<i>In Silico</i> Approach to Predict Severe Cutaneous Adverse Reactions Using the Japanese Adverse Drug Event Report Database

Ambe, Kaori; Ohya, Kazuyuki; Takada, Waki; Suzuki, Masaharu; Tohkin, Masahiro

doi:10.1111/cts.12944

Cited by 4 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, lamotrigine (SMQ level) was the agent with the highest reporting proportion followed by acetaminophen and allopurinol, while antibacterials (SMQ level) were the drug class with the highest reporting proportions followed by antiepileptics and antineoplastic agents. However, our results are not consistent with previous studies in reporting the proportion rank ( Kardaun et al, 2013 ; Su and Aw, 2014 ; Zhao et al, 2019 ; Oshikoya et al, 2020 ; Ambe et al, 2021 ). Reporting on the proportions of drugs or drug classes may vary according to the region, study design, sample size, and patient inclusion and exclusion criteria, but our larger sample and global perspective make our results on reporting proportions more reliable, giving more precise guidance on which drugs to focus on.…”

Section: Discussioncontrasting

confidence: 99%

Severe cutaneous adverse reactions to drugs: A real-world pharmacovigilance study using the FDA Adverse Event Reporting System database

Gou

Zhu

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

Background: Sound drug safety information is important to optimize patient management, but the widely recognized comprehensive landscape of culprit-drugs that cause severe cutaneous adverse reactions (SCARs) is currently lacking.Objective: The main aim of the study is to provide a comprehensive landscape of culprit-drugs for SCARs to guide clinical practice.Methods: We analyzed reports associated with SCARs in the FDA Adverse Event Reporting System database between 1 January 2004 and 31 December 2021 and compiled a list of drugs with potentially serious skin toxicity. According to this list, we summarized the reporting proportions of different drugs and drug classes and conducted disproportionality analysis for all the drugs. In addition, the risk characteristic of SCARs due to different drugs and drug classes was summarized by the positive–negative distribution based on the results of the disproportionality analysis.Results: A total of 77,789 reports in the FDA Adverse Event Reporting System database were considered SCAR-related, of which lamotrigine (6.2%) was the most reported single drug followed by acetaminophen (5.8%) and allopurinol (5.8%) and antibacterials (20.6%) was the most reported drug class followed by antiepileptics (16.7%) and antineoplastics (11.3%). A total of 1,219 drugs were reported as culprit-drugs causing SCARs in those reports, and the largest number of drugs belonged to antineoplastics. In disproportionality analysis, 776 drugs showed at least one positive pharmacovigilance signal. Drugs with the most positive signals were lamotrigine, acetaminophen, furosemide, and sulfamethoxazole/trimethoprim.Conclusion: Our study provided a real-world overview of SCARs to drugs, and the investigation of SCAR positive–negative distribution across different drugs revealed its risk characteristics, which may help optimize patient management.

show abstract

Section: Discussioncontrasting

confidence: 99%

Severe cutaneous adverse reactions to drugs: A real-world pharmacovigilance study using the FDA Adverse Event Reporting System database

Gou

Zhu

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

show abstract

“…Previous studies suggested that AD should be considered in the application of ML methods for toxicity prediction. , We compared the distributions of the training and test compounds when divided using the time split by visualizing them in several ways.…”

Section: Resultsmentioning

confidence: 99%

Investigation of a Data Split Strategy Involving the Time Axis in Adverse Event Prediction Using Machine Learning

Morita

Mizuno

Kusuhara

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Adverse events are a serious issue in drug development, and many prediction methods using machine learning have been developed. The random split cross-validation is the de facto standard for model building and evaluation in machine learning, but care should be taken in adverse event prediction because this approach does not strictly match the real-world situation. The time split, which uses the time axis, is considered suitable for real-world prediction. However, the differences in model performance obtained using the time and random splits are not clear due to the lack of comparable studies. To understand the differences, we compared the model performance between the time and random splits using nine types of compound information as input, eight adverse events as targets, and six machine learning algorithms. The random split showed higher area under the curve values than did the time split for six of eight targets. The chemical spaces of the training and test datasets of the time split were similar, suggesting that the concept of applicability domain is insufficient to explain the differences derived from the splitting. The area under the curve differences were smaller for the protein interaction than for the other datasets. Subsequent detailed analyses suggested the danger of confounding in the use of knowledge-based information in the time split. These findings indicate the importance of understanding the differences between the time and random splits in adverse event prediction and suggest that appropriate use of the splitting strategies and interpretation of results are necessary for the real-world prediction of adverse events. We provide the analysis code and datasets used in the present study at .

show abstract

“…As a data‐driven approach, recent machine learning techniques based on neural networks trained by chemical constitutions of drugs have been applied to identify culprit drugs of ADR. However, the model targeted only one specific ADR (severe cutaneous adverse reactions) 25 . Considering practical situations with numerous ADRs and combinations of prescribed drugs, it is preferable to specify culprit drugs among administered drugs for an ADR.…”

Section: Discussionmentioning

confidence: 99%

“…However, the model targeted only one specific ADR (severe cutaneous adverse reactions). 25 Considering practical situations with numerous ADRs and combinations of prescribed drugs, it is preferable to specify culprit drugs among administered drugs for an ADR. Moreover, the rank or probability of being a culprit among prescribed drugs would be a meaningful clue for dose reduction or withdrawal.…”

Section: Articlementioning

confidence: 99%

“…The Pharmaceuticals and Medical Devices Agency (PMDA) in Japan provides a large‐scale database of spontaneous adverse events called the Japanese Adverse Drug Event Report (JADER) database 24 . The JADER database, including a type of ADR, concomitant drugs, and diagnosed culprit drugs for each case, is used by researchers and other agencies to research pharmacovigilance 13,25,26 …”

mentioning

confidence: 99%

See 1 more Smart Citation

Estimating Culprit Drugs for Adverse Drug Reactions Based on Bayesian Inference

Hamada

Abé

Kouda

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

The utility of big data in spontaneous adverse drug reactions (ADRs) reporting systems has improved the pharmacovigilance process. However, identifying culprit drugs in ADRs remains challenging, although it is one of the foremost steps to managing ADRs. Aiming to estimate the likelihood of prescribed drugs being culprit drugs for given ADRs, we devised a Bayesian estimation model based on the Japanese Adverse Drug Events Reports database. After developing the model, a validation study was conducted with 67 ADR reports with a gross of 1,387 drugs (67 culprit drugs and 1,320 concomitant drugs) prescribed and recorded at Yamaguchi University Hospital. As a result, the model estimated a culprit drug of ADRs with acceptable accuracy (area under the receiver operating characteristic curve 0.93 (95% confidence interval 0.88-0.97)). The estimation results provided by the model to healthcare practitioners can be used as one clue to determine the culprit drugs for various ADRs, which will improve the management of ADRs by shortening the treatment turnaround time and increasing the precision of diagnosis, leading to minimizing the adverse effects on patients.An adverse drug reaction (ADR) is an unfavorable and unavoidable effect of a drug. 1 ADRs are fundamental problems in medical care worldwide, increasing hospital admissions and morbidity/ mortality. The in-hospital mortality due to ADRs is 0.4-2.7%. 2 ADRs account for ~ 3.5% of hospital admissions. 3,4 Efficient pharmacovigilance, a pharmaceutical science relating to the detection, risk assessment, and prevention of ADRs, is needed to improve drug safety. 5 In the pharmacovigilance process, ADR management includes reducing the dose or withdrawing a culprit drug. When an ADR occurs in patients, identifying the culprit drug is one of the foremost steps to minimize the adverse effects.However, identifying a culprit drug from several candidate drugs remains challenging to this date due to multiple candidate drugs, time-constraints, and sometimes diagnostic urgency. [6][7][8] A previous study demonstrated that 31% of healthcare practitioners reported, "It is often too difficult to identify the causative drug." 7 Although several conventional methods (e.g., Naranjo, Jones, and Karch-Lasagna algorithm) have been used for the identification of the culprit drugs in ADRs, 9-11 these methods did not show acceptable accuracy in medical practice (accuracy 45%). 12 Furthermore, identifying a culprit drug may be more difficult in cases of polypharmacy (usually defined as five or more medications daily) due to many potential candidates. 13,14 In the era of big data, a data-driven approach, such as data mining for early detection of pharmacovigilance signals and artificial intelligence technology for drug safety based on automatic reporting

show abstract

In Silico Approach to Predict Severe Cutaneous Adverse Reactions Using the Japanese Adverse Drug Event Report Database

Cited by 4 publications

References 33 publications

Severe cutaneous adverse reactions to drugs: A real-world pharmacovigilance study using the FDA Adverse Event Reporting System database

Severe cutaneous adverse reactions to drugs: A real-world pharmacovigilance study using the FDA Adverse Event Reporting System database

Investigation of a Data Split Strategy Involving the Time Axis in Adverse Event Prediction Using Machine Learning

Estimating Culprit Drugs for Adverse Drug Reactions Based on Bayesian Inference

Contact Info

Product

Resources

About