Dataset Information

Predicting potential adverse events using safety data from marketed drugs.

ABSTRACT: BACKGROUND:While clinical trials are considered the gold standard for detecting adverse events, often these trials are not sufficiently powered to detect difficult to observe adverse events. We developed a preliminary approach to predict 135 adverse events using post-market safety data from marketed drugs. Adverse event information available from FDA product labels and scientific literature for drugs that have the same activity at one or more of the same targets, structural and target similarities, and the duration of post market experience were used as features for a classifier algorithm. The proposed method was studied using 54 drugs and a probabilistic approach of performance evaluation using bootstrapping with 10,000 iterations. RESULTS:Out of 135 adverse events, 53 had high probability of having high positive predictive value. Cross validation showed that 32% of the model-predicted safety label changes occurred within four to nine years of approval (median: six years). CONCLUSIONS:This approach predicts 53 serious adverse events with high positive predictive values where well-characterized target-event relationships exist. Adverse events with well-defined target-event associations were better predicted compared to adverse events that may be idiosyncratic or related to secondary target effects that were poorly captured. Further enhancement of this model with additional features, such as target prediction and drug binding data, may increase accuracy.

SUBMITTER: Daluwatte C

PROVIDER: S-EPMC7191698 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting potential adverse events using safety data from marketed drugs.

Daluwatte Chathuri C Schotland Peter P Strauss David G DG Burkhart Keith K KK Racz Rebecca R

BMC bioinformatics 20200429 1

<h4>Background</h4>While clinical trials are considered the gold standard for detecting adverse events, often these trials are not sufficiently powered to detect difficult to observe adverse events. We developed a preliminary approach to predict 135 adverse events using post-market safety data from marketed drugs. Adverse event information available from FDA product labels and scientific literature for drugs that have the same activity at one or more of the same targets, structural and target si ...[more]

PMID: 32349656

Similar Datasets

Project description:Background Carotid endarterectomy (CEA) is a major vascular operation for stroke prevention that carries significant perioperative risks; however, outcome prediction tools remain limited. The authors developed machine learning algorithms to predict outcomes following CEA. Methods and Results The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent CEA between 2011 and 2021. Input features included 36 preoperative demographic/clinical variables. The primary outcome was 30-day major adverse cardiovascular events (composite of stroke, myocardial infarction, or death). The data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary metric for evaluating model performance was area under the receiver operating characteristic curve. Model robustness was evaluated with calibration plot and Brier score. Overall, 38 853 patients underwent CEA during the study period. Thirty-day major adverse cardiovascular events occurred in 1683 (4.3%) patients. The best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve of 0.91 (95% CI, 0.90-0.92). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.62 (95% CI, 0.60-0.64), and existing tools in the literature demonstrate area under the receiver operating characteristic curve values ranging from 0.58 to 0.74. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.02. The strongest predictive feature in our algorithm was carotid symptom status. Conclusions The machine learning models accurately predicted 30-day outcomes following CEA using preoperative data and performed better than existing tools. They have potential for important utility in guiding risk-mitigation strategies to improve outcomes for patients being considered for CEA.

Project description:ObjectiveTo integrate pharmacovigilance and network toxicology methods to explore the potential adverse drug events (ADEs) and toxic mechanisms of selumetinib, and to provide a reference for quickly understanding the safety and toxicological mechanisms of newly marketed drugs.MethodsTaking selumetinib as an example, this study integrated pharmacovigilance methods based on real-world data and network toxicology methods to analyze its ADE and its potential toxicological mechanism. First, the ADE reports of selumetinib were extracted from the US Food and Drug Administration (FDA) adverse event reporting system (FAERS), and the ADE signals were detected by reporting odds ratio (ROR) and UK medicines and healthcare products regulatory agency (MHRA) methods. The ADE signals were classified and described according to the preferred terms (PTs) and system organ class (SOC) derived from the Medical Dictionary for Regulatory Activities (MedDRA). The network toxicology method was used to analyze the toxicological mechanism of the interested SOCs. The specific steps included predicting the potential targets of selumetinib using TOXRIC, STITCH, ChEMBL, CTD, SwissTargetPreditcion, and Super-PRED databases, collecting the targets of SOC using GeneCards database, conducting protein-protein interaction (PPI) analysis through STRING database, conducting gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG) analysis through DAVID database, and testing the molecular affinity using AutoDock software.ResultsA total of 1388 ADE reports related to selumetinib were extracted, and 53 positive signals were detected by ROR and MHRA methods, of which 20 signals were not mentioned in the package insert, including ingrowing nail, hyperphosphatemia, cardiac valve disease, hematuria, neutropenia, etc. Analysis of the toxicological mechanism of six SOCs involved in positive ADE signals revealed that the key targets included EGFR, STAT3, AKT1, IL6, BCL2, etc., and the key pathways included PI3K/Akt pathway, apoptosis, ErbB signaling pathway, and EGFR tyrosine kinase inhibitor resistance, etc. Molecular docking assays showed spontaneous binding of selumetinib to key targets in these pathways.ConclusionThe pharmacovigilance analysis identified some new potential ADEs of selumetinib, and the network toxicology analysis showed that the toxic effects of selumetinib may be related to PI3K/Akt pathway, apoptosis, ErbB signaling pathway, EGFR tyrosine kinase inhibitor resistance and other pathways.

Dataset Information

Predicting potential adverse events using safety data from marketed drugs.

Publications

Predicting potential adverse events using safety data from marketed drugs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets