Matching Patient Records to Clinical Trials Using Ontologies

Abstract

Abstract. This paper describes a large case study that explores the applicability of ontology reasoning to problems in the medical domain. We investigate whether it is possible to use such reasoning to automate common clinical tasks that are currently labor intensive and error prone, and focus our case study on improving cohort selection for clinical trials. An obstacle to automating such clinical tasks is the need to bridge the semantic gulf between raw patient data, such as laboratory tests or specific medications, and the way a clinician interprets this data. Our key insight is that matching patients to clinical trials can be formulated as a problem of semantic retrieval. We describe the technical challenges to building a realistic case study, which include problems related to scalability, the integration of large ontologies, and dealing with noisy, inconsistent data. Our solution is based on the SNOMED CT R ontology, and scales to one year of patient records (approx. 240,000 patients).

Towards the Automated Calculation of Clinical Quality Indicators

“…In the following, we describe two methods for clinical trial recruitment [1], [13] that are based on Semantic Web technologies. Similar to our approach, both methods employ a terminology.…”

“…They use the NCI ontology to represent both patient data and the eligibility criteria. Patel et al [13] demonstrated that clinical trial criteria can be formulated as description logic queries, which a reasoner can use together with SNOMED CT to infer implicit information that results in retrieving eligible patients.…”

Scalable highly expressive reasoner (SHER)

“…In collaboration with Columbia University Medical Center, we used SHER to design a solution for the problem of finding matching patient records for clinical trials criteria [10]. Currently, there are approximately 65,000 clinical trials that are designed to test various drugs and proce-250 dures.…”

Mathematical Logic for Life Science Ontologies

“…In this way, query answering turns into logical deduction. From a logic perspective, an interesting new flavour of this application is scale: in addition to the already large Snomed CT, the logical theory now also comprises a potentially huge amount of medical data (as ground facts), and new questions arise due to the special use of deduction in this application [23,17].…”