Dataset Information

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

ABSTRACT: Severe cutaneous adverse reactions (SCARs), such as Stevens-Johnson syndrome/toxic epidermal necrolysis and drug-induced hypersensitivity syndrome, are rare and occasionally fatal. However, it is difficult to detect SCARs at the drug development stage, necessitating a new approach for prediction. Therefore, in this study, using the chemical structure information of SCAR-causative drugs from the Japanese Adverse Drug Event Report (JADER) database, we tried to develop a predictive classification model of SCAR through deep learning. In the JADER database from 2004 to 2017, we defined 185 SCAR-positive drugs and 195 SCAR-negative drugs using proportional reporting ratios as the signal detection method, and the total number of reports. These SCAR-positive and SCAR-negative drugs were randomly divided into the training dataset for model construction and the test dataset for evaluation. The model performance was evaluated in the independent test dataset inside the applicability domain (AD), which is the chemical space for reliable prediction results. Using the deep learning model with molecular descriptors as the drug structure information, the area under the curve was 0.76 for the 148 drugs of the test dataset inside the AD. The method developed in the present study allows for utilizing the JADER database for SCAR classification, with potential to improve screening efficiency in the development of new drugs. This method may also help to noninvasively identify the causative drug, and help assess the causality between drugs and SCARs in postmarketing surveillance.

SUBMITTER: Ambe K

PROVIDER: S-EPMC7993315 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:IntroductionAnticholinergic adverse effects (AEs) are a problem for elderly people. This study aimed to answer the following questions. First, is an analysis of anticholinergic AEs using spontaneous adverse drug event databases possible? Second, what is the main drug suspected of inducing anticholinergic AEs in the databases? Third, do database differences yield different results?MethodsWe used two databases: the US Food and Drug Administration Adverse Event Reporting System database (FAERS) and the Japanese Adverse Drug Event Report database (JADER) recorded from 2004 to 2020. We defined three types of anticholinergic AEs: central nervous system (CNS) AEs, peripheral nervous system (PNS) AEs, and a combination of these AEs. We counted the number of cases and evaluated the ratio of drug-anticholinergic AE pairs between FAERS and JADER. We computed reporting odds ratios (RORs) and assessed the drugs using Beers Criteria®.ResultsConstipation was the most reported AE in FAERS. The ratio of drug-anticholinergic AE pairs was statistically significantly larger in FAERS than JADER. Overactive bladder agents were suspected drugs common to both databases. Other drugs differed between the two databases. CNS AEs were associated with antidementia drugs in FAERS and opioids in JADER. In the assessment using Beers Criteria®, signals were detected for almost all drugs. Between the two databases, a significantly higher positive correlation was observed for PNS AEs (correlation coefficient 0.85, P = 0.0001). The ROR was significantly greater in JADER.ConclusionsThere are many methods to investigate AEs. This study shows that the analysis of anticholinergic AEs using spontaneous adverse drug event databases is possible. From this analysis, various suspected drugs were detected. In particular, FAERS had many cases. The differences in the results between the two databases may reflect differences in the reporting countries. Further study of the relationship between drugs and CNS AEs should be conducted.

Project description:Hiccups are occasionally experienced by most individuals. Although hiccups are not life-threatening, they may lead to a decline in quality of life. Previous studies showed that hiccups may occur as an adverse effect of certain medicines during chemotherapy. Furthermore, a male dominance in hiccups has been reported. However, due to the limited number of studies conducted on this phenomenon, debate still surrounds the few factors influencing hiccups. The present study aimed to investigate the influence of medicines and patient characteristics on hiccups using a large-sized adverse drug event report database and, specifically, the Japanese Adverse Drug Event Report (JADER) database. Cases of adverse effects associated with medications were extracted from JADER, and Fisher's exact test was performed to assess the presence or absence of hiccups for each medication. In a multivariate analysis, we conducted a multiple logistic regression analysis using medication and patient characteristic variables exhibiting significance. We also examined the role of dexamethasone in inducing hiccups during chemotherapy. Medicines associated with hiccups included dexamethasone, levofolinate, fluorouracil, oxaliplatin, carboplatin, and irinotecan. Patient characteristics associated with hiccups included a male gender and greater height. The combination of anti-cancer agent and dexamethasone use was noted in more than 95% of patients in the dexamethasone-use group. Hiccups also occurred in patients in the anti-cancer agent-use group who did not use dexamethasone. Most of the medications that induce hiccups are used in chemotherapy. The results of the present study suggest that it is possible to predict a high risk of hiccups using patient characteristics. We confirmed that dexamethasone was the drug that has the strongest influence on the induction of hiccups. However, the influence of anti-cancer agents on the induction of hiccups cannot be denied. We consider the results of the present study to be helpful for the prevention and treatment of hiccups.

Project description:Drug-induced gastrointestinal obstruction (DIGO) and gastrointestinal perforation (DIGP) may be the result of gastrointestinal hypomotility and severe constipation, which may lead to potentially fatal complications of bowel ischemia, sepsis and perforation. We evaluated the onset profile of DIGs (DIGO and DIGP) associated with prescription drugs by analyzing data in the Japanese Adverse Drug Event Report (JADER) database. We selected 161 DIG-related drugs and categorized them into 19 classes based on the Anatomical Therapeutic Chemical (ATC) Classification System. Finally, we focused on 58 drugs and conducted subsequent analyses for the time-to-onset and outcomes. We extracted 79 preferred terms (PTs) with the strings "ileus," "stenosis," "obstruction," "obstructive," "impaction," "perforation," "perforated," "hypomotility," and "intussusception" from the Standardized Medical Dictionary for Regulatory Activities (MedDRA) Queries (SMQs) of SMQ20000104: gastrointestinal perforation, ulcer, hemorrhage, obstruction non-specific findings/procedures; SMQ20000105: gastrointestinal obstruction; and SMQ20000107: gastrointestinal perforation. Among the 667, 729 reports in the JADER database submitted between April 2004 and November 2020, we identified 11,351 occurrences of DIGs. The reporting odds ratios (RORs) (95% confidence interval) of "barium sulfate containing X-ray media," "drugs for treatment of hyperkalemia and hyperphosphatemia," and "oral bowel cleanser" were 142.0 (127.1-158.6), 25.8 (23.1-28.8), and 29.7 (24.8-35.6), respectively. The median number of days (interquartile range) until the onset of an adverse event caused by each drug category was as follows: barium sulfate containing X-ray contrast media [2.0 (1.0-3.0)], diazepines, oxazepines, thiazepines, and oxepines [8.0 (8.0-18.5)], drugs for treatment of hyperkalemia and hyperphosphatemia [29.0 (8.0-55.0)], non-selective monoamine reuptake inhibitors [19.0 (7.0-47.5)], and oral bowel cleanser [0.0 (0.0-0.0)]. Depending on the drug, the time to onset of side effects ranged from days to several months. Our results highlighted the need to perform detailed monitoring of each drug for possible association with DIGs, which might otherwise have fatal consequences.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets