CogStack - experiences of deploying integrated information retrieval and extraction services in a large National Health Service Foundation Trust hospital

Richard Jackson,Damian Lewsley,Doug Northwood,Robert Stewart,Clive Stringer,Genevieve Gorrell,Tudor Groza,Ismail Kartoglu,Asha Agrawal,Amos Folarin,Angus Roberts,Honghan Wu,Xingyi Song,Kenneth Lui,Richard Dobson

doi:10.1186/s12911-018-0623-9

Abstract

BackgroundTraditional health information systems are generally devised to support clinical data collection at the point of care. However, as the significance of the modern information economy expands in scope and permeates the healthcare domain, there is an increasing urgency for healthcare organisations to offer information systems that address the expectations of clinicians, researchers and the business intelligence community alike. Amongst other emergent requirements, the principal unmet need might be defined as the 3R principle (right data, right place, right time) to address deficiencies in organisational data flow while retaining the strict information governance policies that apply within the UK National Health Service (NHS). Here, we describe our work on creating and deploying a low cost structured and unstructured information retrieval and extraction architecture within King’s College Hospital, the management of governance concerns and the associated use cases and cost saving opportunities that such components present.ResultsTo date, our CogStack architecture has processed over 300 million lines of clinical data, making it available for internal service improvement projects at King’s College London. On generated data designed to simulate real world clinical text, our de-identification algorithm achieved up to 94% precision and up to 96% recall.ConclusionWe describe a toolkit which we feel is of huge value to the UK (and beyond) healthcare community. It is the only open source, easily deployable solution designed for the UK healthcare environment, in a landscape populated by expensive proprietary systems. Solutions such as these provide a crucial foundation for the genomic revolution in medicine.

Highlights

Traditional health information systems are generally devised to support clinical data collection at the point of care
While there have been many attempts to standardise intra-system communication with the use of controlled languages and data schemas, such as Health level 7 (HL7) [1], the myriad of vendors, differential versioning of the standards and the ambiguity in the interpretation of the standards has caused such efforts to be only partially successful in practice[2,3,4]. This has lead to a high degree of heterogeneity in how information is managed within and between different National Health Service (NHS) Trusts, which in turn has inflated the costs of creating suitable data management and analytics solutions, due to the investment required for successful implementation
Implementation Here, we describe our work on the CogStack architecture, an open source information retrieval and extraction architecture to provide an alternative to the UK healthcare community in a space traditionally occupied by commercial vendors

Summary

Introduction

Traditional health information systems are generally devised to support clinical data collection at the point of care. Large healthcare organisations are often responsible for provisioning care in a wide range of medical specialties It is not uncommon for a given speciality to make use of bespoke IT systems to support the specific requirements of clinicians at the point of care, such as imaging technologies, electronic prescribing and intensive care monitoring. While there have been many attempts to standardise intra-system communication with the use of controlled languages and data schemas, such as HL7 [1], the myriad of vendors, differential versioning of the standards and the ambiguity in the interpretation of the standards has caused such efforts to be only partially successful in practice[2,3,4] This has lead to a high degree of heterogeneity in how information is managed within and between different NHS Trusts, which in turn has inflated the costs of creating suitable data management and analytics solutions, due to the investment required for successful implementation. Without significant guidance from central hospital IT departments, many lay users of health information systems may not be aware of the logic of how data flows between them, and opportunities to use the organisation’s data to drive efficiency improvements are undermined

Objectives

Results

Discussion

Conclusion