A supervised adverse drug reaction signalling framework imitating Bradford Hill's causality considerations

Large language model aided automatic high-throughput drug screening using self-controlled cohort study

Background

Developing medicine from scratch to governmental authorization and detecting adverse drug reactions (ADR) have barely been economical, expeditious, and risk-averse investments. The availability of large-scale observational healthcare databases and the popularity of large language models offer an unparalleled opportunity to enable automatic high-throughput drug screening for both repurposing and pharmacovigilance.

Objectives

To demonstrate a general workflow for automatic high-throughput drug screening with the following advantages: (i) the association of various exposure on diseases can be estimated; (ii) both repurposing and pharmacovigilance are integrated; (iii) accurate exposure length for each prescription is parsed from clinical texts; (iv) intrinsic relationship between drugs and diseases are removed jointly by bioinformatic mapping and large language model - ChatGPT; (v) causal-wise interpretations for incidence rate contrasts are provided.

Methods

Using a self-controlled cohort study design where subjects serve as their own control group, we tested the intention-to-treat association between medications on the incidence of diseases. Exposure length for each prescription is determined by parsing common dosages in English free text into a structured format. Exposure period starts from initial prescription to treatment discontinuation. A same exposure length preceding initial treatment is the control period. Clinical outcomes and categories are identified using existing phenotyping algorithms. Incident rate ratios (IRR) are tested using uniformly most powerful (UMP) unbiased tests.

Results

We assessed 3,444 medications on 276 diseases on 6,613,198 patients from the Clinical Practice Research Datalink (CPRD), an UK primary care electronic health records (EHR) spanning from 1987 to 2018. Due to the built-in selection bias of self-controlled cohort studies, ingredients-disease pairs confounded by deterministic medical relationships are removed by existing map from RxNorm and nonexistent maps by calling ChatGPT. A total of 16,901 drug-disease pairs reveals significant risk reduction, which can be considered as candidates for repurposing, while a total of 11,089 pairs showed significant risk increase, where drug safety might be of a concern instead.

Conclusions

This work developed a data-driven, nonparametric, hypothesis generating, and automatic high-throughput workflow, which reveals the potential of natural language processing in pharmacoepidemiology. We demonstrate the paradigm to a large observational health dataset to help discover potential novel therapies and adverse drug effects. The framework of this study can be extended to other observational medical databases.

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.

Exploratory pharmacovigilance with machine learning in big patient data: A focused scoping review

BACKGROUND

Machine learning can operationalize the rich and complex data in electronic patient records for exploratory pharmacovigilance endeavours.

OBJECTIVE

The objective of this review is to identify applications of machine learning and big patient data in exploratory pharmacovigilance.

METHODS

We searched PubMed and Embase and included original articles with an exploratory pharmacovigilance purpose, focusing on medicinal interventions and reporting the use of machine learning in electronic patient records with ≥1000 patients collected after market entry.

FINDINGS

Of 2557 studies screened, seven were included. Those covered six countries and were published between 2015 and 2021. The most prominent machine learning methods were random forests, logistic regressions, and support vector machines. Two studies used artificial neural networks or naive Bayes classifiers. One study used formal concept analysis for association mining, and another used temporal difference learning. Five studies compared several methods against each other. The numbers of patients in most data sets were in the order of thousands; two studies used what can more reasonably be considered big data with >1 000 000 patients records.

CONCLUSION

Despite years of great aspirations for combining machine learning and clinical data for exploratory pharmacovigilance, only few studies still seem to deliver somewhat on these expectations.

Methods for drug safety signal detection using routinely collected observational electronic health care data: A systematic review

PURPOSE

Signal detection is a crucial step in the discovery of post-marketing adverse drug reactions. There is a growing interest in using routinely collected data to complement established spontaneous report analyses. This work aims to systematically review the methods for drug safety signal detection using routinely collected healthcare data and their performance, both in general and for specific types of drugs and outcomes.

METHODS

We conducted a systematic review following the PRISMA guidelines, and registered a protocol in PROSPERO. MEDLINE, EMBASE, PubMed, Web of Science, Scopus, and the Cochrane Library were searched until July 13, 2021.

RESULTS

The review included 101 articles, among which there were 39 methodological works, 25 performance assessment papers, and 24 observational studies. Methods included adaptations from those used with spontaneous reports, traditional epidemiological designs, methods specific to signal detection with real-world data. More recently, implementations of machine learning have been studied in the literature. Twenty-five studies evaluated method performances, 16 of them using the area under the curve (AUC) for a range of positive and negative controls as their main measure. Despite the likelihood that performance measurement could vary by drug-event pair, only 10 studies reported performance stratified by drugs and outcomes, in a heterogeneous manner. The replicability of the performance assessment results was limited due to lack of transparency in reporting and the lack of a gold standard reference set.

CONCLUSIONS

A variety of methods have been described in the literature for signal detection with routinely collected data. No method showed superior performance in all papers and across all drugs and outcomes, performance assessment and reporting were heterogeneous. However, there is limited evidence that self-controlled designs, high dimensional propensity scores, and machine learning can achieve higher performances than other methods.

Applying Machine Learning in Distributed Data Networks for Pharmacoepidemiologic and Pharmacovigilance Studies: Opportunities, Challenges, and Considerations

Increasing availability of electronic health databases capturing real-world experiences with medical products has garnered much interest in their use for pharmacoepidemiologic and pharmacovigilance studies. The traditional practice of having numerous groups use single databases to accomplish similar tasks and address common questions about medical products can be made more efficient through well-coordinated multi-database studies, greatly facilitated through distributed data network (DDN) architectures. Access to larger amounts of electronic health data within DDNs has created a growing interest in using data-adaptive machine learning (ML) techniques that can automatically model complex associations in high-dimensional data with minimal human guidance. However, the siloed storage and diverse nature of the databases in DDNs create unique challenges for using ML. In this paper, we discuss opportunities, challenges, and considerations for applying ML in DDNs for pharmacoepidemiologic and pharmacovigilance studies. We first discuss major types of activities performed by DDNs and how ML may be used. Next, we discuss practical data-related factors influencing how DDNs work in practice. We then combine these discussions and jointly consider how opportunities for ML are affected by practical data-related factors for DDNs, leading to several challenges. We present different approaches for addressing these challenges and highlight efforts that real-world DDNs have taken or are currently taking to help mitigate them. Despite these challenges, the time is ripe for the emerging interest to use ML in DDNs, and the utility of these data-adaptive modeling techniques in pharmacoepidemiologic and pharmacovigilance studies will likely continue to increase in the coming years.

A novel method for predicting the progression rate of ALS disease based on automatic generation of probabilistic causal chains

Causal discovery is considered as a major concept in biomedical informatics contributing to diagnosis, therapy, and prognosis of diseases. Probabilistic causality approaches in epidemiology and medicine is a common method for finding relationships between pathogen and disease, environment and disease, and adverse events and drugs. Bayesian Network (BN) is one of the common approaches for probabilistic causality, which is widely used in health-care and biomedical science. Since in many biomedical applications we deal with temporal dataset, the temporal extension of BNs called Dynamic Bayesian network (DBN) is used for such applications. DBNs define probabilistic relationships between parameters in consecutive time points in the form of a graph and have been successfully used in many biomedical applications. In this paper, a novel method was introduced for finding probabilistic causal chains from a temporal dataset with the help of entropy and causal tendency measures. In this method, first, Causal Features Dependency (CFD) matrix is created on the basis of parameters changes in consecutive events of a phenomenon, and then the probabilistic causal graph is constructed from this matrix based on entropy criteria. At the next step, a set of probabilistic causal chains of the corresponding causal graph is constructed by a novel polynomial-time heuristic. Finally, the causal chains are used for predicting the future trend of the phenomenon. The proposed model was applied to the Pooled Resource Open-Access Clinical Trials (PRO-ACT) dataset related to Amyotrophic Lateral Sclerosis (ALS) disease, in order to predict the progression rate of this disease. The results of comparison with Bayesian tree, random forest, support vector regression, linear regression, and multivariate regression show that the proposed algorithm can compete with these methods and in some cases outperforms other algorithms. This study revealed that probabilistic causality is an appropriate approach for predicting the future states of chronic diseases with unknown cause.

Causality Assessment of Adverse Drug Reaction: Controlling Confounding Induced by Polypharmacy

BACKGROUND

Post-marketing pharmaceutical surveillance, a.k.a. pragmatic clinical trials (i.e., PCT), plays a vital role in preventing accidents in practical treatment. The most important and difficult task in PCT is to assess which drug causes adverse reactions (i.e., ADRs) from clinical texts. The confounding (i.e., factors cause confusions in causality assessment) is generated by the polypharmacy (i.e., multiple drugs use), which makes most of existing methods poor for detecting drugs that capably cause observed ADRs.

OBJECTIVE

We aim to improve the performance of detecting drug-ADR causal relations from clinical texts. To this end, a mechanism for reducing the impact of confounding on the detecting process is needful.

METHODS

We proposed a novel model which is called the analogy-based active voting (i.e., AAV) for improving the ability of detecting causal drug-ADR pairs, in case multiple drugs are prescribed for treating the comorbidity. This model is inspired by the analogy principle which was proposed by Bradford Hill.

RESULTS

The experimental results show the improvement of recognizing causal relations between drugs and ADRs that are confirmed by the SIDER. In addition, the proposed model is promising to detect infrequently observed causal drug-ADR pairs when the drug is not commonly used.

CONCLUSION

The proposed model demonstrates its ability for controlling the polypharmacy-induced confounding, to improve the quality of causality assessment of ADRs. Additionally, this also shows that the analogy principle is applicable for the assessment.

Efficacy of Capsaicin for the Treatment of Cannabinoid Hyperemesis Syndrome: A Systematic Review

Objective: Cannabinoid hyperemesis syndrome (CHS) is characterized by cyclic vomiting, abdominal pain, and alleviation of symptoms via hot showers in chronic cannabinoid users. Capsaicin is recommended as a reasonable first-line treatment approach for CHS despite limited clinical evidence regarding its use. The objective of this study is to systematically review the efficacy data for capsaicin in CHS. Data Sources: A literature search using keywords related to cannabinoids, emesis, and capsaicin was performed in MEDLINE, CINAHL, and EMBASE from inception through March 31, 2019. Study Selection and Data Extraction: Studies and published abstracts in which capsaicin was used for CHS and clinical outcomes were reported were eligible for inclusion. Data Synthesis: A total of 241 articles were screened, of which 5 full-text articles and 6 conference abstracts were included. Full-text case reports (n = 3) and case series (n = 2) found capsaicin to be effective in a total of 18 patients. Published abstracts were in the form of case reports (n = 1), case series (n = 3), and retrospective cohort studies (n = 2). Relevance to Patient Care and Clinical Practice: Capsaicin use was described as beneficial in all case series and case reports; however, both retrospective cohort studies were unable to find a significant benefit for capsaicin on primary outcomes (emergency department length of stay). Conclusion: Current data for capsaicin efficacy in CHS is of low methodological quality. However, the limited data on alternative antiemetic therapies and capsaicin’s favorable risk-benefit profile make it a reasonable adjunctive treatment option.

From Big Data to Smart Data for Pharmacovigilance: The Role of Healthcare Databases and Other Emerging Sources

In the last decade 'big data' has become a buzzword used in several industrial sectors, including but not limited to telephony, finance and healthcare. Despite its popularity, it is not always clear what big data refers to exactly. Big data has become a very popular topic in healthcare, where the term primarily refers to the vast and growing volumes of computerized medical information available in the form of electronic health records, administrative or health claims data, disease and drug monitoring registries and so on. This kind of data is generally collected routinely during administrative processes and clinical practice by different healthcare professionals: from doctors recording their patients' medical history, drug prescriptions or medical claims to pharmacists registering dispensed prescriptions. For a long time, this data accumulated without its value being fully recognized and leveraged. Today big data has an important place in healthcare, including in pharmacovigilance. The expanding role of big data in pharmacovigilance includes signal detection, substantiation and validation of drug or vaccine safety signals, and increasingly new sources of information such as social media are also being considered. The aim of the present paper is to discuss the uses of big data for drug safety post-marketing assessment.

Supervised signal detection for adverse drug reactions in medication dispensing data

MOTIVATION

Adverse drug reactions (ADRs) are one of the leading causes of morbidity and mortality and thus should be detected early to reduce consequences on health outcomes. Medication dispensing data are comprehensive sources of information about medicine uses that can be utilized for the signal detection of ADRs. Sequence symmetry analysis (SSA) has been employed in previous studies to detect signals of ADRs from medication dispensing data, but it has a moderate sensitivity and tends to miss some ADR signals. With successful applications in various areas, supervised machine learning (SML) methods are promising in detecting ADR signals. Gold standards of known ADRs and non- ADRs from previous studies create opportunities to take into account additional domain knowledge to improve ADR signal detection with SML.

OBJECTIVE

We assess the utility of SML as a signal detection tool for ADRs in medication dispensing data with the consideration of domain knowledge from DrugBank and MedDRA. We compare the best performing SML method with SSA.

METHODS

We model the ADR signal detection problem as a supervised machine learning problem by linking medication dispensing data with domain knowledge bases. Suspected ADR signals are extracted from the Australian Pharmaceutical Benefit Scheme (PBS) medication dispensing data from 2013 to 2016. We construct predictive features for each signal candidate based on its occurrences in medication dispensing data as well as its pharmacological properties. Pharmaceutical knowledge bases including DrugBank and MedDRA are employed to provide pharmacological features for a signal candidate. Given a gold standard of known ADRs and non-ADRs, SML learns to differentiate between known ADRs and non-ADRs based on their combined predictive features from linked sources, and then predicts whether a new case is a potential ADR signal.

RESULTS

We evaluate the performance of six widely used SML methods with two gold standards of known ADRs and non-ADRs from previous studies. On average, gradient boosting classifier achieves the sensitivity of 77%, specificity of 81%, positive predictive value of 76%, negative predictive value of 82%, area under precision-recall curve of 81%, and area under receiver operating characteristic curve of 82%, most of which are higher than in other SML methods. In particular, gradient boosting classifier has 21% higher sensitivity than and comparable specificity with SSA. Furthermore, gradient boosting classifier detects 10% more unknown potential ADR signals than SSA.

CONCLUSIONS

Our study demonstrates that gradient boosting classifier is a promising supervised signal detection tool for ADRs in medication dispensing data to complement SSA.

Side Effects of Long-Term Proton Pump Inhibitor Use: A Review

Proton pump inhibitors (PPIs) are widely used, and concerns about overuse have been raised. Therefore, side effects are important to be aware of and several suggested side effects of long-term use have been studied. In this MiniReview, we sum up the evidence of side effects related to long-term PPI treatment. Suspected side effects are mainly related to increased susceptibility to infections, secondary hypergastrinaemia, impeded absorption of micronutrients or idiosyncratic reactions. Most of the potential side effects have only been evaluated in observational studies demonstrating conflicting and weak associations with a substantial risk of confounding. However, a high probability of causality seems to be established for the side effects increased risk of gastrointestinal infections and rebound acid hypersecretion following discontinuation of treatment due to secondary hypergastrinaemia. The risk of side effects should not be a reason to withhold PPIs from patients with a true indication, and worry about poorly proven side effects should not lead to unnecessary discontinuation. The most important safety issue regarding PPI therapy is to critically evaluate the indication when initiating treatment and reconsidering the indication in long-term-treated patients.

Accuracy of an automated knowledge base for identifying drug adverse reactions

INTRODUCTION

Drug safety researchers seek to know the degree of certainty with which a particular drug is associated with an adverse drug reaction. There are different sources of information used in pharmacovigilance to identify, evaluate, and disseminate medical product safety evidence including spontaneous reports, published peer-reviewed literature, and product labels. Automated data processing and classification using these evidence sources can greatly reduce the manual curation currently required to develop reference sets of positive and negative controls (i.e. drugs that cause adverse drug events and those that do not) to be used in drug safety research.

METHODS

In this paper we explore a method for automatically aggregating disparate sources of information together into a single repository, developing a predictive model to classify drug-adverse event relationships, and applying those predictions to a real world problem of identifying negative controls for statistical method calibration.

RESULTS

Our results showed high predictive accuracy for the models combining all available evidence, with an area under the receiver-operator curve of ⩾0.92 when tested on three manually generated lists of drugs and conditions that are known to either have or not have an association with an adverse drug event.

CONCLUSIONS

Results from a pilot implementation of the method suggests that it is feasible to develop a scalable alternative to the time-and-resource-intensive, manual curation exercise previously applied to develop reference sets of positive and negative controls to be used in drug safety research.