Classification Of Adverse Drug Reactions Research Articles

Mining Real-World Big Data to Characterize Adverse Drug Reaction Quantitatively: Mixed Methods Study.

Adverse drug reactions (ADRs), which are the phenotypic manifestations of clinical drug toxicity in humans, are a major concern in precision clinical medicine. A comprehensive evaluation of ADRs is helpful for unbiased supervision of marketed drugs and for discovering new drugs with high success rates. In current practice, drug safety evaluation is often oversimplified to the occurrence or nonoccurrence of ADRs. Given the limitations of current qualitative methods, there is an urgent need for a quantitative evaluation model to improve pharmacovigilance and the accurate assessment of drug safety. In this study, we developed a mathematical model, namely the Adverse Drug Reaction Classification System (ADReCS) severity-grading model, for the quantitative characterization of ADR severity, a crucial feature for evaluating the impact of ADRs on human health. The model was constructed by mining millions of real-world historical adverse drug event reports. A new parameter called Severity_score was introduced to measure the severity of ADRs, and upper and lower score boundaries were determined for 5 severity grades. The ADReCS severity-grading model exhibited excellent consistency (99.22%) with the expert-grading system, the Common Terminology Criteria for Adverse Events. Hence, we graded the severity of 6277 standard ADRs for 129,407 drug-ADR pairs. Moreover, we calculated the occurrence rates of 6272 distinct ADRs for 127,763 drug-ADR pairs in large patient populations by mining real-world medication prescriptions. With the quantitative features, we demonstrated example applications in systematically elucidating ADR mechanisms and thereby discovered a list of drugs with improper dosages. In summary, this study represents the first comprehensive determination of both ADR severity grades and ADR frequencies. This endeavor establishes a strong foundation for future artificial intelligence applications in discovering new drugs with high efficacy and low toxicity. It also heralds a paradigm shift in clinical toxicity research, moving from qualitative description to quantitative evaluation.

Improving the performance of machine learning penicillin adverse drug reaction classification with synthetic data and transfer learning.

Machine learning may assist with the identification of potentially inappropriate penicillin allergy labels. Strategies to improve the performance of existing models for this task include the use of additional training data, synthetic data and transfer learning. The aims of this study were to investigate the use of additional training data and novel machine learning strategies, namely synthetic data and transfer learning, to improve the performance of penicillin adverse drug reaction (ADR) machine learning classification. Machine learning natural language processing was applied to free-text penicillin ADR data extracted from a public health system electronic health record (EHR). The models were developed by training on various labelled data sets. ADR entries were split into training and testing data sets and used to develop and test a variety of machine learning models. The effect of training on additional data and synthetic data versus the use of transfer learning was analysed. Following the application of these techniques, the area under the receiver operator curve of best-performing models for the classification of penicillin allergy (vs intolerance) and high-risk allergy (vs low-risk allergy) improved to 0.984 (using the artificial neural network model) and 0.995 (with the transfer learning approach) respectively. Machine learning models demonstrate high levels of accuracy in the classification and risk stratification of penicillin ADR labels using the reaction documented in the EHR. The model can be further optimised by incorporating additional training data and using transfer learning. Practical applications include automating case detection for penicillin allergy delabelling programmes.

Adverse Drug Reactions: Identification, Prevention and Management

This article addresses the critical aspects of adverse drug reactions (ADRs), focusing on their identification, prevention, and management. ADRs, defined as harmful or unintended reactions to drugs, necessitate a nuanced understanding due to their varying severity. Side effects, though not always harmful, can evolve into ADRs, prompting intervention. The decision-making process involves assessing the adverse reaction's severity, potential benefits of the drug, and the overall risk-benefit profile for the patient. Healthcare professionals play a pivotal role in monitoring and reporting ADRs to regulatory authorities for ongoing drug safety assessment. The article further discusses the classification of ADRs and outlines strategies for identification, including clinical manifestations, patient reporting, and pharmacovigilance systems. Management strategies, particularly in the case of anaphylaxis, underscore the importance of early recognition, acute therapy, and drug discontinuation. The prevention of ADRs involves a comprehensive approach, encompassing patient assessment, communication among healthcare providers, education, and the use of electronic health records. The collaborative effort between stakeholders and active participation in pharmacovigilance programs contribute to ongoing drug safety enhancement. The article concludes by emphasizing the collective goal of minimizing ADR occurrence and impact to enhance overall pharmacotherapy safety and effectiveness.

The evolution of pharmacovigilance: the contributions of Michael D Rawlins

Summary In the last 175 years, pharmacovigilance has evolved, albeit sometimes in response to serious incidents. The late Professor Sir Michael D Rawlins made major contributions to pharmacovigilance internationally. He proposed a widely used classification of adverse drug reactions (ADRs). He highlighted the importance of post-marketing surveillance immediately after a medicine's launch, and the strengths and weaknesses of existing spontaneous suspected ADR reporting systems. He encouraged the broadening of pharmacovigilance to involve all health professional groups, as well as patients. He highlighted the value of all sources of evidence and of judgement in making risk-benefit assessments. He was a strong early advocate of greater use of databases and registries, and of continuing surveillance throughout the lifespan of medicines as therapeutic agents.

Deep-Learning-Based Drug Recommendation and ADR Detection Healthcare Model on Social Media

The rapid rise of healthcare social media websites captures a significant amount of healthcare information, leading to mining medical content for pharmacovigilance, medication repositioning, and the healthcare industry. Paramedical advertisers gather health information from social media to propose suitable therapy. Social media makes patients aware of the revolution in clinical care and medical services. The researcher created a centralized social-media-based pharmacovigilance virtual podium to extract relevant medical services. And simultaneously built a virtual community of homogeneous e-patients for informational and emotional support. This article presents a new research-based review of the clinical recommendation system and possible medication repository and adverse drug reaction (ADR) research gaps. This article also explores ADR categorization with SVM, naive Bayes, linear regression, random forest, and deep neural networks. Subsequently, this article presents a preprocessing and clinical feature extraction approach described for drug recommendation and ADR classification. This methodology analyzed preprocessed clinical tweets for language diversity and clinical characteristics. This system also does multilayer content and collaborative filtering for patient-to-disease and disease-to-drug similarity indexing. It reveals the scope and collaborative filtering’s strengths and weaknesses. The collaborative association for filtering comparable clinical entities improves ADR detection and medicine recommendation. DNN comes out with the best result for ADR detection and classification and naive Bayes and SVM gain the comparatively biased result. In contrast, SVM achieves the highest improvement after preprocessing and with the amalgamation of clinical vector space. However, with the amalgamation of clinical vector space, the performance of ADR classification increased by approximately 12% and gained 86% accurate classification with the SIDER dataset.

Antibiotics-Related Adverse Drug Reaction in a Tertiary Hospital in Saudi Arabia: A Cohort, Retrospective Study.

Adverse drug reactions (ADR) are caused by a wide range of drugs including antibiotics. Currently, the prevalence and pattern of antibiotic-related ADR in Saudi Arabia are not well reported. The present study aimed to evaluate the ADR pattern caused by antibiotics in a tertiary healthcare center. This was a retrospective study conducted on 85 patients admitted to tertiary care hospitalmedical wards during the period from 2015 to 2019.The following data such as patient demographics (age, gender, weight, height), reason for admission, number of antibiotics use, comorbid condition, antibiotic(s) involved in ADR, classification of ADR, and type of ADR were recorded. Naranjo's scale was used to measure the probability of ADR. Among the 85 patients, the most frequent type of antibiotic was cephalosporins in 36.47%, followed by penicillins in 31.76% of the patients. The major type of ADR was rash (52.95%), followed by anaphylaxis reactions (10.59%) of the patients. Based on the Naranjo scale, the ADR was possible in 80% and probable in 18.82% of the cases. The presence of medical conditions displayed a significant association with the development of rashes (p=0.03). In addition, the female gender (p=0.009) and the presence of medical conditions (p=0.03) showed significant association with the development of anaphylaxis. Cephalosporin and penicillins were the most common antibiotics responsible for ADR, and the rash was the most common ADR.

Review on Adverse Drug Reactions

Adverse Drug Reaction is the process that it involves the unaffected and undesirable effects of medication that used during normal clinical use. Adverse drug effects are normal some time but at some case there are some very serious adverse effects that can be very hazardous can be life threatening Adverse medication responses may make patients feel uneasy or untrusting of their doctors, leading them to look for other forms of self-care, which may lead to more adverse drug reactions (ADRs). In this review article it includes all introduction of the Adverse drug effects and mainly there is Focus on the biological hazard effects. Review article is based on the introduction of adverse effects of Drug some relevant definition and terms. The classification of ADR is done different types are enlisted in the review article. The all articles are about the ADR detection, identification and prevention. It also includes the relevant casualties assessment overview done by the WHO-UMC Monitoring Centre. In this the review of market greatest Risk factor are assessed by the monitoring center and further the methods for prevention of the ADR are suggested. If any ADR is reported, then all relevant information is collected by using questionnaire introduced in this review. My overall intention for choice of the reviewing the article is just to introduce the termpharmacovigilance and ADR in detailed and deep manner. the pharmacovigilance term is very important in market sector of view because it defines the performance of the product on human life.

Multimodal model with text and drug embeddings for adverse drug reaction classification

In this paper, we focus on the classification of tweets as sources of potential signals for adverse drug effects (ADEs) or drug reactions (ADRs). Following the intuition that text and drug structure representations are complementary, we introduce a multimodal model with two components. These components are state-of-the-art BERT-based models for language understanding and molecular property prediction. Experiments were carried out on multilingual benchmarks of the Social Media Mining for Health Research and Applications (#SMM4H) initiative. Our models obtained state-of-the-art results of 0.61 F1-measure and 0.57 F1-measure on #SMM4H 2021 Shared Tasks 1a and 2 in English and Russian, respectively. On the classification of French tweets from SMM4H 2020 Task 1, our approach pushes the state of the art by an absolute gain of 8% F1. Our experiments show that the molecular information obtained from neural networks is more beneficial for ADE classification than traditional molecular descriptors. The source code for our models is freely available at https://github.com/Andoree/smm4h_2021_classification.

Nutritional evaluation study based on NRS 2002, OPNI, and their combined use in patients with adverse drug reactions after chemotherapy: a cross-sectional study.

BackgroundIt is important to assess the nutritional status of patients who have experienced adverse drug reactions (ADRs) after chemotherapy. We aimed to explore the nutritional status of patients who developed ADRs after chemotherapy, using the Nutritional Risk Screening 2002 (NRS 2002) tool, the Onodera Prognostic Nutrition Index (OPNI), and their combined application.MethodsNRS 2002 screening and OPNI calculation for patients before chemotherapy. Patients with ADRs after chemotherapy were grouped according to the NRS 2002, OPNI, and combined scores from both assessments. The types of ADRs were classified according to the National adverse drug reaction monitoring system (http://www.adrs.org.cn/). The impact of nutritional risk on the classification and types of ADRs in cancer chemotherapy patients was analyzed. Logistic regression was used to analyze the key influencing factors of gastrointestinal damage and bone marrow suppression. the consistency between the NRS 2002, OPNI, and their combined application analyzed.ResultsThe difference in body mass index (BMI) scores between the OPNI (P=0.041) and NRS 2002 groups was statistically significant (P=0.051). The difference in ADR type in the OPNI subgroups (P=0.04) was statistically significant. It showed that the proportion of new and severe ADRs in the low OPNI group (47.14%) was significantly higher than that in the high OPNI group (27.13%). The differences in digestive tract-associated ADRs were statistically significant among the OPNI groups (P=0.004), NRS 2002 groups (P=0.012), and combined measures groups (P=0.000), as were the differences in myelosuppressive-type ADRs in the OPNI groups (P=0.035), NRS 2002 groups (P=0.000), and combined measures groups (P=0.000). Logistic regression analysis showed that BMI was the key influencing factor for digestive tract-associated ADRs (95% CI: 1.267, 95% CI: 1.022–1.570, P=0.031) and myelosuppressive-type ADRs (95% CI: 1.213, 95% CI: 1.020–1.443, P=0.029). It had good consistency with the combined measures of nutritional risk (Kappa value =0.675).ConclusionsPatients with severe ADRs after chemotherapy showed low OPNI values, high NRS 2002 scores, and malnutrition. These patients also had a significantly increased incidence of digestive tract and myelosuppressive-type ADRs with BMI as the key influencing factor. The combined assessments showed good consistency with the NRS 2002 scores.

Completeness and accuracy of adverse drug reaction documentation in electronic medical records at a tertiary care hospital in Australia.

Background: A large proportion of patients presenting to hospitals have experienced a previous adverse drug reaction (ADR). Electronic medical records (EMRs) present an opportunity to accurately document ADRs and alert clinicians against inadvertent rechallenge where there is a pre-existing reaction. However, EMR systems are imperfect and rely on the accuracy of the data entered. Objective: To ascertain the completeness of ADR documentation and the accuracy of the classification of ADRs as allergy versus intolerance in the EMR at a major metropolitan hospital in Australia. Method: Cross-sectional audit of the ADR field of the EMR for a sample of patients on four different wards over 3weeks to ascertain the completeness of ADR documentation and the accuracy of classification of ADRs. Results: Of the 264 patients assessed, 102 (38.6%) had a total of 210 ADRs documented in the EMR. Of these, 105 (50%) were considered to have complete documentation; 63/210 (30.0%) were missing a reaction description and 88/210 (41.9%) were missing severity information. For those ADRs with a reaction description (n = 147), 97 (66.0%) were considered to be appropriately classified as allergy or intolerance. Conclusion: Incomplete and inaccurate ADR documentation was common. These findings highlight a need for optimising ADR documentation to improve appropriate medication use in hospital. Implications: Improved EMR design and education of healthcare workers on the importance of complete and accurate documentation of reactions are needed to improve completeness and accuracy of ADR classification.

Classification and clinical features of adverse drug reactions in patients with ulcerative colitis treated with 5‐aminosalicylate acid: a single-center, observational study

Background 5-Aminosalicylate acid (5-ASA) is a crucial drug for ulcerative colitis (UC) patients. 5-ASA has several side effects. However, the types of side effects vary and are sometimes severe. Methods A single-center, retrospective cohort study was conducted from September 2001 to June 2020. We surveyed consecutive UC patients who visited our hospital and investigated adverse drug reactions (ADRs) related to 5-ASA formulations. We grouped patients into four subgroups: (1) lupus-like symptoms, (2) blood test abnormalities, (3) mimicking IBD exacerbation and (4) others. Their clinical courses were evaluated. Results We surveyed 288 consecutive UC patients, 35 of whom developed ADRs of any grade (12.9%), and analyzed 27 patients. The median age and 5-ASA doses were 43 years and 4000 mg, respectively, and 48% were male. The ADR triggers were the first use of 5-ASA (n = 17, 63%), 5-ASA switch (n = 9, 33%) and 5-ASA dose escalation (n = 1, 3.7%). The median time to ADR was 15 days (IQR: 7, 63). Ten patients (37%) had grade 3/4 ADRs. Fever was the most common ADR (n = 6, 23%), followed by hyperamylasemia and headache (n = 4, 15%). Lupus-like symptoms accounted for 56% (n = 15), blood test abnormalities for 26% (n = 7), mimicking IBD exacerbation for 15% (n = 4) and others for 3.7% (n = 1). The time to ADR was shorter in the mimicking IBD exacerbation group (median 11 days) than in the lupus-like symptoms (22 days) and blood test abnormalities (55 days) groups. Conclusion Classification of ADRs related to 5-ASA into four groups might lead to early recognition of ADRs.

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

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

Analysis of Adverse Drug Reactions Identified in Nursing Notes Using Reinforcement Learning.

ObjectivesElectronic Health Records (EHRs)-based surveillance systems are being actively developed for detecting adverse drug reactions (ADRs), but this is being hindered by the difficulty of extracting data from unstructured records. This study performed the analysis of ADRs from nursing notes for drug safety surveillance using the temporal difference method in reinforcement learning (TD learning).MethodsNursing notes of 8,316 patients (4,158 ADR and 4,158 non-ADR cases) admitted to Ajou University Hospital were used for the ADR classification task. A TD(λ) model was used to estimate state values for indicating the ADR risk. For the TD learning, each nursing phrase was encoded into one of seven states, and the state values estimated during training were employed for the subsequent testing phase. We applied logistic regression to the state values from the TD(λ) model for the classification task.ResultsThe overall accuracy of TD-based logistic regression of 0.63 was comparable to that of two machine-learning methods (0.64 for a naïve Bayes classifier and 0.63 for a support vector machine), while it outperformed two deep learning-based methods (0.58 for a text convolutional neural network and 0.61 for a long short-term memory neural network). Most importantly, it was found that the TD-based method can estimate state values according to the context of nursing phrases.ConclusionsTD learning is a promising approach because it can exploit contextual, time-dependent aspects of the available data and provide an analysis of the severity of ADRs in a fully incremental manner.

Entity-Level Classification of Adverse Drug Reaction: A Comparative Analysis of Neural Network Models

An experimental work on the analysis of effectiveness of neural network models applied to the classification of adverse drug reactions at the entity level is described. Aspect-level sentiment analysis, which aims to determine the sentimental class of a specific aspect conveyed in user opinions, has been actively studied for more than 10 years. A number of neural network architectures have been proposed. Even though the models based on these architectures have much in common, they differ in certain components. In this paper, the applicability of the neural network models developed for the aspect-level sentiment analysis to the problem of the classification of adverse drug reactions is studied. Extensive experiments on English language texts of biomedical topic, including health records, scientific literature, and social media have been conducted. The proposed models mentioned above are compared with one of the best model based on the support vector machine method and a large set of features.

Adverse drug reactions monitoring of anticoagulant drugs used in cardiac coronary care unit of a tertiary care hospital

Background: Cardiovascular diseases are one of the leading causes of morbidity and mortality worldwide. Anticoagulants are the most commonly implicated drugs, used in cardiology unit and they are responsible for a majority of adverse drug reactions (ADRs). The objective of the present study was to evaluate the pattern of ADRs reported with anticoagulant drugs used in the cardiology unit of a tertiary care hospital.Methods: This observational prospective study was undertaken from September 2017 to August 2018. Causality assessment of ADRs was assessed using the WHO and Naranjo scale of probability. The severity was assessed by modified Hartwig and Siegel scale, and preventability of ADRs was assessed by Schumock and Thornton scale.Results: Out of the total forty-one ADRs recorded, 40 (97.56%) were mild and 1 (2.44%) was reported as severe on the Hartwig and Siegel severity scale. Hematuria (68.29%) was the most common ADR followed by hemoptysis (14.63%). Among all anticoagulants, low molecular weight heparin was associated with the majority of ADRs (85.37%). The WHO causality and Naranjo Scale revealed that maximum of the ADRs (~80%) were possible. All ADRs reported was Type “A” reactions according to Wills and Brown classification of ADRs. Majority of ADRs (97.56%) were probably preventable.Conclusions: In the present study, hematuria was the most common ADR reported. Among all anticoagulants, Low molecular weight heparin accounted for the majority of ADRs followed by acenocoumarol and heparin. Intensive monitoring and frequent reporting need to be done in cardiac units to improve patient safety.

Smoothing dense spaces for improved relation extraction between drugs and adverse reactions

Background and objectiveThis work aims at extracting Adverse Drug Reactions (ADRs), i.e. a harm directly caused by a drug at normal doses, from Electronic Health Records (EHRs). The lack of readily available EHRs because of confidentiality issues and their lexical variability make the ADR extraction challenging. Furthermore, ADRs are rare events. Therefore, efficient representations against data sparsity are needed. MethodsEmbedding-based characterizations are able to group semantically related words. However, dense spaces suffer from data sparsity. We employed context-aware continuous representations to enhance the modelling of infrequent events through their context and we turned to simple smoothing techniques to increase the proximity between similar words (e.g. direction cosines, truncation, Principal Component Analysis (PCA) and clustering) in an attempt to cope with data sparsity. ResultsAn F-measure of 0.639 for the ADR classification was achieved, obtaining an improvement of approximately 0.300 in comparison with the results obtained by a word-based characterization. ConclusionThe embbeding-based representation together with the smoothing techniques increased the robustness of the ADR characterization. It was proven particularly appropriate to cope with lexical variability and data sparsity.

Adverse drug reaction classification by health professionals: appropriate discrimination between allergy and intolerance?

BackgroundThe correct classification of an adverse drug reaction (ADR) as allergy (immunological) or intolerance (non-immunological) has important clinical implications. The aim of this study was to examine the ability of health professionals to discriminate between allergy and intolerance, classify the severity of the ADR and degree of contraindication.MethodsHealth professionals were presented ten ‘real-life’ ADR scenarios using an online questionnaire and asked to: categorise the reaction as allergy or intolerance, rate the severity of the reaction and judge the level of contraindication of the causative drug. The number and proportion of responses were calculated for each of the cases presented and associations between classification of reaction type, severity and level of contraindication were examined.ResultsA total of 394 responses were received. Overall 59.0% (SD 28.9) correctly categorised the cases, 60.8% (SD 16.8) classified the severity correct, and less than half (44.7%, SD 28.6) correctly identified the level of contraindication. The proportion of health professionals correctly answering the type, severity and level of contraindication for the allergy case was significantly higher (p < 0.0001) by comparison to the intolerance cases (type: 56.6% ± 33.1; severity: 57.3 ± 11.9; level of contraindication: 38.5 ± 19.9).ConclusionsHealth professionals have suboptimal understanding of classification of ADRs. Strategies are required to strictly avoid re-exposure of patients to drugs which carry an increased risk of inducing a dangerous reaction, whilst minimising the avoidance of drugs which are of minimal risk or allowing the use of low-risk drugs where the benefits may be significant.

Differences in Adverse Reactions Among Iodinated Contrast Media: Analysis of the KAERS Database

The various adverse drug reactions (ADRs) arise from different types of iodinated contrast media (ICM). Thus, we investigated the occurrence rate and types of ADRs according to the total usage cases of the 7 most common ICM. We retrospectively reviewed 74,242 causal ADRs caused by ICM from the Korea Adverse Event Reporting System database between January 2014 and December 2016. The 11,712,796 total usage cases that represent all administrations of ICM reported from individual medical institutions were received from the Health Insurance Review and Assessment Service. A proportionality test was used to examine the differences in the frequency ratio of causal ADRs to total usage cases. Immediate hypersensitivity (44,467 cases, 88.56%) occurred more frequently than delayed hypersensitivity (5,725 cases, 11.4%; P < .001). The overall occurrence rate of causal ADRs and serious ADRs considering total usage cases was 0.37% and 0.02%, respectively (P < .001). The ICM most commonly resulting in ADRs were iomeprol (0.7%) and iopromide (0.59%). The serious ADRs were most common for iomeprol (0.05%). When ADRs were classified according to the system organ class, "skin and appendages disorders" (47,065 cases, 63.4%) occurred most common. Iodixanol resulted in the highest frequency of "urinary system disorders." By comparison of the ADRs considering total usage cases, the incidence and classification of ADRs were different for each contrast medium. A prospective study is needed because the differences in these 7 major contrast media may assist in the selection of ICM tailored for each patient.

Applying DoTS adverse drug reactions classification to reports from hospital stimulated reporting

Applying DoTS adverse drug reactions classification to reports from hospital stimulated reporting

Improving Recognition and Reporting of Adverse Drug Reactions in the NICU: A Quality Improvement Project.

Introduction:Adverse drug reactions (ADRs) are under-recognized and under-reported in the Neonatal Intensive Care Unit (NICU) population, with up to 95% of all ADRs not reported. Compared with non-elderly adults, pediatric patients are 3 times more likely to experience an ADR, with varying rates from 0.6% to 16.8%. The Children’s Mercy NICU has an ADR rate of 0.29% (2015). This high rate presents an opportunity to increase recognition and reporting, and improve characterization of ADRs in the NICU.Methods:The primary aim of this quality improvement project was for 70% of patients who received specified medications (indomethacin, dexmedetomidine, fentanyl, lorazepam, dexamethasone, or hydrocortisone) in the first 3 months of age to be assessed daily for ADRs. We selected these medications due to the frequency of use and well-understood ADR associations. For each ADR recognized, the Naranjo score, was calculated and compared with the neonatal-specific Du score to assess the effectiveness of ADR characterization.Results:Implementation occurred on May 15, 2017. We completed 3 PDSA cycles over 1 year. The bedside monitoring tool was utilized 83% of the time. Twenty-eight potential ADRs were identified, far exceeding the number reported before implementation. The Du score appeared to better characterize ADRs compared with the Naranjo score.Conclusions:Use of a bedside monitoring tool improves ADR detection. We experienced challenges with consistently identifying patients on target drugs and getting the tool to the bedside. Application of the Du score for ADR classification in neonates appears to be more appropriate than the use of the Naranjo.