this figure is usually assumed to be an underestimate. Machine learning and artificial intelligence such as natural language processing has the potential to become a major technique for the detection, diagnosis, and treatment of people. (2) Methods: PubMed, EMBASE, MEDLINE, PsycInfo, and Global Health databases were searched for studies that reported use of NLP for suicide ideation or self-harm. (3) Result: The preliminary search of 5 databases generated 387 results. Removal of duplicates resulted in 158 potentially suitable studies. Twenty papers were finally included in this review. (4) Discussion: Studies show that combining structured and unstructured data in NLP data modelling yielded more accurate results than utilizing either alone. Additionally, to reduce suicides, people with mental problems must be continuously and passively monitored. (5) Conclusions: The use of AI&ML opens new avenues for considerably guiding risk prediction and advancing suicide prevention frameworks. The review's analysis of the included research revealed that the use of NLP may result in low-cost and effective alternatives to existing resource-intensive methods of suicide prevention.

Extraction of Active Medications and Adherence Using Natural Language Processing for Glaucoma Patients

Accuracy of medication data in electronic health records (EHRs) is crucial for patient care and research, but many studies have shown that medication lists frequently contain errors. In contrast, physicians often pay more attention to the clinical notes and record medication information in them. The medication information in notes may be used for medication reconciliation to improve the medication lists' accuracy. However, accurately extracting patient's current medications from free-text narratives is challenging. In this study, we first explored the discrepancies between medication documentation in medication lists and progress notes for glaucoma patients by manually reviewing patients' charts. Next, we developed and validated a named entity recognition model to identify current medication and adherence from progress notes. Lastly, a prototype tool for medication reconciliation using the developed model was demonstrated. In the future, the model has the potential to be incorporated into the EHR system to help with realtime medication reconciliation.

Combining word embeddings to extract chemical and drug entities in biomedical literature

BACKGROUND

Natural language processing (NLP) and text mining technologies for the extraction and indexing of chemical and drug entities are key to improving the access and integration of information from unstructured data such as biomedical literature.

METHODS

In this paper we evaluate two important tasks in NLP: the named entity recognition (NER) and Entity indexing using the SNOMED-CT terminology. For this purpose, we propose a combination of word embeddings in order to improve the results obtained in the PharmaCoNER challenge.

RESULTS

For the NER task we present a neural network composed of BiLSTM with a CRF sequential layer where different word embeddings are combined as an input to the architecture. A hybrid method combining supervised and unsupervised models is used for the concept indexing task. In the supervised model, we use the training set to find previously trained concepts, and the unsupervised model is based on a 6-step architecture. This architecture uses a dictionary of synonyms and the Levenshtein distance to assign the correct SNOMED-CT code.

CONCLUSION

On the one hand, the combination of word embeddings helps to improve the recognition of chemicals and drugs in the biomedical literature. We achieved results of 91.41% for precision, 90.14% for recall, and 90.77% for F1-score using micro-averaging. On the other hand, our indexing system achieves a 92.67% F1-score, 92.44% for recall, and 92.91% for precision. With these results in a final ranking, we would be in the first position.

Natural language processing and machine learning to assist radiation oncology incident learning

PURPOSE

To develop a Natural Language Processing (NLP) and Machine Learning (ML) pipeline that can be integrated into an Incident Learning System (ILS) to assist radiation oncology incident learning by semi-automating incident classification. Our goal was to develop ML models that can generate label recommendations, arranged according to their likelihoods, for three data elements in Canadian NSIR-RT taxonomy.

METHODS

Over 6000 incident reports were gathered from the Canadian national ILS as well as our local ILS database. Incident descriptions from these reports were processed using various NLP techniques. The processed data with the expert-generated labels were used to train and evaluate over 500 multi-output ML algorithms. The top three models were identified and tuned for each of three different taxonomy data elements, namely: (1) process step where the incident occurred, (2) problem type of the incident and (3) the contributing factors of the incident. The best-performing model after tuning was identified for each data element and tested on unseen data.

RESULTS

The MultiOutputRegressor extended Linear SVR models performed best on the three data elements. On testing, our models ranked the most appropriate label 1.48 ± 0.03, 1.73 ± 0.05 and 2.66 ± 0.08 for process-step, problem-type and contributing factors respectively.

CONCLUSIONS

We developed NLP-ML models that can perform incident classification. These models will be integrated into our ILS to generate a drop-down menu. This semi-automated feature has the potential to improve the usability, accuracy and efficiency of our radiation oncology ILS.

Applications of artificial intelligence in drug development using real-world data

The US Food and Drug Administration (FDA) has been actively promoting the use of real-world data (RWD) in drug development. RWD can generate important real-world evidence reflecting the real-world clinical environment where the treatments are used. Meanwhile, artificial intelligence (AI), especially machine- and deep-learning (ML/DL) methods, have been increasingly used across many stages of the drug development process. Advancements in AI have also provided new strategies to analyze large, multidimensional RWD. Thus, we conducted a rapid review of articles from the past 20 years, to provide an overview of the drug development studies that use both AI and RWD. We found that the most popular applications were adverse event detection, trial recruitment, and drug repurposing. Here, we also discuss current research gaps and future opportunities.

Ontological Organization and Bioinformatic Analysis of Adverse Drug Reactions From Package Inserts: Development and Usability Study

BACKGROUND

Licensed drugs may cause unexpected adverse reactions in patients, resulting in morbidity, risk of mortality, therapy disruptions, and prolonged hospital stays. Officially approved drug package inserts list the adverse reactions identified from randomized controlled clinical trials with high evidence levels and worldwide postmarketing surveillance. Formal representation of the adverse drug reaction (ADR) enclosed in semistructured package inserts will enable deep recognition of side effects and rational drug use, substantially reduce morbidity, and decrease societal costs.

OBJECTIVE

This paper aims to present an ontological organization of traceable ADR information extracted from licensed package inserts. In addition, it will provide machine-understandable knowledge for bioinformatics analysis, semantic retrieval, and intelligent clinical applications.

METHODS

Based on the essential content of package inserts, a generic ADR ontology model is proposed from two dimensions (and nine subdimensions), covering the ADR information and medication instructions. This is followed by a customized natural language processing method programmed with Python to retrieve the relevant information enclosed in package inserts. After the biocuration and identification of retrieved data from the package insert, an ADR ontology is automatically built for further bioinformatic analysis.

RESULTS

We collected 165 package inserts of quinolone drugs from the National Medical Products Administration and other drug databases in China, and built a specialized ADR ontology containing 2879 classes and 15,711 semantic relations. For each quinolone drug, the reported ADR information and medication instructions have been logically represented and formally organized in an ADR ontology. To demonstrate its usage, the source data were further bioinformatically analyzed. For example, the number of drug-ADR triples and major ADRs associated with each active ingredient were recorded. The 10 ADRs most frequently observed among quinolones were identified and categorized based on the 18 categories defined in the proposal. The occurrence frequency, severity, and ADR mitigation method explicitly stated in package inserts were also analyzed, as well as the top 5 specific populations with contraindications for quinolone drugs.

CONCLUSIONS

Ontological representation and organization using officially approved information from drug package inserts enables the identification and bioinformatic analysis of adverse reactions caused by a specific drug with regard to predefined ADR ontology classes and semantic relations. The resulting ontology-based ADR knowledge source classifies drug-specific adverse reactions, and supports a better understanding of ADRs and safer prescription of medications.

Identifying Herbal Adverse Events From Spontaneous Reporting Systems Using Taxonomic Name Resolution Approach

The efficacy and safety of herbal supplements suffer from challenges due to non-uniform representation of ingredient terms within biomedical and observational health data sources. The nature of how supplement data are reported within Spontaneous Reporting Systems (SRS) can limit analyses of supplement-associated adverse events due to the use of incorrect nomenclature or failing to identify herbs. This study aimed to extract, standardize, and summarize supplement-relevant reports from two SRSs: (1) Food and Drug Administration Adverse Event Reporting System (FAERS) and (2) Canada Vigilance Adverse Reaction (CVAR) database. A thesaurus of plant names was developed and integrated with a mapping and normalization approach that accommodated misspellings and variants. The reports gathered from FAERS between the years 2004 and 2016 show 185,915 herbal and 7,235,330 non-herbal accounting for 2.51%. The data from CVAR found 36,940 reports of herbal and 503,580 non-herbal reports between the years 1965 and 2017 for a total of 6.83%. Although not all cases were actual adverse events due to numerous variables and incomplete reporting, it is interesting to note that the herbs most frequently reported and significantly associated with adverse events were as follows: Avena sativa (Oats), Cannabis sativa (marijuana), Digitalis purpurea (foxglove), Humulus lupulus (hops), Hypericum perforatum (St John’s Wort), Paullinia cupana (guarana), Phleum pretense (timothy-grass), Silybum marianum (milk thistle), Taraxacum officinale (Dandelion), and Valeriana officinalis (valerian). Using a scalable approach for mapping and resolution of herb names allowed data-driven exploration of potential adverse events from sources that have remained isolated in this specific area of research. The results from this study highlight several herb-associated safety issues providing motivation for subsequent in-depth analyses, including those that focus on the scope and severity of potential safety issues with supplement use.

Comparisons of different classification algorithms while using text mining to screen psychiatric inpatients with suicidal behaviors

OBJECTIVE

To compare the performance of methods based on text mining to screen suicidal behaviors according to chief complaint of the psychiatric inpatients.

METHODS

Electronic Medical Records of inpatients with mental disorders were collected. Text mining method was adopted to screen suicidal behaviors. The performances of different combinations of six algorithms and two term weighting factors were compared under various training set sizes, which were assessed by precision, recall, F1-value and accuracy.

RESULTS

A total of 3600 psychiatric inpatients (1800 with suicidal behaviors and 1800 without suicidal behaviors) were included in this study. In chief complaints of suicidal inpatients, "suicide", "notion" and "suspicion" were the commonest statements, appearing 1228, 705 and 638 times respectively. In contrast, "excitement", "instability" and "impulsion" appeared more frequently in chief complaints of patients without suicidal behaviors (599, 599, 534 times respectively). The performance of each algorithm was generally improved with the increasing training set sizes and tended to be stable when the number of training cases reached 1000, where most of them could achieve satisfactory accuracy values (>0.95). Results of testing set showed that SVM, Random Forest and AdaBoost weighted by TF had better generalization ability. The F1 values were 0.9889 for SVM, 0.9838 for random forest and 0.9828 for AdaBoost, respectively.

CONCLUSION

This study confirmed the feasibility of filtering suicidal inpatients with small amounts of representative terms. SVM, Random Forest and AdaBoost weighted by TF have better performance in this task. Our findings provided a practical way to automatically classify patients with or without suicidal behaviors before admission to hospital, which potentially led to considerable savings in time and human resources for identification of high-risk patients and suicide prevention.

Drug Abuse Research Trend Investigation with Text Mining

Drug abuse poses great physical and psychological harm to humans, thereby attracting scholarly attention. It often requires experience and time for a researcher, just entering this field, to find an appropriate method to study drug abuse issue. It is crucial for researchers to rapidly understand the existing research on a particular topic and be able to propose an effective new research method. Text mining analysis has been widely applied in recent years, and this study integrated the text mining method into a review of drug abuse research. Through searches for keywords related to the drug abuse, all related publications were identified and downloaded from PubMed. After removing the duplicate and incomplete literature, the retained data were imported for analysis through text mining. A total of 19,843 papers were analyzed, and the text mining technique was used to search for keyword and questionnaire types. The results showed the associations between these questionnaires, with the top five being the Addiction Severity Index (16.44%), the Quality of Life survey (5.01%), the Beck Depression Inventory (3.24%), the Addiction Research Center Inventory (2.81%), and the Profile of Mood States (1.10%). Specifically, the Addiction Severity Index was most commonly used in combination with Quality of Life scales. In conclusion, association analysis is useful to extract core knowledge. Researchers can learn and visualize the latest research trend.

Text Mining Method for Studying Medication Administration Incidents and Nurse-Staffing Contributing Factors: A Pilot Study

Incident reporting systems are being implemented globally, thus increasing the profile and prevalence of incidents, but the analysis of free-text descriptions remains largely hidden. The aims of the study were to explore the extent to which incident reports recorded staffing issues as contributors to medication administration incidents. Incident reports related to medication administration (N = 1012) were collected from two hospitals in Finland between January 1, 2013, and December 31, 2014. The SAS Enterprise Miner 13.2 and its Text Miner tool were used to excavate terms and descriptors and to uncover themes and concepts in the free-text descriptions of incidents with (n = 194) and without (n = 818) nurse staffing-related contributing factors. Text mining included (1) text parsing, (2) text filtering, and (3) modeling text clusters and text topics. The term "rush/hurry" was the sixth most common term used in incidents where nurse-staffing was identified as a contributing factor. Nurse-staffing factors, however, were not pronounced in clusters or in text topics of either data set. Text mining offers the opportunity to analyze large free-text mass and holds promise for providing insight into the antecedents of medication administration incidents.

Linking glycemic dysregulation in diabetes to symptoms, comorbidities, and genetics through EHR data mining

Diabetes is a diverse and complex disease, with considerable variation in phenotypic manifestation and severity. This variation hampers the study of etiological differences and reduces the statistical power of analyses of associations to genetics, treatment outcomes, and complications. We address these issues through deep, fine-grained phenotypic stratification of a diabetes cohort. Text mining the electronic health records of 14,017 patients, we matched two controlled vocabularies (ICD-10 and a custom vocabulary developed at the clinical center Steno Diabetes Center Copenhagen) to clinical narratives spanning a 19 year period. The two matched vocabularies comprise over 20,000 medical terms describing symptoms, other diagnoses, and lifestyle factors. The cohort is genetically homogeneous (Caucasian diabetes patients from Denmark) so the resulting stratification is not driven by ethnic differences, but rather by inherently dissimilar progression patterns and lifestyle related risk factors. Using unsupervised Markov clustering, we defined 71 clusters of at least 50 individuals within the diabetes spectrum. The clusters display both distinct and shared longitudinal glycemic dysregulation patterns, temporal co-occurrences of comorbidities, and associations to single nucleotide polymorphisms in or near genes relevant for diabetes comorbidities.

Detecting substance-related problems in narrative investigation summaries of child abuse and neglect using text mining and machine learning

BACKGROUND

State child welfare agencies collect, store, and manage vast amounts of data. However, they often do not have the right data, or the data is problematic or difficult to inform strategies to improve services and system processes. Considerable resources are required to read and code these text data. Data science and text mining offer potentially efficient and cost-effective strategies for maximizing the value of these data.

OBJECTIVE

The current study tests the feasibility of using text mining for extracting information from unstructured text to better understand substance-related problems among families investigated for abuse or neglect.

METHOD

A state child welfare agency provided written summaries from investigations of child abuse and neglect. Expert human reviewers coded 2956 investigation summaries based on whether the caseworker observed a substance-related problem. These coded documents were used to develop, train, and validate computer models that could perform the coding on an automated basis.

RESULTS

A set of computer models achieved greater than 90% accuracy when judged against expert human reviewers. Fleiss kappa estimates among computer models and expert human reviewers exceeded .80, indicating that expert human reviewer ratings are exchangeable with the computer models.

CONCLUSION

These results provide compelling evidence that text mining procedures can be a cost-effective and efficient solution for extracting meaningful insights from unstructured text data. Additional research is necessary to understand how to extract the actionable insights from these under-utilized stores of data in child welfare.

The Contribution of Staffing to Medication Administration Errors: A Text Mining Analysis of Incident Report Data

PURPOSE

(a) To describe trigger terms that can be used to identify reports of inadequate staffing contributing to medication administration errors, (b) to identify such reports, (c) to compare the degree of harm within incidents with and without those triggers, and (d) to examine the association between the most commonly reported inadequate staffing trigger terms and the incidence of omission errors and "no harm" terms.

DESIGN AND SETTING

This was a retrospective study using descriptive statistical analysis, text mining, and manual analysis of free text descriptions of medication administration-related incident reports (N = 72,390) reported to the National Reporting and Learning System for England and Wales in 2016.

METHODS

Analysis included identifying terms indicating inadequate staffing (manual analysis), followed by text parsing, filtering, and concept linking (SAS Text Miner tool). IBM SPSS was used to describe the data, compare degree of harm for incidents with and without triggers, and to compare incidence of "omission errors" and "no harm" among the inadequate staffing trigger terms.

FINDINGS

The most effective trigger terms for identifying inadequate staffing were "short staffing" (n = 81), "workload" (n = 80), and "extremely busy" (n = 51). There was significant variation in omission errors across inadequate staffing trigger terms (Fisher's exact test = 44.11, p < .001), with those related to "workload" most likely to accompany a report of an omission, followed by terms that mention "staffing" and being "busy." Prevalence of "no harm" did not vary statistically between the trigger terms (Fisher's exact test = 11.45, p = 0.49), but the triggers "workload," "staffing level," "busy night," and "busy unit" identified incidents with lower levels of "no harm" than for incidents overall.

CONCLUSIONS

Inadequate staffing levels, workload, and working in haste may increase the risk for omissions and other types of error, as well as for patient harm.

CLINICAL RELEVANCE

This work lays the groundwork for creating automated text-analytical systems that could analyze incident reports in real time and flag or monitor staffing levels and related medication administration errors.

Off-label use of pentazocine and the associated adverse events among pediatric surgical patients in a tertiary hospital in Northern Nigeria: a retrospective chart review

Background and aims: Pentazocine remains a widely used opioid pre-anesthetic medication and post-operative analgesic in low- and middle-income countries despite concerns. We assessed the adverse events (AEs) associated with off-label use of pentazocine in pediatric surgical patients and determined the possible risk factors associated with slow respiratory AEs.Method: Children ≤18 years old were administered pentazocine IM/IV as a pre-anesthetic medication or post-operative analgesic. Pertinent data including total daily dose and duration of use of pentazocine and its associated AEs were obtained from patients' case files. Risk factors associated with slow respiratory AEs were determined using logistic regression analyses.Results: One hundred and fifty-nine patients were included with a median age of 2 years; they were mainly males (52.8%). Pentazocine was administered off-label to all patients for post-operative pain management (96.2%) or pre-anesthetic medication (3.8%). All patients experienced at least one AE with most experiencing 2-7 AEs. Rapid breathing (120; 18.7%), followed by fast pulse (101; 15.7%) and sleepiness/sedation/drowsiness (81; 12.6%) were the most common AEs. None of the demographics and clinical variables significantly predicted the risk of slow respiratory AEs.Conclusion: Off-label use of pentazocine is common and associated with multiple AEs. Care is needed as no predictors of slow respiratory AEs were observed.

Phenotyping to Facilitate Accrual for a Cardiovascular Intervention

Background

The conventional approach for clinical studies is to identify a cohort of potentially eligible patients and then screen for enrollment. In an effort to reduce the cost and manual effort involved in the screening process, several studies have leveraged electronic health records (EHR) to refine cohorts to better match the eligibility criteria, which is referred to as phenotyping. We extend this approach to dynamically identify a cohort by repeating phenotyping in alternation with manual screening.

Methods

Our approach consists of multiple screen cycles. At the start of each cycle, the phenotyping algorithm is used to identify eligible patients from the EHR, creating an ordered list such that patients that are most likely eligible are listed first. This list is then manually screened, and the results are analyzed to improve the phenotyping for the next cycle. We describe the preliminary results and challenges in the implementation of this approach for an intervention study on heart failure.

Results

A total of 1,022 patients were screened, with 223 (23%) of patients being found eligible for enrollment into the intervention study. The iterative approach improved the phenotyping in each screening cycle. Without an iterative approach, the positive screening rate (PSR) was expected to dip below the 20% measured in the first cycle; however, the cyclical approach increased the PSR to 23%.

Conclusions

Our study demonstrates that dynamic phenotyping can facilitate recruitment for prospective clinical study. Future directions include improved informatics infrastructure and governance policies to enable real-time updates to research repositories, tooling for EHR annotation, and methodologies to reduce human annotation.

Automated classification of primary care patient safety incident report content and severity using supervised machine learning (ML) approaches

Learning from patient safety incident reports is a vital part of improving healthcare. However, the volume of reports and their largely free-text nature poses a major analytic challenge. The objective of this study was to test the capability of autonomous classifying of free text within patient safety incident reports to determine incident type and the severity of harm outcome. Primary care patient safety incident reports (n=31333) previously expert-categorised by clinicians (training data) were processed using J48, SVM and Naïve Bayes.The SVM classifier was the highest scoring classifier for incident type (AUROC, 0.891) and severity of harm (AUROC, 0.708). Incident reports containing deaths were most easily classified, correctly identifying 72.82% of reports. In conclusion, supervised ML can be used to classify patient safety incident report categories. The severity classifier, whilst not accurate enough to replace manual processing, could provide a valuable screening tool for this critical aspect of patient safety.

Pharmacovigilance in China: development and challenges

Background Rational drug use and drug safety are becoming increasingly important concerns in China with the increasing public access to drugs and the health-care system, and this has led to the development of pharmacovigilance in China. Aim of the review To provide a brief introduction about pharmacovigilance in China in terms of system development, utilization and challenges. Method Relevant studies on pharmacovigilance related to the study aim was undertaken through literature search to synthesize the extracted data. Results The creation and evolvement of China's pharmacovigilance system spans across 30 years since 1989. The system consists of four progressing administrative layers: county, municipal, provincial and national levels. China has passed over 20 laws and regulations related to pharmacovigilance covering the processes of drug development, manufacture, distribution and use with the aim to guard drug safety. An online spontaneous self-reporting Adverse Drug Reaction (ADR) Monitoring System was established in 2003. ADRs are mainly reported by medical institutions, pharmaceutical manufacturers, and drug distributors. Currently there is no mandatory ADR reporting requirement for pharmaceutical manufacturers, and a proposed regulation under public comment will likely change this. China has started to build active pharmacovigilance surveillance programs in addition to the passive ADR reporting system. The China Food and Drug Administration has established the intensive Safety Monitoring Program and the National Adverse Drug Reaction Monitoring Sentinel Alliance Program based on electronic health records to further the efforts of ADR reporting, monitoring and analysis. Conclusion The practice of ADR monitoring and pharmacovigilance in China have made great progress. More efforts are needed both in system building, and creation of laws and regulations to strengthen the safe use of medicines.

Ontology-based literature mining and class effect analysis of adverse drug reactions associated with neuropathy-inducing drugs

BACKGROUND

Adverse drug reactions (ADRs), also called as drug adverse events (AEs), are reported in the FDA drug labels; however, it is a big challenge to properly retrieve and analyze the ADRs and their potential relationships from textual data. Previously, we identified and ontologically modeled over 240 drugs that can induce peripheral neuropathy through mining public drug-related databases and drug labels. However, the ADR mechanisms of these drugs are still unclear. In this study, we aimed to develop an ontology-based literature mining system to identify ADRs from drug labels and to elucidate potential mechanisms of the neuropathy-inducing drugs (NIDs).

RESULTS

We developed and applied an ontology-based SciMiner literature mining strategy to mine ADRs from the drug labels provided in the Text Analysis Conference (TAC) 2017, which included drug labels for 53 neuropathy-inducing drugs (NIDs). We identified an average of 243 ADRs per NID and constructed an ADR-ADR network, which consists of 29 ADR nodes and 149 edges, including only those ADR-ADR pairs found in at least 50% of NIDs. Comparison to the ADR-ADR network of non-NIDs revealed that the ADRs such as pruritus, pyrexia, thrombocytopenia, nervousness, asthenia, acute lymphocytic leukaemia were highly enriched in the NID network. Our ChEBI-based ontology analysis identified three benzimidazole NIDs (i.e., lansoprazole, omeprazole, and pantoprazole), which were associated with 43 ADRs. Based on ontology-based drug class effect definition, the benzimidazole drug group has a drug class effect on all of these 43 ADRs. Many of these 43 ADRs also exist in the enriched NID ADR network. Our Ontology of Adverse Events (OAE) classification further found that these 43 benzimidazole-related ADRs were distributed in many systems, primarily in behavioral and neurological, digestive, skin, and immune systems.

CONCLUSIONS

Our study demonstrates that ontology-based literature mining and network analysis can efficiently identify and study specific group of drugs and their associated ADRs. Furthermore, our analysis of drug class effects identified 3 benzimidazole drugs sharing 43 ADRs, leading to new hypothesis generation and possible mechanism understanding of drug-induced peripheral neuropathy.

Evaluation of a Novel System to Enhance Clinicians' Recognition of Preadmission Adverse Drug Reactions

BACKGROUND

Often unrecognized by providers, adverse drug reactions (ADRs) diminish patients' quality of life, cause preventable admissions and emergency department visits, and increase health care costs.

OBJECTIVE

This article evaluates whether an automated system, the Adverse Drug Effect Recognizer (ADER), could assist clinicians in detecting and addressing inpatients' ongoing preadmission ADRs.

METHODS

ADER uses natural language processing to extract patients' medications, findings, and past diagnoses from admission notes. It compares excerpted information to a database of known medication adverse effects and promptly warns clinicians about potential ongoing ADRs and potential confounders via alerts placed in patients' electronic health records (EHRs). A 3-month intervention trial evaluated ADER's impact on antihypertensive medication ordering behaviors. At the time of patient admission, ADER warned providers on the Internal Medicine wards of Vanderbilt University Hospital about potential ongoing preadmission antihypertensive medication ADRs. A retrospective control group, comprised similar physicians from a period prior to the intervention, received no alerts. The evaluation compared ordering behaviors for each group to determine if preadmission medications changed during hospitalization or at discharge. The study also analyzed intervention group participants' survey responses and user comments.

RESULTS

ADER identified potential preadmission ADRs for 30% of both groups. Compared with controls, intervention providers more often withheld or discontinued suspected ADR-causing medications during the inpatient stay (p < 0.001). Intervention providers who responded to alert-related surveys held or discontinued suspected ADR-causing medications more often at discharge (p < 0.001).

CONCLUSION

Results indicate that ADER helped physicians recognize ADRs and reduced ordering of suspected ADR-causing medications. In hospitals using EHRs, ADER-like systems could improve clinicians' recognition and elimination of ongoing ADRs.

Development and validation of an algorithm to identify drug-induced anaphylaxis in the Beijing Pharmacovigilance Database

Background Pharmacovigilance databases are utilized to identify serious adverse drug events (ADEs). In China, very few studies have evaluated the validity of using pharmacovigilance databases to identify drug-induced anaphylaxis (DIA). Objective We aimed to develop and validate an algorithm to identify DIA using the Beijing Pharmacovigilance Database (BPD). Setting ADEs from the BPD mainly spontaneously reported from 94 hospitals in Beijing, China. Method Using the diagnoses, we developed an algorithm to identify potential DIAs from the BPD between January 2004 and December 2014. A sample of 500 patients was randomly selected for chart abstraction. Two physician adjudicators assessed whether DIA occurred using the published clinical criteria as the gold standard. Main outcome measure Positive predictive values (PPVs) and 95% confidence intervals of the algorithm and algorithm criteria components were calculated. Results 500 patients (53.2% female; the mean age 48.2 years) with potential DIA were selected using the algorithm. 444 were adjudicated as having anaphylaxis by physicians. The PPV of the overall algorithm was 88.8% (95% CI 86.0-91.6%). PPV for the algorithm only using specific diagnoses of "anaphylactic shock", "anaphylactic reaction", and "anaphylactoid reaction [severe]" was 89.6% (95% CI 86.6-92.4%); this partial algorithm identified 387 (87.2%) DIAs. The diagnosis that identified the most DIAs (83.8%) was "anaphylactic shock", with a PPV of 91.6% (95% CI 88.9-94.3%). Conclusion The overall algorithm identified a greater number of DIAs than the algorithm that only used specific diagnoses; however, its PPV was slightly lower. We were able to identify DIAs with the algorithm we developed.

Automated Screening of Emergency Department Notes for Drug-Associated Bleeding Adverse Events Occurring in Older Adults

Objective To conduct research to show the value of text mining for automatically identifying suspected bleeding adverse drug events (ADEs) in the emergency department (ED). Methods A corpus of ED admission notes was manually annotated for bleeding ADEs. The notes were taken for patients ≥ 65 years of age who had an ICD-9 code for bleeding, the presence of hemoglobin value ≤ 8 g/dL, or were transfused > 2 units of packed red blood cells. This training corpus was used to develop bleeding ADE algorithms using Random Forest and Classification and Regression Tree (CART). A completely separate set of notes was annotated and used to test the classification performance of the final models using the area under the ROC curve (AUROC). Results The best performing CART resulted in an AUROC on the training set of 0.882. The model's AUROC on the test set was 0.827. At a sensitivity of 0.679, the model had a specificity of 0.908 and a positive predictive value (PPV) of 0.814. It had a relatively simple and intuitive structure consisting of 13 decision nodes and 14 leaf nodes. Decision path probabilities ranged from 0.041 to 1.0. The AUROC for the best performing Random Forest method on the training set was 0.917. On the test set, the model's AUROC was 0.859. At a sensitivity of 0.274, the model had a specificity of 0.986 and a PPV of 0.92. Conclusion Both models accurately identify bleeding ADEs using the presence or absence of certain clinical concepts in ED admission notes for older adult patients. The CART model is particularly noteworthy because it does not require significant technical overhead to implement. Future work should seek to replicate the results on a larger test set pulled from another institution.

Content Analysis of Student Essays after Attending a Problem-Based Learning Course: Facilitating the Development of Critical Thinking and Communication Skills in Japanese Nursing Students

The importance of active learning has continued to increase in Japan. The authors conducted classes for first-year students who entered the nursing program using the problem-based learning method which is a kind of active learning. Students discussed social topics in classes. The purposes of this study were to analyze the post-class essay, describe logical and critical thinking after attended a Problem-Based Learning (PBL) course. The authors used Mayring's methodology for qualitative content analysis and text mining. In the description about the skills required to resolve social issues, seven categories were extracted: (recognition of diverse social issues), (attitudes about resolving social issues), (discerning the root cause), (multi-lateral information processing skills), (making a path to resolve issues), (processivity in dealing with issues), and (reflecting). In the description about communication, five categories were extracted: (simple statement), (robust theories), (respecting the opponent), (communication skills), and (attractive presentations). As the result of text mining, the words extracted more than 100 times included "issue," "society," "resolve," "myself," "ability," "opinion," and "information." Education using PBL could be an effective means of improving skills that students described, and communication in general. Some students felt difficulty of communication resulting from characteristics of Japanese.

Pilot Algorithm Designed to Help Early Detection of HMG-CoA Reductase Inhibitor-Induced Hepatotoxicity

Objectives

To enable early detection of adverse drug reactions (ADRs) in patients using HMG-CoA reductase inhibitors (statins), we developed an algorithm that automatically detects liver injury caused by statins from Electronic Medical Record (EMR) data. We verified the performance of our algorithm through manual ADR assessment and a direct chart review.

Methods

The subjects in this study were patients who had been prescribed a statin for the first time among outpatients in Seoul St. Mary's Hospital in Korea between January 2009 and December 2012. We extracted basic information about the patients, including laboratory information, underlying disease, diagnosis information, prescription information, and concomitant drugs. We developed an automatic ADR detection algorithm by using EMR data. We validated the results of the algorithm through a chart review.

Results

We developed the algorithm to assess ADR occurrences based on alanine transaminase (ALT) and alkaline phosphatase (ALP) levels. According to the proposed algorithm, any of these result options could be attained: ADR-free, little association, strong association, and weak association or indeterminable. The results of the ADR assessments obtained using the proposed algorithm showed that the data of 126 patients (1.4% of all 9,241 patients) included suspicious figures, thus indicating the possibility of an ADR. In the EMR chart review for verifying the algorithm, ADRs of 33 patients were not associated with statin use; therefore, the ADR occurrence rate was found to be 1.0% (93/9,241). Therefore, the positive predictive value was calculated to be 73.8% (93/126; 95% confidence interval, 69.2%–77.6%). No differences were observed between statin types (p = 0.472).

Conclusions

For early detection of statin-induced liver injury, we developed an automatic ADR assessment algorithm. We expect that algorithms that are more reliable can be developed if we conduct supplement clinical studies with a focus on adverse drug effects.

LSTM-CRF for Drug-Named Entity Recognition

Drug-Named Entity Recognition (DNER) for biomedical literature is a fundamental facilitator of Information Extraction. For this reason, the DDIExtraction2011 (DDI2011) and DDIExtraction2013 (DDI2013) challenge introduced one task aiming at recognition of drug names. State-of-the-art DNER approaches heavily rely on hand-engineered features and domain-specific knowledge which are difficult to collect and define. Therefore, we offer an automatic exploring words and characters level features approach: a recurrent neural network using bidirectional long short-term memory (LSTM) with Conditional Random Fields decoding (LSTM-CRF). Two kinds of word representations are used in this work: word embedding, which is trained from a large amount of text, and character-based representation, which can capture orthographic feature of words. Experimental results on the DDI2011 and DDI2013 dataset show the effect of the proposed LSTM-CRF method. Our method outperforms the best system in the DDI2013 challenge.

Text mining applied to electronic cardiovascular procedure reports to identify patients with trileaflet aortic stenosis and coronary artery disease

BACKGROUND

Interrogation of the electronic health record (EHR) using billing codes as a surrogate for diagnoses of interest has been widely used for clinical research. However, the accuracy of this methodology is variable, as it reflects billing codes rather than severity of disease, and depends on the disease and the accuracy of the coding practitioner. Systematic application of text mining to the EHR has had variable success for the detection of cardiovascular phenotypes. We hypothesize that the application of text mining algorithms to cardiovascular procedure reports may be a superior method to identify patients with cardiovascular conditions of interest.

METHODS

We adapted the Oracle product Endeca, which utilizes text mining to identify terms of interest from a NoSQL-like database, for purposes of searching cardiovascular procedure reports and termed the tool "PennSeek". We imported 282,569 echocardiography reports representing 81,164 individuals and 27,205 cardiac catheterization reports representing 14,567 individuals from non-searchable databases into PennSeek. We then applied clinical criteria to these reports in PennSeek to identify patients with trileaflet aortic stenosis (TAS) and coronary artery disease (CAD). Accuracy of patient identification by text mining through PennSeek was compared with ICD-9 billing codes.

RESULTS

Text mining identified 7115 patients with TAS and 9247 patients with CAD. ICD-9 codes identified 8272 patients with TAS and 6913 patients with CAD. 4346 patients with AS and 6024 patients with CAD were identified by both approaches. A randomly selected sample of 200-250 patients uniquely identified by text mining was compared with 200-250 patients uniquely identified by billing codes for both diseases. We demonstrate that text mining was superior, with a positive predictive value (PPV) of 0.95 compared to 0.53 by ICD-9 for TAS, and a PPV of 0.97 compared to 0.86 for CAD.

CONCLUSION

These results highlight the superiority of text mining algorithms applied to electronic cardiovascular procedure reports in the identification of phenotypes of interest for cardiovascular research.

Using multiclass classification to automate the identification of patient safety incident reports by type and severity

BACKGROUND

Approximately 10% of admissions to acute-care hospitals are associated with an adverse event. Analysis of incident reports helps to understand how and why incidents occur and can inform policy and practice for safer care. Unfortunately our capacity to monitor and respond to incident reports in a timely manner is limited by the sheer volumes of data collected. In this study, we aim to evaluate the feasibility of using multiclass classification to automate the identification of patient safety incidents in hospitals.

METHODS

Text based classifiers were applied to identify 10 incident types and 4 severity levels. Using the one-versus-one (OvsO) and one-versus-all (OvsA) ensemble strategies, we evaluated regularized logistic regression, linear support vector machine (SVM) and SVM with a radial-basis function (RBF) kernel. Classifiers were trained and tested with "balanced" datasets (n_ _Type  = 2860, n_ _{SeverityLevel}  = 1160) from a state-wide incident reporting system. Testing was also undertaken with imbalanced "stratified" datasets (n_ _Type  = 6000, n_ _{SeverityLevel} =5950) from the state-wide system and an independent hospital reporting system. Classifier performance was evaluated using a confusion matrix, as well as F-score, precision and recall.

RESULTS

The most effective combination was a OvsO ensemble of binary SVM RBF classifiers with binary count feature extraction. For incident type, classifiers performed well on balanced and stratified datasets (F-score: 78.3, 73.9%), but were worse on independent datasets (68.5%). Reports about falls, medications, pressure injury, aggression and blood products were identified with high recall and precision. "Documentation" was the hardest type to identify. For severity level, F-score for severity assessment code (SAC) 1 (extreme risk) was 87.3 and 64% for SAC4 (low risk) on balanced data. With stratified data, high recall was achieved for SAC1 (82.8-84%) but precision was poor (6.8-11.2%). High risk incidents (SAC2) were confused with medium risk incidents (SAC3).

CONCLUSIONS

Binary classifier ensembles appear to be a feasible method for identifying incidents by type and severity level. Automated identification should enable safety problems to be detected and addressed in a more timely manner. Multi-label classifiers may be necessary for reports that relate to more than one incident type.

Information Retrieval and Text Mining Technologies for Chemistry

Efficient access to chemical information contained in scientific literature, patents, technical reports, or the web is a pressing need shared by researchers and patent attorneys from different chemical disciplines. Retrieval of important chemical information in most cases starts with finding relevant documents for a particular chemical compound or family. Targeted retrieval of chemical documents is closely connected to the automatic recognition of chemical entities in the text, which commonly involves the extraction of the entire list of chemicals mentioned in a document, including any associated information. In this Review, we provide a comprehensive and in-depth description of fundamental concepts, technical implementations, and current technologies for meeting these information demands. A strong focus is placed on community challenges addressing systems performance, more particularly CHEMDNER and CHEMDNER patents tasks of BioCreative IV and V, respectively. Considering the growing interest in the construction of automatically annotated chemical knowledge bases that integrate chemical information and biological data, cheminformatics approaches for mapping the extracted chemical names into chemical structures and their subsequent annotation together with text mining applications for linking chemistry with biological information are also presented. Finally, future trends and current challenges are highlighted as a roadmap proposal for research in this emerging field.

Data Requirements for the Correct Identification of Medication Errors and Adverse Drug Events in Patients Presenting at an Emergency Department

BACKGROUND

Adverse drug events (ADE) involving or not involving medication errors (ME) are common, but frequently remain undetected as such. Presently, the majority of available clinical decision support systems (CDSS) relies mostly on coded medication data for the generation of drug alerts. It was the aim of our study to identify the key types of data required for the adequate detection and classification of adverse drug events (ADE) and medication errors (ME) in patients presenting at an emergency department (ED).

METHODS

As part of a prospective study, ADE and ME were identified in 1510 patients presenting at the ED of an university teaching hospital by an interdisciplinary panel of specialists in emergency medicine, clinical pharmacology and pharmacy. For each ADE and ME the required different clinical data sources (i.e. information items such as acute clinical symptoms, underlying diseases, laboratory values or ECG) for the detection and correct classification were evaluated.

RESULTS

Of all 739 ADE identified 387 (52.4%), 298 (40.3%), 54 (7.3%), respectively, required one, two, or three, more information items to be detected and correctly classified. Only 68 (10.2%) of the ME were simple drug-drug interactions that could be identified based on medication data alone while 381 (57.5%), 181 (27.3%) and 33 (5.0%) of the ME required one, two or three additional information items, respectively, for detection and clinical classification.

CONCLUSIONS

Only 10% of all ME observed in emergency patients could be identified on the basis of medication data alone. Focusing electronic decisions support on more easily available drug data alone may lead to an under-detection of clinically relevant ADE and ME.

A Text Searching Tool to Identify Patients with Idiosyncratic Drug-Induced Liver Injury

BACKGROUND

Idiosyncratic drug-induced liver injury (DILI) is an uncommon but important cause of liver disease that is challenging to diagnose and identify in the electronic medical record (EMR).

AIM

To develop an accurate, reliable, and efficient method of identifying patients with bonafide DILI in an EMR system.

METHODS

In total, 527,000 outpatient and ER encounters in an EPIC-based EMR were searched for potential DILI cases attributed to eight drugs. A searching algorithm that extracted 200 characters of text around 14 liver injury terms in the EMR were extracted and collated. Physician investigators reviewed the data outputs and used standardized causality assessment methods to adjudicate the potential DILI cases.

RESULTS

A total of 101 DILI cases were identified from the 2564 potential DILI cases that included 62 probable DILI cases, 25 possible DILI cases, nine historical DILI cases, and five allergy-only cases. Elimination of the term "liver disease" from the search strategy improved the search recall from 4 to 19 %, while inclusion of the four highest yield liver injury terms further improved the positive predictive value to 64 % but reduced the overall case detection rate by 47 %. RUCAM scores of the 57 probable DILI cases were generally high and concordant with expert opinion causality assessment scores.

CONCLUSIONS

A novel text searching tool was developed that identified a large number of DILI cases from a widely used EMR system. A computerized extraction of dictated text followed by the manual review of text snippets can rapidly identify bona fide cases of idiosyncratic DILI.

What Can Big Data Offer the Pharmacovigilance of Orphan Drugs?

The pharmacovigilance of drugs for orphan diseases presents problems related to the small patient population. Obtaining high-quality information on individual reports of suspected adverse reactions is of particular importance for the pharmacovigilance of orphan drugs. The possibility of mining "big data" to detect suspected adverse reactions is being explored in pharmacovigilance generally but may have limited application to orphan drugs. Sources of big data such as social media may be infrequently used as communication channels by patients with rare disease or their caregivers or by health care providers; any adverse reactions identified are likely to reflect what is already known about the safety of the drug from the network of support that grows up around these patients. Opportunities related to potential future big data sources are discussed.

Improving drug safety: From adverse drug reaction knowledge discovery to clinical implementation

Adverse drug reactions (ADRs) are a major public health concern, causing over 100,000 fatalities in the United States every year with an annual cost of $136 billion. Early detection and accurate prediction of ADRs is thus vital for drug development and patient safety. Multiple scientific disciplines, namely pharmacology, pharmacovigilance, and pharmacoinformatics, have been addressing the ADR problem from different perspectives. With the same goal of improving drug safety, this article summarizes and links the research efforts in the multiple disciplines into a single framework from comprehensive understanding of the interactions between drugs and biological system and the identification of genetic and phenotypic predispositions of patients susceptible to higher ADR risks and finally to the current state of implementation of medication-related decision support systems. We start by describing available computational resources for building drug-target interaction networks with biological annotations, which provides a fundamental knowledge for ADR prediction. Databases are classified by functions to help users in selection. Post-marketing surveillance is then introduced where data-driven approach can not only enhance the prediction accuracy of ADRs but also enables the discovery of genetic and phenotypic risk factors of ADRs. Understanding genetic risk factors for ADR requires well organized patient genetics information and analysis by pharmacogenomic approaches. Finally, current state of clinical decision support systems is presented and described how clinicians can be assisted with the integrated knowledgebase to minimize the risk of ADR. This review ends with a discussion of existing challenges in each of disciplines with potential solutions and future directions.

Developing an Algorithm to Detect Early Childhood Obesity in Two Tertiary Pediatric Medical Centers

OBJECTIVE

The objective of this study is to develop an algorithm to accurately identify children with severe early onset childhood obesity (ages 1-5.99 years) using structured and unstructured data from the electronic health record (EHR).

INTRODUCTION

Childhood obesity increases risk factors for cardiovascular morbidity and vascular disease. Accurate definition of a high precision phenotype through a standardize tool is critical to the success of large-scale genomic studies and validating rare monogenic variants causing severe early onset obesity.

DATA AND METHODS

Rule based and machine learning based algorithms were developed using structured and unstructured data from two EHR databases from Boston Children's Hospital (BCH) and Cincinnati Children's Hospital and Medical Center (CCHMC). Exclusion criteria including medications or comorbid diagnoses were defined. Machine learning algorithms were developed using cross-site training and testing in addition to experimenting with natural language processing features.

RESULTS

Precision was emphasized for a high fidelity cohort. The rule-based algorithm performed the best overall, 0.895 (CCHMC) and 0.770 (BCH). The best feature set for machine learning employed Unified Medical Language System (UMLS) concept unique identifiers (CUIs), ICD-9 codes, and RxNorm codes.

CONCLUSIONS

Detecting severe early childhood obesity is essential for the intervention potential in children at the highest long-term risk of developing comorbidities related to obesity and excluding patients with underlying pathological and non-syndromic causes of obesity assists in developing a high-precision cohort for genetic study. Further such phenotyping efforts inform future practical application in health care environments utilizing clinical decision support.

Using Literature-Based Discovery to Explain Adverse Drug Effects

We report on our research in using literature-based discovery (LBD) to provide pharmacological and/or pharmacogenomic explanations for reported adverse drug effects. The goal of LBD is to generate novel and potentially useful hypotheses by analyzing the scientific literature and optionally some additional resources. Our assumption is that drugs have effects on some genes or proteins and that these genes or proteins are associated with the observed adverse effects. Therefore, by using LBD we try to find genes or proteins that link the drugs with the reported adverse effects. These genes or proteins can be used to provide insight into the processes causing the adverse effects. Initial results show that our method has the potential to assist in explaining reported adverse drug effects.

Switch in Therapy from Methylphenidate to Atomoxetine in Children and Adolescents with Attention-Deficit/Hyperactivity Disorder: An Analysis of Patient Records

OBJECTIVE

The purpose of this study was to investigate therapy switching from methylphenidate (MPH) to atomoxetine (ATX) in a clinical sample of Danish children and adolescents with attention-deficit/hyperactivity disorder (ADHD); specifically, to determine the duration of MPH treatment before switching to ATX, and the reasons leading to a switch in therapy.

METHODS

We included 55 patients with ADHD who switched from first-line MPH to second-line ATX during January 01, 2012 and May 15, 2014. Patient and treatment characteristics along with clinical reasons for switching therapy were extracted from individual patients' records.

RESULTS

Mean duration of MPH treatment until switch to ATX was 11.2 months (range = 0.3-28.5 months); 36% of the patients switched within the first 6 months, 56% within the first year, and 76% within 1.5 years of initiating MPH; 24% continued MPH treatment for up to 2.5 years prior to switching. Most common reasons for switching were "adverse events" (AEs) (78%), "wish for more optimal day coverage" (24%), and "lack of efficacy" (16%). Other reasons for switching included "patient/parental request" (13%) and "noncompliance" (2%). Most common AEs leading to switch were psychiatric disorders (insomnia, aggression, tic, depression, anxiety) and decreased appetite.

CONCLUSIONS

Our findings highlight the importance of continuous evaluation of the need for prescription switch to ATX in children and adolescents treated with MPH, taking into consideration various factors including potential AEs, non-optimal day coverage, lack of efficacy, patient/parental preferences, and noncompliance. These factors should be considered, not only at the initial stage of MPH treatment but throughout the whole treatment course.

Identification of major cardiovascular events in patients with diabetes using primary care data

Background

Routine primary care data are increasingly being used for evaluation and research purposes but there are concerns about the completeness and accuracy of diagnoses and events captured in such databases. We evaluated how well patients with major cardiovascular disease (CVD) can be identified using primary care morbidity data and drug prescriptions.

Methods

The study was conducted using data from 17,230 diabetes patients of the GIANTT database and Dutch Hospital Data register. To estimate the accuracy of the different measures, we analyzed the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) relative to hospitalizations and/or records with a diagnosis indicating major CVD, including ischaemic heart diseases and cerebrovascular events.

Results

Using primary care morbidity data, 43 % of major CVD hospitalizations could be identified. Adding drug prescriptions to the search increased the sensitivity up to 94 %. A proxy of at least one prescription of either a platelet aggregation inhibitor, vitamin k antagonist or nitrate could identify 85 % of patients with a history of major CVD recorded in primary care, with an NPV of 97 %. Using the same proxy, 57 % of incident major CVD recorded in primary or hospital care could be identified, with an NPV of 99 %.

Conclusions

A substantial proportion of major CVD hospitalizations was not recorded in primary care morbidity data. Drug prescriptions can be used in addition to diagnosis codes to identify more patients with major CVD, and also to identify patients without a history of major CVD.

Electronic supplementary material

The online version of this article (doi:10.1186/s12913-016-1361-2) contains supplementary material, which is available to authorized users.

Leveraging MEDLINE indexing for pharmacovigilance - Inherent limitations and mitigation strategies

BACKGROUND

Traditional approaches to pharmacovigilance center on the signal detection from spontaneous reports, e.g., the U.S. Food and Drug Administration (FDA) adverse event reporting system (FAERS). In order to enrich the scientific evidence and enhance the detection of emerging adverse drug events that can lead to unintended harmful outcomes, pharmacovigilance activities need to evolve to encompass novel complementary data streams, for example the biomedical literature available through MEDLINE.

OBJECTIVES

(1) To review how the characteristics of MEDLINE indexing influence the identification of adverse drug events (ADEs); (2) to leverage this knowledge to inform the design of a system for extracting ADEs from MEDLINE indexing; and (3) to assess the specific contribution of some characteristics of MEDLINE indexing to the performance of this system.

METHODS

We analyze the characteristics of MEDLINE indexing. We integrate three specific characteristics into the design of a system for extracting ADEs from MEDLINE indexing. We experimentally assess the specific contribution of these characteristics over a baseline system based on co-occurrence between drug descriptors qualified by adverse effects and disease descriptors qualified by chemically induced.

RESULTS

Our system extracted 405,300 ADEs from 366,120 MEDLINE articles. The baseline system accounts for 297,093 ADEs (73%). 85,318 ADEs (21%) can be extracted only after integrating specific pre-coordinated MeSH descriptors and additional qualifiers. 22,889 ADEs (6%) can be extracted only after considering indirect links between the drug of interest and the descriptor that bears the ADE context.

CONCLUSIONS

In this paper, we demonstrate significant improvement over a baseline approach to identifying ADEs from MEDLINE indexing, which mitigates some of the inherent limitations of MEDLINE indexing for pharmacovigilance. ADEs extracted from MEDLINE indexing are complementary to, not a replacement for, other sources.

Adverse Drug Reaction Identification and Extraction in Social Media: A Scoping Review

Background

The underreporting of adverse drug reactions (ADRs) through traditional reporting channels is a limitation in the efficiency of the current pharmacovigilance system. Patients’ experiences with drugs that they report on social media represent a new source of data that may have some value in postmarketing safety surveillance.

Objective

A scoping review was undertaken to explore the breadth of evidence about the use of social media as a new source of knowledge for pharmacovigilance.

Methods

Daubt et al’s recommendations for scoping reviews were followed. The research questions were as follows: How can social media be used as a data source for postmarketing drug surveillance? What are the available methods for extracting data? What are the different ways to use these data? We queried PubMed, Embase, and Google Scholar to extract relevant articles that were published before June 2014 and with no lower date limit. Two pairs of reviewers independently screened the selected studies and proposed two themes of review: manual ADR identification (theme 1) and automated ADR extraction from social media (theme 2). Descriptive characteristics were collected from the publications to create a database for themes 1 and 2.

Results

Of the 1032 citations from PubMed and Embase, 11 were relevant to the research question. An additional 13 citations were added after further research on the Internet and in reference lists. Themes 1 and 2 explored 11 and 13 articles, respectively. Ways of approaching the use of social media as a pharmacovigilance data source were identified.

Conclusions

This scoping review noted multiple methods for identifying target data, extracting them, and evaluating the quality of medical information from social media. It also showed some remaining gaps in the field. Studies related to the identification theme usually failed to accurately assess the completeness, quality, and reliability of the data that were analyzed from social media. Regarding extraction, no study proposed a generic approach to easily adding a new site or data source. Additional studies are required to precisely determine the role of social media in the pharmacovigilance system.

Identification of possible adverse drug reactions in clinical notes: The case of glucose-lowering medicines

Objective:

Through manual review of clinical notes for patients with type 2 diabetes mellitus attending a Danish diabetes center, the aim of the study was to identify adverse drug reactions (ADRs) associated with three classes of glucose-lowering medicines: “Combinations of oral blood-glucose lowering medicines” (A10BD), “dipeptidyl peptidase-4 (DDP-4) inhibitors” (A10BH), and “other blood glucose lowering medicines” (A10BX). Specifically, we aimed to describe the potential of clinical notes to identify new ADRs and to evaluate if sufficient information can be obtained for causality assessment.

Methods:

For observed adverse events (AEs) we extracted time to onset, outcome, and suspected medicine(s). AEs were assessed according to World Health Organization-Uppsala Monitoring Centre causality criteria and analyzed with respect to suspected medicines, type of ADR (system organ class), seriousness and labeling status.

Findings:

A total of 207 patients were included in the study leading to the identification of 163 AEs. 14% were categorized as certain, 60% as probable/likely, and 26% as possible. 15 (9%) ADRs were unlabeled of which two were serious: peripheral edema associated with sitagliptin and stomach ulcer associated with liraglutide. Of the unlabeled ADRs, 13 (87%) were associated with “other blood glucose lowering medications,” the remaining 2 (13%) with “DDP-4 inhibitors.”

Conclusion:

Clinical notes could potentially reveal unlabeled ADRs associated with prescribed medicines and sufficient information is generally available for causality assessment. However, manual review of clinical notes is too time-consuming for routine use and hence there is a need for developing information technology (IT) tools for automatic screening of patient records with the purpose to detect information about potentially serious and unlabeled ADRs.

Role of text mining in early identification of potential drug safety issues

Drugs are an important part of today's medicine, designed to treat, control, and prevent diseases; however, besides their therapeutic effects, drugs may also cause adverse effects that range from cosmetic to severe morbidity and mortality. To identify these potential drug safety issues early, surveillance must be conducted for each drug throughout its life cycle, from drug development to different phases of clinical trials, and continued after market approval. A major aim of pharmacovigilance is to identify the potential drug-event associations that may be novel in nature, severity, and/or frequency. Currently, the state-of-the-art approach for signal detection is through automated procedures by analyzing vast quantities of data for clinical knowledge. There exists a variety of resources for the task, and many of them are textual data that require text analytics and natural language processing to derive high-quality information. This chapter focuses on the utilization of text mining techniques in identifying potential safety issues of drugs from textual sources such as biomedical literature, consumer posts in social media, and narrative electronic medical records.