Dataset Information

A hierarchical testing approach for detecting safety signals in clinical trials.

ABSTRACT: Detecting safety signals in clinical trial safety data is known to be challenging due to high dimensionality, rare occurrence, weak signal, and complex dependence. We propose a new hierarchical testing approach for analyzing safety data from a typical randomized clinical trial. This approach accounts for the hierarchical structure of adverse events (AEs), that is, AEs are categorized by system organ class (SOC). Our approach contains two steps: the first step tests, for each SOC, whether any AEs within this SOC are differently distributed between treatment arms; and the second step identifies signal AEs from SOCs passing the first step tests. We show the superiority, in terms of power of detecting safety signals given controlled false discovery rate, of the new approach comparing with currently available approaches through simulation studies. We also demonstrate this approach with two real data examples.

SUBMITTER: Tan X

PROVIDER: S-EPMC8258607 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A hierarchical testing approach for detecting safety signals in clinical trials.

Tan Xianming X Chen Bingshu E BE Sun Jianping J Patel Tejendra T Ibrahim Joseph G JG

Statistics in medicine 20200212 10

Detecting safety signals in clinical trial safety data is known to be challenging due to high dimensionality, rare occurrence, weak signal, and complex dependence. We propose a new hierarchical testing approach for analyzing safety data from a typical randomized clinical trial. This approach accounts for the hierarchical structure of adverse events (AEs), that is, AEs are categorized by system organ class (SOC). Our approach contains two steps: the first step tests, for each SOC, whether any AEs ...[more]

PMID: 32050050

Similar Datasets

Project description:ObjectiveCohort selection for clinical trials is a key step for clinical research. We proposed a hierarchical neural network to determine whether a patient satisfied selection criteria or not.Materials and methodsWe designed a hierarchical neural network (denoted as CNN-Highway-LSTM or LSTM-Highway-LSTM) for the track 1 of the national natural language processing (NLP) clinical challenge (n2c2) on cohort selection for clinical trials in 2018. The neural network is composed of 5 components: (1) sentence representation using convolutional neural network (CNN) or long short-term memory (LSTM) network; (2) a highway network to adjust information flow; (3) a self-attention neural network to reweight sentences; (4) document representation using LSTM, which takes sentence representations in chronological order as input; (5) a fully connected neural network to determine whether each criterion is met or not. We compared the proposed method with its variants, including the methods only using the first component to represent documents directly and the fully connected neural network for classification (denoted as CNN-only or LSTM-only) and the methods without using the highway network (denoted as CNN-LSTM or LSTM-LSTM). The performance of all methods was measured by micro-averaged precision, recall, and F1 score.ResultsThe micro-averaged F1 scores of CNN-only, LSTM-only, CNN-LSTM, LSTM-LSTM, CNN-Highway-LSTM, and LSTM-Highway-LSTM were 85.24%, 84.25%, 87.27%, 88.68%, 88.48%, and 90.21%, respectively. The highest micro-averaged F1 score is higher than our submitted 1 of 88.55%, which is 1 of the top-ranked results in the challenge. The results indicate that the proposed method is effective for cohort selection for clinical trials.DiscussionAlthough the proposed method achieved promising results, some mistakes were caused by word ambiguity, negation, number analysis and incomplete dictionary. Moreover, imbalanced data was another challenge that needs to be tackled in the future.ConclusionIn this article, we proposed a hierarchical neural network for cohort selection. Experimental results show that this method is good at selecting cohort.

Project description:BackgroundThe use of porcine islets to replace insulin-producing islet β-cells, destroyed during the diabetogenic disease process, presents distinct challenges if this option is to become a therapeutic reality for the treatment of type 1 diabetes. These challenges include a thorough evaluation of the microbiological safety of the islets. In this study, we describe a robust porcine islet-screening program that provides a high level of confidence in the microbiological safety of porcine islets suitable for clinical trials.MethodsA four-checkpoint program systematically screens the donor herd (Large White - Yorkshire × Landrace F1 hybrid animals), individual sentinel and pancreas donor animals and, critically, the islet macrobeads themselves. Molecular assays screen for more than 30 known viruses, while electron microscopy and in vitro studies are employed to screen for potential new or divergent (emergent) viruses.ResultsOf 1207 monthly samples taken from random animals over a 2-year period, only a single positive result for Transmissible gastroenteritis virus was observed, demonstrating the high level of biosecurity maintained in the source herd. Given the lack of clinical signs, positive antibody titers for Porcine reproductive and respiratory syndrome virus, Porcine parvovirus, and Influenza A confirm the efficacy of the herd vaccination program. Porcine respiratory coronavirus was found to be present in the herd, as expected for domestic swine. Tissue homogenate samples from six sentinel and 11 donor animals, over the same 2-year period, were negative for the presence of viruses when co-cultured with six different cell lines from four species. The absence of adventitious viruses in separate islet macrobead preparations produced from 12 individual pancreas donor animals was confirmed using validated molecular (n = 32 viruses), in vitro culture (cells from four species), and transmission electron microscopy assays (200 cell profiles per donor animal) over the same 2-year period. There has been no evidence of viral transmission following the implantation of these same encapsulated and functional porcine islets into non-immunosuppressed diabetic cynomolgus macaques for up to 4 years. Isolated peripheral blood mononuclear cells from all time points were negative for PCV (Type 2), PLHV, PRRSV, PCMV, and PERV-A, PERV-B, and PERV-C by PCR analysis in all six recipient animals.ConclusionThe four-checkpoint program is a robust and reliable method for characterization of the microbiological safety of encapsulated porcine islets intended for clinical trials.

Dataset Information

A hierarchical testing approach for detecting safety signals in clinical trials.

Publications

A hierarchical testing approach for detecting safety signals in clinical trials.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets