RESUMEN
Randomised trials are often funded by commercial companies and methodological studies support a widely held suspicion that commercial funding may influence trial results and conclusions. However, these studies often have a risk of confounding and reporting bias. The risk of confounding is markedly reduced in meta-epidemiological studies that compare fairly similar trials within meta-analyses, and risk of reporting bias is reduced with access to unpublished data. Therefore, we initiated the COMmercial Funding In Trials (COMFIT) study aimed at investigating the impact of commercial funding on estimated intervention effects in randomised clinical trials based on a consortium of researchers who agreed to share meta-epidemiological study datasets with information on meta-analyses and trials included in meta-epidemiological studies. Here, we describe the COMFIT study, its database, and descriptive results. We included meta-epidemiological studies with published or unpublished data on trial funding source and results or conclusions. We searched five bibliographic databases and other sources. We invited authors of eligible meta-epidemiological studies to join the COMFIT consortium and to share data. The final construction of the COMFIT database involves checking data quality, identifying trial references, harmonising variable categories, and removing non-informative meta-analyses as well as correlated meta-analyses and trial results. We included data from 17 meta-epidemiological studies, covering 728 meta-analyses and 6841 trials. Seven studies (405 meta-analyses, 3272 trials) had not published analyses on the impact of commercial funding, but shared unpublished data on funding source. On this basis, we initiated the construction of a combined database. Once completed, the database will enable comprehensive analyses of the impact of commercial funding on trial results and conclusions with increased statistical power and a markedly reduced risk of confounding and reporting bias.
Asunto(s)
Estudios Epidemiológicos , SesgoRESUMEN
CONTEXT: Citation screening (also called study selection) is a phase of systematic review process that has attracted a growing interest on the use of text mining (TM) methods to support it to reduce time and effort. Search results are usually imbalanced between the relevant and the irrelevant classes of returned citations. Class imbalance among other factors has been a persistent problem that impairs the performance of TM models, particularly in the context of automatic citation screening for systematic reviews. This has often caused the performance of classification models using the basic title and abstract data to ordinarily fall short of expectations. OBJECTIVE: In this study, we explore the effects of using full bibliography data in addition to title and abstract on text classification performance for automatic citation screening. METHODS: We experiment with binary and Word2vec feature representations and SVM models using 4 software engineering (SE) and 15 medical review datasets. We build and compare 3 types of models (binary-non-linear, Word2vec-linear and Word2vec-non-linear kernels) with each dataset using the two feature sets. RESULTS: The bibliography enriched data exhibited consistent improved performance in terms of recall, work saved over sampling (WSS) and Matthews correlation coefficient (MCC) in 3 of the 4 SE datasets that are fairly large in size. For the medical datasets, the results vary, however in the majority of cases the performance is the same or better. CONCLUSION: Inclusion of the bibliography data provides the potential of improving the performance of the models but to date results are inconclusive.
Asunto(s)
Bibliografías como Asunto , Minería de Datos/métodos , Automatización , Biología Computacional/métodos , Modelos TeóricosRESUMEN
CONTEXT: Independent validation of published scientific results through study replication is a pre-condition for accepting the validity of such results. In computation research, full replication is often unrealistic for independent results validation, therefore, study reproduction has been justified as the minimum acceptable standard to evaluate the validity of scientific claims. The application of text mining techniques to citation screening in the context of systematic literature reviews is a relatively young and growing computational field with high relevance for software engineering, medical research and other fields. However, there is little work so far on reproduction studies in the field. OBJECTIVE: In this paper, we investigate the reproducibility of studies in this area based on information contained in published articles and we propose reporting guidelines that could improve reproducibility. METHODS: The study was approached in two ways. Initially we attempted to reproduce results from six studies, which were based on the same raw dataset. Then, based on this experience, we identified steps considered essential to successful reproduction of text mining experiments and characterized them to measure how reproducible is a study given the information provided on these steps. 33 articles were systematically assessed for reproducibility using this approach. RESULTS: Our work revealed that it is currently difficult if not impossible to independently reproduce the results published in any of the studies investigated. The lack of information about the datasets used limits reproducibility of about 80% of the studies assessed. Also, information about the machine learning algorithms is inadequate in about 27% of the papers. On the plus side, the third party software tools used are mostly free and available. CONCLUSIONS: The reproducibility potential of most of the studies can be significantly improved if more attention is paid to information provided on the datasets used, how they were partitioned and utilized, and how any randomization was controlled. We introduce a checklist of information that needs to be provided in order to ensure that a published study can be reproduced.