Streamlining Considerations for Safety Measures: A Predictive Model for Addition of Clinically Significant Adverse Reactions to Japanese Drug Package Inserts.

The addition of clinically significant adverse reactions (CSARs) to Japanese package inserts (PIs) is an important safety measure that can be used to inform medical personnel of potential health risks; however, determining the necessity of their addition can be lengthy and complex. Therefore, we aimed to construct a machine learning-based model that can predict the addition of CSARs at an early stage due to the accumulation of both Japanese and overseas adverse drug reaction (ADR) cases. The target comprised CSARs added to PIs from August 2011 to March 2022. The control group consisted of drugs without the same CSARs in their PIs by March 2022. Features were generated using ADR case accumulation data obtained from the Japanese Adverse Drug Event Report and the U.S. Food and Drug Administration Adverse Event Reporting System databases. The model was constructed using DataRobot, and its performance evaluated using the Matthews correlation coefficient. The target for the addition of CSARs included 414 cases, comprising 302 due to domestic case accumulation, 22 due to both domestic and overseas case accumulation, 12 due to overseas case accumulation, and 78 due to revisions of the company core data sheet. The best model was a generalized linear model with informative features, achieving a cross-validation of 0.8754 and a holdout of 0.8995. In conclusion, the proposed model effectively predicted CSAR additions to PIs resulting from the accumulation of ADR cases using data from both Japan and the United States.

Predicting the Addition of Information Regarding Clinically Significant Adverse Drug Reactions to Japanese Drug Package Inserts Using a Machine-Learning Model.

PURPOSE: To develop a machine learning (ML)-based model for predicting the addition of clinically significant adverse reaction (CSAR)-associated information to drug package inserts (PIs) based on information of adverse drug reaction (ADR) cases during the post-marketing stage in Japan. METHODS: We collected data on CSARs added to PIs from August 2011 to March 2020. ADR cases that led to CSARs resulting in PI revisions were considered as a positive case, and ML was used to construct a binary classification model to predict the PI revisions. We selected 34 features based on the ADR aggregate data collected 6 months before PI revisions. Prediction performance was evaluated using the Matthews correlation coefficient (MCC). RESULTS: We found CSAR information added to PIs in 617 cases, 334 of which were due to the accumulation of domestic cases, and used only domestic case data for the prediction model. Among prediction models developed using several kinds of algorithms, the support vector machine with the radial basis function kernel with feature selection showed the highest predictive performance, having an MCC of 0.938 for the cross-validation and 0.922 for the test dataset. The feature with the highest importance in the model was the "average number of patients reported per quarter." CONCLUSION: Our model accurately predicted PI revisions using information on ADR cases that occurred 6 months before. This is the first ML model that can predict the necessary safety measures and is an efficient method for guiding the decision to adopt additional safety measures early.

Epidemiology and predictors of hyponatremia in a contemporary cohort of patients with malignancy: a retrospective cohort study.

Background: Hyponatremia is associated with worse outcomes among patients with malignancy. However, contemporary cohort data on epidemiology and risk factors are lacking. Methods: In this single-centre, retrospective cohort study, patients who received intravenous antineoplastic agents from 2018 to 2020 at Nagoya City University Hospital were enrolled. Associations of demographics, antineoplastic agents, types of malignancy and concomitant medications with hyponatremia, defined as serum sodium concentration ≤130 mmol/l, were analysed by mixed-effects logistic regression and the machine learning-based LightGBM model artificial intelligence technology. Results: Among 2644 patients, 657 (24.8%) developed at least one episode of hyponatremia. Approximately 80% of hyponatremia was due to sodium wasting from the kidneys. Variables associated with hyponatremia both by mixed-effects logistic regression and the LightGBM model were older age, hypoalbuminemia and higher estimated glomerular filtration rate. Among antineoplastic agents, cisplatin {odds ratio [OR] 1.52 [95% confidence interval (CI) 1.18-1.96]}, pembrolizumab [OR 1.42 (95% CI 1.02-1.97)] and bortezomib [OR 3.04 (95% CI 1.96-4.71)] were associated with hyponatremia and these variables also had a positive impact on predicted hyponatremia in the LightGBM model. Conclusions: Hyponatremia was common among patients with malignancy. In addition to older age and poor nutritional status, novel antineoplastic agents, including immune checkpoint inhibitors and bortezomib, should be recognized as risk factors for hyponatremia.

Comparison of Efficacy and Safety of Direct Oral Anticoagulants and Warfarin between Patients in Asian and Non-Asian Regions: A Systematic Review and Meta-Regression Analysis.

Direct oral anticoagulants (DOACs) have increasingly replaced warfarin for treating patients with non-valvular atrial fibrillation (NVAF). DOACs have been demonstrated to be more useful than warfarin, which was highlighted at its ethnic differences in efficacy and safety; however, the regional differences of DOACs remain unclear. We conducted a systematic review, meta-analysis, and meta-regression to evaluate the efficacy and safety of DOACs in patients from Asian and non-Asian regions with NVAF. We systematically searched randomized control trials published before August 2019. We defined 11 studies comprising 7,118 Asian and 53,282 non-Asian patients, totaling 60,400 patients with NVAF. The risk ratios (RRs) of DOACs were calculated against warfarin. The efficacy of DOACs was significantly higher in Asian regions regarding stroke/systemic embolism events (RR: 0.62 and 95% confidence interval (CI): 0.49-0.78 for the Asian region; RR: 0.83 and 95% CI: 0.75-0.92 for non-Asian regions; P interaction: 0.02), when compared with warfarin. The safety of DOACs was significantly higher in Asian regions regarding major bleeding (RR: 0.62 and 95% CI: 0.51-0.75 for Asian regions; RR: 0.90 and 95% CI: 0.76-1.05 for non-Asian regions; P interaction: 0.004), compared with warfarin. In addition, we conducted meta-regression analysis to discuss the true regional differences of DOACs to warfarin. The meta-regression analysis, which adjusts the effect of individual backgrounds in each study, indicated that the regional differences were observed in the efficacy but not in drug safety. These results suggest that treatment with DOACs may be more effective than the conventional warfarin in the Asian region.

Development of quantitative model of a local lymph node assay for evaluating skin sensitization potency applying machine learning CatBoost.

The estimated concentrations for a stimulation index of 3 (EC3) in murine local lymph node assay (LLNA) is an important quantitative value for determining the strength of skin sensitization to chemicals, including cosmetic ingredients. However, animal testing bans on cosmetics in Europe necessitate the development of alternative testing methods to LLNA. A machine learning-based prediction method can predict complex toxicity risks from multiple variables. Therefore, we developed an LLNA EC3 regression model using CatBoost, a new gradient boosting decision tree, based on the reliable Cosmetics Europe database which included data for 119 substances. We found that a model using in chemico/in vitro tests, physical properties, and chemical information associated with key events of skin sensitization adverse outcome pathway as variables showed the best performance with a coefficient of determination (R2) of 0.75. In addition, this model can indicate the variable importance as the interpretation of the model, and the most important variable was associated with the human cell line activation test that evaluate dendritic cell activation. The good performance and interpretability of our LLNA EC3 predictable regression model suggests that it could serve as a useful approach for quantitative assessment of skin sensitization.

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

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.

Comparison of Efficacy of Dipeptidyl Peptidase-4 Inhibitors and Sodium-Glucose Co-Transporter 2 Inhibitors Between Japanese and Non-Japanese Patients: A Meta-Analysis.

We explored efficacy of dipeptidyl peptidase-4 inhibitors (DPP-4is) and sodium-glucose co-transporter 2 inhibitors (SGLT2is) between Japanese and non-Japanese patients with type 2 diabetes mellitus by conducting a systematic review and meta-analysis. A literature search of public databases before May 2017 identified 91 (DPP-4i) and 63 (SGLT2i) randomized placebo-controlled trials (> 12-week treatment). Multivariate meta-regression analysis identified baseline hemoglobin A1c (HbA1c) levels and placebo responses as covariates affecting efficacy of two agent classes independently of study region (Japanese/non-Japanese). When accounted for covariates, DPP-4i caused more pronounced HbA1c reduction in Japanese studies than in non-Japanese studies by 0.18% difference (P < 0.05) while causing no difference in fasting plasma glucose reduction between regions. On the other hand, when adjusted by baseline HbA1c levels and placebo responses, efficacy of SGLT2i were comparable between regions. The contrasting results for two agent classes indicate that drug efficacy is affected by different pathophysiology at its therapeutic action point.

Comparison of the developmental/reproductive toxicity and hepatotoxicity of phthalate esters in rats using an open toxicity data source.

Phthalate esters (PEs) are widely used as plasticizers in various kinds of plastic products. Some PEs have been known to induce developmental and reproductive toxicity (DART) as well as hepatotoxicity in laboratory animals. In some cases of DART, the strength of toxicity of PEs depends on the side chain lengths, while the relationship between hepatotoxicity and side chain length is unknown. Therefore, in this study, we compared DART and hepatotoxicity in rats, focusing on 6 PEs with different side chains. We collected toxicity data of 6 PEs, namely, n-butyl benzyl phthalate (BBP), di-n-butyl phthalate (DBP), di(2-ethylhexyl) phthalate (DEHP), di-isodecyl phthalate (DIDP), di-isononyl phthalate (DINP), and di-n-octyl phthalate (DNOP), from open data source, then, we constructed the toxicity database to comprehensively and efficiently compare the toxicity effects. When we compared DART using the toxicity database, we found that BBP, DBP, and DEHP with short side chains showed strong toxicities against the reproductive organs of male offspring, and the No-Observed-Adverse-Effect Levels (NOAELs) of BBP, DBP, and DEHP were lower than DIDP, DINP, and DNOP with long side chains. Comparing hepatotoxicities, the lowest NOAEL was shown 14 mg/kg/day for DEHP, based on liver weight gain with histopathological changes. However, as BBP and DBP showed higher NOAEL than the other 3 PEs (DIDP, DINP, and DNOP), we conclude that hepatotoxicity does not depend on the length of side chain. Concerning side chain length of PEs, we effectively utilized our constructed database and found that DART and hepatotoxicity in rats showed different modes of toxicities.

In Silico Prediction of Chemical-Induced Hepatocellular Hypertrophy Using Molecular Descriptors.

In silico prediction for toxicity of chemicals is required to reduce cost, time, and animal testing. However, predicting hepatocellular hypertrophy, which often affects the derivation of the No-Observed-Adverse-Effect Level in repeated dose toxicity studies, is difficult because pathological findings are diverse, mechanisms are largely unknown, and a wide variety of chemical structures exists. Therefore, a method for predicting the hepatocellular hypertrophy of diverse chemicals without complete understanding of their mechanisms is necessary. In this study, we developed predictive classification models of hepatocellular hypertrophy using machine learning-specifically, deep learning, random forest, and support vector machine. We extracted hepatocellular hypertrophy data on rats from 2 toxicological databases, our original database developed from risk assessment reports such as pesticides, and the Hazard Evaluation Support System Integrated Platform. Then, we constructed prediction models based on molecular descriptors and evaluated their performance using independent test chemicals datasets, which differed from the training chemicals datasets. Further, we defined the applicability domain (AD), which generally limits the application for chemicals, as structurally similar to the training chemicals dataset. The best model was found to be the support vector machine model using the Hazard Evaluation Support System Integrated Platform dataset, which was trained with 251 chemicals and predicted 214 test chemicals inside the applicability domain. It afforded a prediction accuracy of 0.76, sensitivity of 0.90, and area under the curve of 0.81. These in silico predictive classification models could be reliable tools for hepatocellular hypertrophy assessments and can facilitate the development of in silico models for toxicity prediction.