Assessment Of Adverse Drug Reactions Research Articles

Pharmacovigilance Activities

Pharmacovigilance (PV) is an important area for the safety and ensuring that the patients are safe in every aspect of the drugs being taken or injected. India is still in its nascent stage; there is a lot to be done and to learn, in the field of PV, in ensuring that the safe implementation of the activities and work done is achieved. The major problem in India is the under-reporting of adverse drug reaction (ADR). There is an increasing number of hospitalization of patients owing to adverse effects of drugs and it becomes a challenge to find out the exact cause the ADRs when a patient in treated with multiple drugs simultaneously. In the review, we will explore the different types of assessment scale to do the ADR assessment and to find its causative agents.

Assessment and Monitoring of Adverse Drug Reactions at a Tertiary Care Hospital

Background: Incidences of adverse drug reactions were reported through spontane-ous reporting at an ADR monitoring unit in a tertiary care hospital. Aims: This study was conducted to describe the distribution pattern of adverse drug reaction (ADR). Objective: The objective of this study was to monitor and report the adverse drug reactions (ADRs) occurring in a tertiary care hospital and to evaluate the incidence, causality, severity, and preventability of adverse drug reactions. Methods: A prospective, observational study was conducted at a tertiary care hospital in Punjab for 6 months. All patients admitted to the hospital above 18 years of age were included in the study. Results: A total of 103 ADRs were observed over the study period of 6 months. The majority of them were females (60), comprising of 58.25%. The therapeutic class of drug associated with most of the ADRs was antibiotics 18 (17.5%). Maximum number of ADRs occurred in the gen-eral medicine ward with frequency of 27 (26.2%) and were of type b 58 (56.3%). Causality was assessed using the Naranjo scale, and most of the ADRs came out to be probable 64 (62.1%) in nature. Severity was assessed using Hartwig’s severity assessment scale, and most of the cases, 66 (64.1%), were moderate in intensity. ADR preventability was assessed using the Schumock and Thornton preventability scale, and it was observed that most of the cases, 82 (79.6%), were not preventable. Conclusion: This study seeks to strengthen the ADR database through analysis of spontaneous reporting patterns of ADRs from various clinical departments of a tertiary care teaching hospital, thereby increasing awareness and improving the reporting culture among health care practition-ers. It can be concluded that continuous medication monitoring and a well-organized and com-mitted pharmacovigilance system led by a clinical pharmacist in a hospital setting would un-doubtedly lower the incidence of adverse drug reactions.

Severe exacerbation of facial dermatitis with swelling following introduction of abrocitinib in a patient with atopic dermatitis

BackgroundAbrocitinib, an oral small-molecule Janus kinase 1 (JAK1) inhibitor, has been widely accepted for the treatment of moderate-to-severe atopic dermatitis (AD). Currently there is a paucity of data on the adverse events (AEs) after abrocitinib treatment, especially on rare events such as exacerbation of facial dermatitis, and their causal relationship and subsequent management remains poorly elucidated.Case presentationA 43-year-old female patient with moderate AD received dupilumab after failure of topical treatments. Facial dermatitis persisted and became refractory after dupilumab treatment, and the patient changed treatment to oral abrocitinib. Fifteen hours after the first dose of abrocitinib, she developed exacerbation of facial dermatitis with swelling. The patient was initially diagnosed as abrocitinib-induced hypersensitivity. However, a score of 3 of the Naranjo adverse drug reaction assessment indicates week correlation between abrocitinib therapy and exacerbation of facial dermatitis, and negative results from subsequent drug provocation test further suggests no causal relationship.ConclusionsThe present case report highlights the necessity of careful determination of abrocitinib-induced hypersensitivity, which should not be diagnosed simply based on the time sequence between drug exposure and symptom occurrence. In addition, caution should be exercised for drug withdrawal, especially when confirmative evidence is absent. Drug provocation test can be helpful and effective treatments could be continued unless severe AEs occur.

Assessment of Adverse Drug Reactions in Geriatric Patients Admitted to a Tertiary Care Teaching Hospital in South India

Assessment of Adverse Drug Reactions in Geriatric Patients Admitted to a Tertiary Care Teaching Hospital in South India

Inter-rater agreement between WHO- Uppsala Monitoring Centre system and Naranjo algorithm for causality assessment of adverse drug reactions

Determining the causality of Adverse Drug Reactions (ADRs) is essential for management and prevention of future occurrences. The WHO-Uppsala Monitoring Centre (UMC) system is recommended under the Pharmacovigilance Program of India whereas Naranjo's algorithm is commonly utilized by clinicians, but their agreement remains a subject of investigation. This study aims to compare the inter-rater agreement between these two scales for causality assessment of ADRs. In this cross-sectional study, two groups of pharmacovigilance experts were given a set of total 399 anonymized individual case safety reports, collected over six months. The raters were blinded to each other's assessments and applied the WHO-UMC system and Naranjo algorithm to each case independently. Inter-rater agreement was then evaluated utilizing Cohen's kappa. The suspected ADRs were also comprehensively analysed on parameters like age, sex, route of administration, speciality, organ system affected, most common drug categories and individual drugs, outcome of ADRs. Analysis of 399 suspected ADRs revealed that mean age of patients was 36.8 ± 18.0 years, females were more frequently affected, highest proportion of reports were from psychiatry inpatients, seen with antipsychotic drugs, involved the central nervous system, with oral administration, and 91% resolved. On causality assessment by the WHO-UMC system, 53.3% were “Certain” whereas Naranjo's algorithm categorized 96.74% of ADRs as “Probable”. Cohen's kappa showed a “Minimal” agreement (0.22) between WHO-UMC and Naranjo system of causality assessment. The considerable lack of agreement between the two commonly employed systems of causality assessment of ADRs warrants further investigation into specific factors influencing the disagreement to improve the accuracy of causality assessments.

Prediction of cytochrome P450-mediated bioactivation using machine learning models and in vitro validation.

Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.e., Random Forest, Random Subspace, SVM and Naïve Bayes. The models were assessed by metrics like "Precision", "Recall", "F-Measure", "AUC" (Area Under the Curve), etc. Random Forest algorithms illustrated the best predictability, with nice AUC values of 0.949, 0.973 and 0.958 for the test sets of Benzene ring, Nitrogen heterocycle and Sulfur heterocycle models, respectively. 2D descriptors like topological indices, 2D autocorrelations and Burden eigenvalues, etc. contributed most to the models. Furthermore, the models were applied to predict the occurrence of bioactivation of an external verification set. Drugs like selpercatinib, glafenine, encorafenib, etc. were predicted to undergo bioactivation into toxic RMs. In vitro, IC50 shift experiment was performed to assess the potential of bioactivation to validate the prediction. Encorafenib and tirbanibulin were observed of bioactivation potential with shifts of 3-6 folds or so. Overall, this study provided a reliable and robust strategy to predict the P450-mediated bioactivation, which will be helpful to the assessment of adverse drug reactions (ADRs) in clinic and the design of new candidates with lower toxicities.

Quantitative Signal Detection for COVID-19 Medicinal Products Based on Retrospective Analysis of Spontaneous Reports from the Russian Pharmacovigilance Database

SCIENTIFIC RELEVANCE. The pandemic of novel coronavirus infection (COVID-19) led to a drastic increase in the use of medicinal products of various therapeutic groups and increased spontaneous reporting of adverse drug reactions (ADRs). Therefore, it is necessary to analyse the reported information to identify potential safety signals.AIM. This study aimed at systematisation and quantitative analysis of data on the safety of COVID-19 medicinal products from the Russian pharmacovigilance database.MATERIALS AND METHODS. This retrospective analysis included spontaneous ADR reports submitted to the Russian pharmacovigilance database from 1 January 2020 to 31 December 2022. The authors applied disproportionality analysis to generate safety signals.RESULTS. During the stated period, the database website published 873 spontaneous reports on 1,636 ADRs associated with COVID-19 treatment. Most ADRs were associated with favipiravir (493 reports), hydroxychloroquine (87 reports), and olokizumab (85 reports). The most common ADRs included 273 (16.7%) abnormal investigation results, 203 (12.4%) hepatobiliary disorders, and 191 (11.6%) gastrointestinal disorders. The majority of adverse events, 674 (77%) cases, had favourable outcomes. Using frequency-based disproportionality analysis, the authors identified 23 potential safety signals based on disproportionately reported ADRs for azithromycin, dexamethasone, levilimab, lopinavir+ritonavir, molnupiravir, olokizumab, tofacitinib, tocilizumab, umifenovir, and favipiravir.CONCLUSIONS. The new safety signals require additional assessment of ADR reporting forms for causal relationship analysis, validation, prioritisation, and clinical interpretation. The frequency-based method did not identify safety signals for hydroxychloroquine, remdesivir, baricitinib, sarilumab, and anti-COVID-19 human immunoglobulin, but this does not rule out the possibility of detecting new causal relationships.

Spontaneously reported adverse drug reaction pattern in a tertiary care teaching hospital: A cross-sectional study

Background: Adverse drug reactions (ADRs) are unintended and harmful reactions to medications that occur at doses normally used for therapeutic purposes. The reporting of ADRs is essential for the identification and prevention of ADRs. Aims and Objectives: The aim of the study was to estimate the frequency and distribution of spontaneously reported ADRs in the tertiary care teaching hospital. Materials and Methods: A retrospective cross-sectional study was conducted from July 2020 to June 2023, from spontaneously reported ADRs by the ADR Monitoring Centre, MGM Medical College, Kishanganj, Bihar. Distribution of age, gender, department, medication groups, and systems involved were examined. Utilizing certain scales, causality, severity, and preventability were evaluated. Results: Total 47 ADRs were reported during the study period. The most common ADRs were cutaneous ADRs (n = 19,40.43%) followed by the central nervous system (CNS) (n = 12, 25.53%), gastrointestinal system (GI) (n = 9, 19.15%), musculoskeletal (n = 4, 8.51%) and others. The most commonly implicated drugs were Antibiotics (21.28%) followed by analgesics (12.77%), DMARD (12.77%), antihypertensive (12.77%), and others shown in the study. The severity assessment of ADRs was done by Modified Hartwig et al. severity assessment scale and was found mild (87%), followed by moderate (8.5%) and severe (4.3%). Using the modified Schumock and Thronton preventability scale preventability assessment of ADRs was done and was found 51.06% of ADRs were definitely preventable, 38.30% were probably preventable and 12.77% of ADRs were not preventable. Conclusion: The findings of this study emphasize the significance of pharmacovigilance and the requirement that medical personnel be knowledgeable about the indications and symptoms of ADRs.

Assessment of Medication Adherence and Adverse Drug Reactions in Depressive Patients Taking Selective Serotonin Reuptake Inhibitors in Tertiary Care Hospitals in Kerala

Assessment of Medication Adherence and Adverse Drug Reactions in Depressive Patients Taking Selective Serotonin Reuptake Inhibitors in Tertiary Care Hospitals in Kerala

Optimisation of Approaches to Adverse Event Analysis in Bioequivalence Clinical Trials

SCIENTIFIC RELEVANCE. The safety assessment of investigational medicinal products is a mandatory step in clinical trials of all phases, including bioequivalence studies. However, there are no approaches providing for the individualised assessment of adverse drug reactions (ADRs), which contributes to the quality of decisions on the safety of pharmacotherapy.AIM. The study aimed to develop and justify approaches to the individualised assessment of the safety of pharmacotherapy based on quantitative integrative analysis of adverse events (AEs).MATERIALS AND METHODS. The authors carried out a systematic review of open-access publications and adapted quantitative integrative analysis methods for assessing the safety of pharmacotherapy in clinical trials involving healthy volunteers. The developed methodology is a step-by-step individualised assessment of ADRs, where each case is assigned a certain score and a weight, with subsequent data aggregation to obtain an integrated indicator at the system/organ and organism levels.RESULTS. The authors developed a five-step procedure for assessing the safety of pharmacotherapy based on quantitative integrative ADR analysis. This procedure involves scoring an AE, converting the score using membership functions, assigning weights, aggregating data to obtain an integrated indicator, and interpreting individual and group indicators. The sequential implementation of the analysis steps in accordance with the proposed procedure makes it possible to assign each volunteer (study subject) to a specific group in accordance with the likelihood of developing AEs. In addition to individual assessment, the article presents an algorithm for interpreting indicators for groups of study subjects, depending on the treatment group (study or comparator medicinal product).CONCLUSIONS. The described algorithm for converting and presenting integrative AE assessments will improve the reliability and validity of conclusions on the safety of medicinal products, which is important for planning and implementing further clinical development programmes.

Navigating Drug-Induced Adversities: A Python-Based Console Application for Causality Assessment Using the Naranjo Algorithm.

The timely and accurate adverse drug reactions (ADR) assessment is vital for effective patient management and healthcare delivery. The Naranjo Algorithm is a widely recognized tool for determining the probability that a drug induces a given ADR. However, the process can be time-consuming and susceptible to human error. This study introduces a Python-based console application (Python Software Foundation, Wilmington, Delaware, United States) designed to automate the Naranjo Algorithm for ADR causality assessment. The application was developed using Python 3.11.4 on a Windows 11 system (Microsoft Corporation, Redmond, Washington, United States) and compiled in Notepad (Microsoft Corporation), a basic text editor, highlighting its accessibility and ease of use in various settings. User input is solicited for each question in the Naranjo Algorithm, validated for acceptable entries, and subsequently scored. The final score categorizes the reaction into Doubtful, Possible, Probable, or Definite ADR, facilitating rapid clinical decision-making. Preliminary validation shows promising reliability and effectiveness, making it a valuable asset in research and clinical settings for assessment.

Assessment of Potential Adverse Drug Reactions Associated with Cardiovascular Medicines

Background: Every drug has the potential to cause ADRs. Cardiovascular medications are a major problem in drug therapy as they can result in several consequences, ranging from allergic reactions to permanent harm. We have undertaken a meta-analytic review of various types of studies performed in different hospital settings to understand the importance of ADRs in CVD patients and how ADRs might be better detected, evaluated, and avoided. Objectives: To study various factors and assess the incidence, causality, severity, and preventability of ADRs associated with cardiovascular drugs. Methods: Meta-analytic study conducted over 6 months by reviewing 24 articles finalized from 58 articles collected from various data sources like Clin Med, Pubmed, and Medline. Information related to ADRs was analyzed by using demographic data through various questionnaires and scales in articles. Results: A total of 4421 ADRs were reported among 9759 patients. 8/24 of the studies performed causality assessment by using the Naranjo scale and 12/24 used the WHO-UMC scale. 9/24 studies assessed severity and 5/24 studies performed preventability assessments. The incidence of ADRs was high in the 40-80 age range (94.69%). Commonly prescribed drugs were calcium-channel blockers and beta-blockers in CVD patients. Organ systems like the cardiovascular, central nervous and respiratory systems were commonly affected. Most ADRs were mild and possible. Females experienced more ADRs compared to males. Conclusion: Although this study provides estimates of the incidence, severity, and preventability of ADRs in different settings, further studies are needed for monitoring ADRs in patients using CVD drugs to address how such ADRs will be prevented.

Knowledge and attitude towards pharmacovigilance among healthcare students at a medical college in Nepal

Background: Pharmacovigilance is the science and activities relating to the detection, assessment, understanding, and prevention of adverse drug reactions (ADRs) and any other possible drug-related problems. Under reporting of adverse drugs reactions are the global health problem. The adequate knowledge and skills towards pharmacovigilance and adverse drugs reactions reporting are crucial for the health care students to ensure patients’ medication safety. This study aims to assess the knowledge and attitude of the health care students towards pharmacovigilance and ADRs. Methods: A closed ended, structured, self-administered questionnaire was administered to 204 undergraduate health care students to collect the data. Data were analyzed using SPSS version 21. Non-parametric tests (Mann Whitney U test and Kruskal Wallis test) were used for analysis. Results: Among 204 respondents, the majority of them had a poor knowledge (91.18%) and positive attitude (87.25%) towards Pharmacovigilance. The inter quartile range (median) score of the respondents’ knowledge was 5.0±2.211 and attitude was 27.0±2.88 towards Pharmacovigilance and ADRs reporting. The main reason for under reporting of ADRs was difficulty to decide whether ADR has occurred or not (32.4%) due to the lack of appropriate knowledge and training. There is a poor knowledge and positive attitude towards Pharmacovigilance. Conclusions: Adequate coverage of Pharmacovigilance and ADRs reporting issues should be covered in the curriculum as well as hand on training and workshop should be conducted to increase the knowledge and confidence in detecting, monitoring and reporting ADR in their clinical posting.

A Critical Review of Drug Safety and Pharmacovigilance Practices

This abstract provides a concise overview of the critical review of drug safety and pharmacovigilance practices. The review highlights advancements in pharmacovigilance systems, including spontaneous reporting mechanisms and signal detection methodologies. Despite progress, challenges such as underreporting, data quality issues, and regulatory disparities persist. The abstract emphasizes the importance of collaborative efforts to address these challenges and recommends strategies for improvement, including education and awareness campaigns, enhanced surveillance infrastructure, regulatory convergence, integration of advanced technologies, and patient-centered approaches. Ultimately, effective pharmacovigilance practices are crucial for maintaining public trust and ensuring the safety of pharmaceutical interventions. It examines the current landscape, highlighting achievements, challenges, and areas for improvement. Advancements in pharmacovigilance systems, such as spontaneous reporting mechanisms and signal detection methodologies, have improved the timely detection and assessment of adverse drug reactions. However, challenges such as underreporting, data quality issues, and regulatory disparities continue to pose significant obstacles. It recommends strategies for improvement, including education and awareness campaigns to promote proactive reporting, investment in enhanced surveillance infrastructure, regulatory convergence to streamline reporting requirements, integration of advanced technologies like artificial intelligence, and patient-centered approaches to engage patients in pharmacovigilance activities.

The Utility of the Liverpool Adverse Drug Reaction Assessment Tools in the Evaluation of Chemotherapy-Induced Nausea and Vomiting in Children

The Utility of the Liverpool Adverse Drug Reaction Assessment Tools in the Evaluation of Chemotherapy-Induced Nausea and Vomiting in Children

Causality assessment of adverse drug reaction: A narrative review to find the most exhaustive and easy-to-use tool in post-authorization settings.

The core motive of pharmacovigilance is the detection and prevention of adverse drug reactions (ADRs), to improve the risk-benefit balance of the drug. However, the causality assessment of ADRs remains a major challenge among clinicians, and none of the available tools of causality assessment used for assessing ADRs have been universally accepted. To provide an up-to-date overview of the different causality assessment tools. We conducted electronic searches in MEDLINE, EMBASE, and the Cochrane database. The eligibility of each tool was screened by three reviewers. Each eligible tool was then scrutinized for its domains (the reported specific set of questions/areas used for calculating the likelihood of cause-and-effect relation of an ADR) to discover the most comprehensive tool. Finally, we subjectively assessed the tool's ease-of-use in a Canadian, Indian, Hungarian, and Brazilian clinical context. Twenty-one eligible causality assessment tools were retrieved. Naranjo's tool and De Boer's tool appeared the most comprehensive among all the tools, covering 10 domains each. Regarding "ease-of-use" in a clinical setting, we judged that many tools were hard to implement in a clinical context because of their complexity and/or lengthiness. Naranjo's tool, Jones's tool, Danan and Benichou's tool, and Hsu and Stoll's tool appeared to be the easiest to implement into various clinical contexts. Among the many tools identified, 1981 Naranjo's scale remains the most comprehensive and easy to use for performing causality assessment of ADRs. Upcoming analysis should compare the performance of each ADR tool in clinical settings.

Assessment and Management of Adverse Drug Reaction in Clinical Practice: A quantitative study

The importance of managing and evaluating adverse drug reactions in medical care is for guaranteeing patient safety and achieving the best medical results. ADRs can vary from slight and brief to extreme and life-threatening and can appear in any medical situation. This abstract underline the value of organized procedures for the assessment and managing of ADRs. The assessment of ADRs involves gathering comprehensive patient information, including medical history, medication use, and symptomatology. Recognizing the temporal relationship between drug administration and the onset of adverse events is essential for accurate identification and assessment. Various tools, such as causality assessment algorithms and probability scales, aid in determining the likelihood of the drug's involvement in the adverse event. Once an ADR is identified, management strategies should be implemented promptly. It is important to keep track of patients who may be particularly susceptible to adverse drug reactions, and to take necessary steps to prevent or manage any results that arise, such as stopping or altering the problematic drug, providing supportive care, or taking some other action in the case of serious responses. Effective assessment and management of ADRs in clinical practice require a systematic approach that includes thorough patient evaluation, accurate causality assessment, and appropriate intervention strategies. This comprehensive approach contributes to patient safety, improves healthcare outcomes, and promotes rational drug use.

Abrupt increased serum creatinine in a hyperferritinemia patient treated with deferoxamine after cord blood transplantation: a case report with literature review

BackgroundErythrocyte transfusion is an indispensable component of supportive care after hematopoietic stem cell transplantation (HSCT). However, HSCT recipients are susceptible to the development of acute kidney injury (AKI) with multifactorial causes. We report a case of a rapid elevation in serum creatinine associated with deferoxamine after cord blood transplantation (CBT).Case presentationA 36-year-old Japanese male diagnosed with relapsed Philadelphia-positive acute lymphoblastic leukemia received CBT. At day 88 post-CBT, multidrug-resistant Pseudomonas aeruginosa (MDRP) was isolated from urine culture. Subsequently, colistin 200 mg/day was administered parenterally for treatment of epididymitis from day 91 to 117 post-CBT. Despite concomitant administration of potential nephrotoxic agents such as piperacillin-tazobactam, acyclovir, and liposomal amphotericin B, no development of AKI was observed during this period. At day 127 post-CBT, MDRP was detected in blood and urine cultures, and colistin 200 mg/day was re-started parenterally. Due to extremely higher ferritin level, deferoxamine was administered intravenously at day 133 post-CBT. While serum creatinine was 1.03 mg/dL before starting deferoxamine, the level increased to 1.36 mg/dL one day after commencing deferoxamine (day 134 post-CBT), and further increased to 2.11 mg/dL at day 141. Even though colistin was discontinued at day 141 post-CBT, serum creatinine continued to increase. Deferoxamine was withdrawn at day 145 post-CBT, when serum creatinine peaked at 2.70 mg/dL. In addition, no cylinduria is observed during the period of development of AKI. In adverse drug reaction (ADR) assessment using Naranjo probability score, the scores of 3 in deferoxamine and 2 in colistin, respectively, indicated “possible” ADR. However, while colistin-associated AKI manifested early onset, recovery time within 2 weeks after discontinuation and development of cylinduria, this case was discordant with the properties. Furthermore, in the literature review, development of AKI within 1 day, including sudden increase in serum creatinine or abrupt reduction in urine volume, was reported in 3 identified cases.ConclusionsWe considered the rapid creatinine elevation to be the result of deferoxamine rather than ADR caused by colistin. Therefore, careful monitoring of kidney function is required in recipients of HSCT treated with deferoxamine.

Therapeutic role of psilocybin and 3,4-methylenedioxymethamphetamine in trauma: A literature review.

With the Food and Drug Administration designation in 2017 of 3,4-methylenedioxymethamphetamine (MDMA) as a breakthrough therapy in post-traumatic stress disorder and psilocybin in treatment-resistant depression, psychedelic drugs have continued to garner the attention of researchers and clinicians for their promise of unmatched, rapid improvement in a multitude of psychiatric conditions. Classic psychedelic drugs including psilocybin, lysergic acid diethylamide, and ayahuasca, as well as non-classic drugs such as MDMA and ketamine, are currently being investigated for a potential therapeutic role in trauma, depressive disorders, and other psychopathologies. However, psilocybin and MDMA each have a functional profile well-suited for integration with psychotherapy. The present review focuses on psilocybin and MDMA in psychedelic-assisted therapy (PAT), as these studies compose most of the literature pool. In this review, we discuss the current and future uses of psychedelic drugs, with an emphasis on the role of MDMA and psilocybin in PAT in the setting of trauma and related comorbidities on the efficacy of psychedelic drugs across multiple psychiatric disorders. The article concludes with thoughts for future research, such as incorporating wearables and standardization of symptom scales, therapy styles, and assessment of adverse drug reactions.

Prediction of adverse effects of drug-drug interactions on the cardiovascular system based on the analysis of structure-activity relationships

The co-administration of drugs often leads to drug-drug interactions, which may be accompanied by various adverse drug reactions that pose a threat to the life and health of patients. The effect caused by adverse drug reactions from the cardiovascular system is one of the most significant manifestations of drug-drug interaction. Clinical assessment of adverse drug reactions resulting from drug-drug interaction between all drug pairs used in therapeutic practice is not possible. The purpose of this work was to build models using structure-activity analysis to predict the effects of adverse drug reactions on the cardiovascular system, mediated by interactions between drug pairs when they are taken together. Data on adverse effects resulting from drug-drug interaction were obtained from the DrugBank database. The data on drug pairs that do not cause the corresponding effects, necessary for building accurate structure-activity models, were obtained from the TwoSides database, which contains the results of the analysis of spontaneous reports. Two types of descriptors were used to describe a pair of drug structures: PoSMNA descriptors and probabilistic estimates of the prediction of biological activities obtained using the PASS program. Structure-activity relationships were established using the Random Forest method. Prediction accuracy was calculated by means of a five-fold cross-validation. The highest accuracy values were obtained using PASS probabilistic estimates as descriptors. The area under the ROC curve was 0.94 for bradycardia, 0.96 for tachycardia, 0.90 for arrhythmia, 0.90 for ECG QT prolongation, 0.91 for hypertension, 0.89 for hypotension.