Dataset Information

Feasibility of feature-based indexing, clustering, and search of clinical trials. A case study of breast cancer trials from ClinicalTrials.gov.

ABSTRACT: When standard therapies fail, clinical trials provide experimental treatment opportunities for patients with drug-resistant illnesses or terminal diseases. Clinical Trials can also provide free treatment and education for individuals who otherwise may not have access to such care. To find relevant clinical trials, patients often search online; however, they often encounter a significant barrier due to the large number of trials and in-effective indexing methods for reducing the trial search space.This study explores the feasibility of feature-based indexing, clustering, and search of clinical trials and informs designs to automate these processes.We decomposed 80 randomly selected stage III breast cancer clinical trials into a vector of eligibility features, which were organized into a hierarchy. We clustered trials based on their eligibility feature similarities. In a simulated search process, manually selected features were used to generate specific eligibility questions to filter trials iteratively.We extracted 1,437 distinct eligibility features and achieved an inter-rater agreement of 0.73 for feature extraction for 37 frequent features occurring in more than 20 trials. Using all the 1,437 features we stratified the 80 trials into six clusters containing trials recruiting similar patients by patient-characteristic features, five clusters by disease-characteristic features, and two clusters by mixed features. Most of the features were mapped to one or more Unified Medical Language System (UMLS) concepts, demonstrating the utility of named entity recognition prior to mapping with the UMLS for automatic feature extraction.It is feasible to develop feature-based indexing and clustering methods for clinical trials to identify trials with similar target populations and to improve trial search efficiency.

SUBMITTER: Boland MR

PROVIDER: S-EPMC3796134 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feasibility of feature-based indexing, clustering, and search of clinical trials. A case study of breast cancer trials from ClinicalTrials.gov.

Boland M R MR Miotto R R Gao J J Weng C C

Methods of information in medicine 20130513 5

<h4>Background</h4>When standard therapies fail, clinical trials provide experimental treatment opportunities for patients with drug-resistant illnesses or terminal diseases. Clinical Trials can also provide free treatment and education for individuals who otherwise may not have access to such care. To find relevant clinical trials, patients often search online; however, they often encounter a significant barrier due to the large number of trials and in-effective indexing methods for reducing th ...[more]

PMID: 23666475

Similar Datasets

Project description:Background/aims The Food and Drug Administration Amendments Act mandates that applicable clinical trials report basic summary results to the ClinicalTrials.gov database within 1?year of trial completion or termination. We aimed to determine the proportion of pulmonary trials reporting basic summary results to ClinicalTrials.gov and assess factors associated with reporting. Methods We identified pulmonary clinical trials subject to the Food and Drug Administration Amendments Act (called highly likely applicable clinical trials) that were completed or terminated between 2008 and 2012 and reported results by September 2013. We estimated the cumulative percentage of applicable clinical trials reporting results by pulmonary disease category. Multivariable Cox regression modeling identified characteristics independently associated with results reporting. Results Of 1450 pulmonary highly likely applicable clinical trials, 380 (26%) examined respiratory neoplasms, 238 (16%) asthma, 175 (12%) chronic obstructive pulmonary disease, and 657 (45%) other respiratory diseases. Most (75%) were pharmaceutical highly likely applicable clinical trials and 71% were industry-funded. Approximately 15% of highly likely applicable clinical trials reported results within 1?year of trial completion, while 55% reported results over the 5-year study period. Earlier phase highly likely applicable clinical trials were less likely to report results compared to phase 4 highly likely applicable clinical trials (phases 1/2 and 2 (adjusted hazard ratio 0.41 (95% confidence interval: 0.31-0.54)), phases 2/3 and 3 (adjusted hazard ratio 0.55 (95% confidence interval: 0.42-0.72)) and phase not applicable (adjusted hazard ratio 0.43 (95% confidence interval: 0.29-0.63)). Pulmonary highly likely applicable clinical trials without Food and Drug Administration oversight were less likely to report results compared with those with oversight (adjusted hazard ratio 0.65 (95% confidence interval: 0.51-0.83)). Conclusion A total of 15% of pulmonary clinical highly likely applicable clinical trials report basic summary results to ClinicalTrials.gov within 1?year of trial completion. Strategies to improve reporting are needed within the pulmonary community.

Project description:Understanding functions of proteins is one of the most important challenges in many studies of biological processes. The function of a protein can be predicted by analyzing the functions of structurally similar proteins, thus finding structurally similar proteins accurately and efficiently from a large set of proteins is crucial. A protein structure can be represented as a vector by 3D-Zernike Descriptor (3DZD) which compactly represents the surface shape of the protein tertiary structure. This simplified representation accelerates the searching process. However, computing the similarity of two protein structures is still computationally expensive, thus it is hard to efficiently process many simultaneous requests of structurally similar protein search. This paper proposes indexing techniques which substantially reduce the search time to find structurally similar proteins. In particular, we first exploit two indexing techniques, i.e., iDistance and iKernel, on the 3DZDs. After that, we extend the techniques to further improve the search speed for protein structures. The extended indexing techniques build and utilize an reduced index constructed from the first few attributes of 3DZDs of protein structures. To retrieve top-k similar structures, top-10 × k similar structures are first found using the reduced index, and top-k structures are selected among them. We also modify the indexing techniques to support θ-based nearest neighbor search, which returns data points less than θ to the query point. The results show that both iDistance and iKernel significantly enhance the searching speed. In top-k nearest neighbor search, the searching time is reduced 69.6%, 77%, 77.4% and 87.9%, respectively using iDistance, iKernel, the extended iDistance, and the extended iKernel. In θ-based nearest neighbor serach, the searching time is reduced 80%, 81%, 95.6% and 95.6% using iDistance, iKernel, the extended iDistance, and the extended iKernel, respectively.

Project description:Objective: Clinical trials are the most effective method for evaluating therapeutic strategies. The purpose of this study was to comprehensively assess the characteristics of trials on lupus nephritis (LN) and provide a reference for LN treatment and research. Methods: Registered therapeutic trials on drug interventions for LN were obtained from ClinicalTrials.gov up to December 3, 2020. The general characteristics, methodological characteristics, detailed characteristics, investigated drugs, eligibility criteria, and outcome measures of these trials were analyzed. Results: A total of 126 eligible trials were evaluated, and these trials mainly investigated the initial treatment of adult proliferative LN. Half of the trials enrolled <50 participants, and 70.7% of the trials lasted for 6-24 months. In total, 95.2% of trials adopted an interventional study design. Of intervention trials, 56.6% were in phase 2 or phase 3, 76.7% were randomized, 77.5% employed a parallel assignment, and 41.7% were masked. The eligibility criteria and outcome measures of the included trials varied and involved a variety of indicators. Chemical agents and biologics are the most widely studied immunotherapies, of which mycophenolate mofetil, tacrolimus, and rituximab are the most studied. In addition, some trials studied cell transplantation treatment. Conclusions: The majority of clinical trials for LN therapy registered on ClinicalTrials.gov investigated the initial treatment of adult proliferative LN, and most of these trials were randomized, parallel assigned, and insufficiently masked interventional trials with small scale, short duration, various eligibility criteria, and outcome measures. We hope that more large-scale, long-term multicenter, and high-quality RCT trials with standardized inclusion criteria/exclusion criteria and treatment effect evaluation systems will be conducted and that more energy and funding will be put into exploring biological products and stem cell therapies. In addition, trials for membranous LN, childhood-onset LN, and maintenance phase LN are needed to establish optimal treatment strategies.

Dataset Information

Feasibility of feature-based indexing, clustering, and search of clinical trials. A case study of breast cancer trials from ClinicalTrials.gov.

Publications

Feasibility of feature-based indexing, clustering, and search of clinical trials. A case study of breast cancer trials from ClinicalTrials.gov.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets