Predicting Intervention Approval in Clinical Trials through Multi-Document Summarization

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 1947 - 1957 May 22-27, 2022 c⃝2022 Association for Computational Linguistics Predicting Intervention Approval in Clinical Trials through Multi-Document Summarization Georgios Katsimpras and Georgios Paliouras NCSR Demokritos, Athens, Greece {gkatsibras,paliourg}@iit.demokritos.gr Abstract Clinical trials offer a fundamental opportunity to discover new treatments and advance the medical knowledge. However, the uncertainty of the outcome of a trial can lead to unfore- seen costs and setbacks. In this study, we propose a new method to predict the effec- tiveness of an intervention in a clinical trial. Our method relies on generating an informa- tive summary from multiple documents avail- able in the literature about the intervention un- der study. Specifically, our method first gath- ers all the abstracts of PubMed articles related to the intervention. Then, an evidence sen- tence, which conveys information about the effectiveness of the intervention, is extracted automatically from each abstract. Based on the set of evidence sentences extracted from the abstracts, a short summary about the inter- vention is constructed. Finally, the produced summaries are used to train a BERT-based classifier, in order to infer the effectiveness of an intervention. To evaluate our proposed method, we introduce a new dataset which is a collection of clinical trials together with their associated PubMed articles. Our exper- iments demonstrate the effectiveness of pro- ducing short informative summaries and using them to predict the effectiveness of an interven- tion. 1 Introduction Clinical Trials (CT) present the basic evidence- based clinical research tool for assessing the ef- fectiveness of health interventions. Nevertheless, only a small number of interventions make it suc- cessfully through the process of clinical testing. Approximately, 39%-64% of interventions actually advance to the next step of each phase of clinical trials (DiMasi et al., 2010). The uncertainty of a CT outcome could lead to increased costs, prolonged drug development and ineffective treatment for the participants. At the same time, the volume of pub- lished scientific literature is rapidly growing and offers the opportunity to explore a valuable knowl- edge. Therefore, there is a need to develop new tools which can i) integrate such information and ii) enhance the process of intervention approval in CT. Predicting the approval of an intervention, a task that describes the ability of a system to predict whether an intervention will reach the final stage of clinical testing, is a topic that has been studied before (Gayvert et al., 2016; Lo et al., 2018). The majority of these studies use various traditional machine learning methods and rely on structured data from various sources, including biomedical, chemical or drug databases (Munos et al., 2020; Heinemann et al., 2016). However, only a few stud- ies take into account the textual information that is available online, and mostly in a supplementary manner (Follett et al., 2019; Geletta et al., 2019). In fact, employing natural language processing (NLP) techniques to address the outcome prediction task has been hardly explored. Recognising this lack …

Content truncated to 500 words