Dataset Information

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel.

ABSTRACT: Introduction: Various methods have been implemented to detect adverse drug reaction (ADR) signals. However, the applicability of machine learning methods has not yet been fully evaluated. Objective: To evaluate the feasibility of machine learning algorithms in detecting ADR signals of nivolumab and docetaxel, new and old anticancer agents. Methods: We conducted a safety surveillance study of nivolumab and docetaxel using the Korea national spontaneous reporting database from 2009 to 2018. We constructed a novel input dataset for each study drug comprised of known ADRs that were listed in the drug labels and unknown ADRs. Given the known ADRs, we trained machine learning algorithms and evaluated predictive performance in generating safety signals of machine learning algorithms (gradient boosting machine [GBM] and random forest [RF]) compared with traditional disproportionality analysis methods (reporting odds ratio [ROR] and information component [IC]) by using the area under the curve (AUC). Each method then was implemented to detect new safety signals from the unknown ADR datasets. Results: Of all methods implemented, GBM achieved the best average predictive performance (AUC: 0.97 and 0.93 for nivolumab and docetaxel). The AUC achieved by each method was 0.95 and 0.92 (RF), 0.55 and 0.51 (ROR), and 0.49 and 0.48 (IC) for respective drug. GBM detected additional 24 and nine signals for nivolumab and 82 and 76 for docetaxel compared to ROR and IC, respectively, from the unknown ADR datasets. Conclusion: Machine learning algorithm based on GBM performed better and detected more new ADR signals than traditional disproportionality analysis methods.

SUBMITTER: Bae JH

PROVIDER: S-EPMC7898680 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel.

Bae Ji-Hwan JH Baek Yeon-Hee YH Lee Jeong-Eun JE Song Inmyung I Lee Jee-Hyong JH Shin Ju-Young JY

Frontiers in pharmacology 20210114

Introduction: Various methods have been implemented to detect adverse drug reaction (ADR) signals. However, the applicability of machine learning methods has not yet been fully evaluated. Objective: To evaluate the feasibility of machine learning algorithms in detecting ADR signals of nivolumab and docetaxel, new and old anticancer agents. Methods: We conducted a safety surveillance study of nivolumab and docetaxel using the Korea national spontaneous reporting database from ...[more]

PMID: 33628176

Similar Datasets

Project description:Background/Objective: Spontaneous reporting systems (SRS) such as the Korea Adverse Event Reporting System (KAERS) are limited in their ability to detect adverse drug reaction (ADR) signals due to their limited data on drug use. Conversely, the national health insurance claim (NHIC) data include drug use information for all qualifying residents. This study aimed to compare ADR signal profiles for antidepressants between KAERS and NHIC, evaluating the extent to which detected signals belong to common ADRs and labeling information. Materials and Methods: ADR signal detection in KAERS and NHIC databases, spanning January to December 2017, employed disproportionality analysis. Signal classes were determined based on System Organ Class (SOC) of the Medical Dictionary for Regulatory Activities (MedDRA). Also, Common ADR Coverage (CAC), the proportion of detected signals deemed common ADRs, and labeling information coverage (LIC) represented by mean average precision (mAP) were calculated. Additionally, protopathic bias and relative risk (RR) evaluation were performed to check for signal robustness. Results: Signal detection revealed 51 and 62 signals in KAERS and NHIC databases, respectively. Both systems predominantly captured signals related to nervous system disorders, comprising 33.3% (N = 17) in KAERS and 50.8% (N = 31) in NHIC. Regarding the type of antidepressants, KAERS predominantly reported signals associated with tricyclic antidepressants (TCAs) (N = 21, 41.2%), while NHIC produced most signals linked to selective serotonin reuptake inhibitors (SSRIs) (N = 22, 35.5%). KAERS exhibited higher CAC (68.63% vs. 29.03%) than NHIC. LIC was also higher in KAERS than in NHIC (mAP for EB05: 1.00 vs. 0.983); i.e., NHIC identified 5 signals not documented in drug labeling information, while KAERS found none. Among the unlabeled signals, one (Duloxetine-Myelopathy) was from protopathic bias, and two (duloxetine-myelopathy and tianeptine-osteomalacia) were statistically significant in RR. Conclusion: NHIC exhibited greater capability in detecting ADR signals associated with antidepressant use, encompassing unlabeled ADR signals, compared to KAERS. NHIC also demonstrated greater potential for identifying less common ADRs. Further investigation is needed for signals detected exclusively in NHIC but not covered by labeling information. This study underscores the value of integrating different sources of data, offering substantial regulatory insights and enriching the scope of pharmacovigilance.

Project description:IntroductionCardiovascular disease remains a significant problem in modern society. Among non-invasive techniques, the electrocardiogram (ECG) is one of the most reliable methods for detecting cardiac abnormalities. However, ECG interpretation requires expert knowledge and it is time-consuming. Developing a novel method to detect the disease early improves the quality and efficiency of medical care.MethodsThe paper presents various modern approaches for classifying cardiac diseases from ECG recordings. The first approach suggests the Poincaré representation of ECG signal and deep-learning-based image classifiers. Additionally, the raw signals were processed with the one-dimensional convolutional model while the XGBoost model was facilitated to predict based on the time-series features.ResultsThe Poincaré-based methods showed decent performance in predicting AF (atrial fibrillation) but not other types of arrhythmia. XGBoost model gave an acceptable performance in long-term data but had a long inference time due to highly-consuming calculations within the pre-processing phase. Finally, the 1D convolutional model, specifically the 1D ResNet, showed the best results in both studied CinC 2017 and CinC 2020 datasets, reaching the F1 score of 85% and 71%, respectively, and they were superior to the first-ranking solution of each challenge. The 1D models also presented high specificity. Additionally, our paper investigated efficiency metrics including power consumption and equivalent CO2 emissions, with one-dimensional models like 1D CNN and 1D ResNet being the most energy efficient. Model interpretation analysis showed that the DenseNet detected AF using heart rate variability while the 1D ResNet assessed the AF patterns in raw ECG signals.DiscussionDespite the under-performed results, the Poincaré diagrams are still worth studying further because of the accessibility and inexpensive procedure. In the 1D convolutional models, the residual connections are useful to keep the model simple but not decrease the performance. Our approach in power measurement and model interpretation helped understand the numerical complexity and mechanism behind the model decision.

Dataset Information

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel.

Publications

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets