A New Biomedical Passage Retrieval Framework for Laboratory Medicine: Leveraging Domain-specific Ontology, Multilevel PRF, and Negation Differential Weighting

Abstract

Clinical decision support (CDS) search is performed to retrieve key medical literature that can assist the practice of medical experts by offering appropriate medical information relevant to the medical case in hand. In this paper, we present a novel CDS search framework designed for passage retrieval from biomedical textbooks in order to support clinical decision-making using laboratory test results. The framework utilizes two unique characteristics of the textual reports derived from the test results, which are syntax variation and negation information. The proposed framework consists of three components: domain ontology, index repository, and query processing engine. We first created a domain ontology to resolve syntax variation by applying the ontology to detect medical concepts from the test results with language translation. We then preprocessed and performed indexing of biomedical textbooks recommended by clinicians for passage retrieval. We finally built the query-processing engine tailored for CDS, including translation, concept detection, query expansion, pseudo-relevance feedback at the local and global levels, and ranking with differential weighting of negation information. To evaluate the effectiveness of the proposed framework, we followed the standard information retrieval evaluation procedure. An evaluation dataset was created, including 28,581 textual reports for 30 laboratory test results and 56,228 passages from widely used biomedical textbooks, recommended by clinicians. Overall, our proposed passage retrieval framework, GPRF-NEG, outperforms the baseline by 36.2, 100.5, and 69.7 percent for MRR, R-precision, and Precision at 5, respectively. Our study results indicate that the proposed CDS search framework specifically designed for passage retrieval of biomedical literature represents a practically viable choice for clinicians as it supports their decision-making processes by providing relevant passages extracted from the sources that they prefer to refer to, with improved performances.

Proximity-Aware Clinical Passage Retrieval Framework by Exploiting Knowledge Structure

“…In this article, we approach proximity-aware retrieval as a query expansion problem as this has been a common means of resolving syntax variations in the CDS searches. One of the critical observations related to query expansions in the CDS searches is that retrieved passages are semantically segmented [37] as they come from different sources stemming from the initial retrieval. Figure 2 presents a list of passages by an initial query.…”

“…We set α to 0.8 to match the best performing value in eariler work [6]. Finally, we combine this function with the node importance weighting, as follows: original query are added to Q, and m is set to be 35 as was done in earlier work [37]. We adapted Terrior to execute the combination by defining a customizing weighting function.…”

“…In this experiment, we have used two datasets: the CDS16 dataset [36] and the CST17 dataset [37]. The CDS16 dataset is a snapshot of the open-access subset of Pubmed Central (PMC), a database of full-text biomedical literature.…”

“…On the other hand, Table 2 shows a partial list of the CST17 dataset [37], which includes 30 cases of patients and its number of syntax variations based on the patients' laboratory test results. The cases can be classified into normal and abnormal cases to determine if the proposed model can capture false-negative cases.…”

“…We evaluate the three proximity-based ranking approaches and previously reported baseline [37] to evaluate the effect of the proximity aspect on the overall CDS search performance. We set the batch size B to be 20.…”