Implementation of a Decision Support System for Interpretation of Laboratory Tests for Patients

The paper presents the results of the development and implementation of an expert system that automatically generates doctors' letters based on the results of laboratory tests. Medical knowledge is expressed using a first order predictate logic based language. The system was implemented and evaluated in the Helix laboratory service.

Networking Hospital ePrescribing: A Systemic View of Digitalization of Medicines' Use in England

Medicine management is at the core of hospital care and digitalization of prescribing and administration of medicines is often the focus of attention of health IT programs. This may be conveyed to the public in terms of the elimination of paper-based drug charts and increased readability of doctors' prescriptions. Based on analysis of documents about hospital medicines supply and use (including systems' implementation) in the UK, in this conceptual paper electronic prescribing and administration are repositioned as only one aspect of an important wider transformation in medicine management in hospital settings, involving, for example, procurement, dispensing, auditing, waste management, research and safety vigilance. Approaching digitalization from a systemic perspective has the potential to uncover the wider implications of this transformation for patients, the organization and the wider health care system.

Harmonising ICNP and SNOMED CT: A Model for Effective Collaboration

The purpose of this panel was to demonstrate an approach to collaborative working within nursing and health informatics. The panel took as an example an initiative to harmonise between two large-scale terminologies, namely the International Classification for Nursing Practice (ICNP) and SNOMED Clinical Terms (SNOMED CT). A number of practical topics were framed within a context of collaboration, including semi-automated and manual approaches to mapping, consensus working, clinical validation, formal concept modelling, etc. Those attending the panel, nurses and informatics professional alike, came away with an increased understanding of a range of approaches to collaborative working within nursing and health informatics.

An Ensemble Approach for Record Matching in Data Linkage

OBJECTIVES

To develop and test an optimal ensemble configuration of two complementary probabilistic data matching techniques namely Fellegi-Sunter (FS) and Jaro-Wrinkler (JW) with the goal of improving record matching accuracy.

METHODS

Experiments and comparative analyses were carried out to compare matching performance amongst the ensemble configurations combining FS and JW against the two techniques independently.

RESULTS

Our results show that an improvement can be achieved when FS technique is applied to the remaining unsure and unmatched records after the JW technique has been applied.

DISCUSSION

Whilst all data matching techniques rely on the quality of a diverse set of demographic data, FS technique focuses on the aggregating matching accuracy from a number of useful variables and JW looks closer into matching the data content (spelling in this case) of each field. Hence, these two techniques are shown to be complementary. In addition, the sequence of applying these two techniques is critical.

CONCLUSION

We have demonstrated a useful ensemble approach that has potential to improve data matching accuracy, particularly when the number of demographic variables is limited. This ensemble technique is particularly useful when there are multiple acceptable spellings in the fields, such as names and addresses.

The MOSART database: linking the SART CORS clinical database to the population-based Massachusetts PELL reproductive public health data system

Although Assisted Reproductive Technology (ART) births make up 1.6 % of births in the US, the impact of ART on subsequent infant and maternal health is not well understood. Clinical ART treatment records linked to population data would be a powerful tool to study long term outcomes among those treated or not by ART. This paper describes the development of a database intended to accomplish this task. We constructed the Massachusetts Outcomes Study of Assisted Reproductive Technology (MOSART) database by linking the Society of Assisted Reproductive Technologies Clinical Outcomes Reporting System (SART CORS) and the Massachusetts (MA) Pregnancy to Early Life Longitudinal (PELL) data systems for children born to MA resident women at MA hospitals between July 2004 and December 2008. PELL data representing 282,971 individual women and their 334,152 deliveries and 342,035 total births were linked with 48,578 cycles of ART treatment in SART CORS delivered to MA residents or women receiving treatment in MA clinics, representing 18,439 eligible women of whom 9,326 had 10,138 deliveries in this time period. A deterministic five phase linkage algorithm methodology was employed. Linkage results, accuracy, and concordance analyses were examined. We linked 9,092 (89.7 %) SART CORS outcome records to PELL delivery records overall, including 95.0 % among known MA residents treated in MA clinics; 70.8 % with full exact matches. There were minimal differences between matched and unmatched delivery records, except for unknown residency and out-of-state ART site. There was very low concordance of reported use of ART treatment between SART CORS and PELL (birth certificate) data. A total of 3.4 % of MA children (11,729) were identified from ART assisted pregnancies (6,556 singletons; 5,173 multiples). The MOSART linked database provides a strong basis for further longitudinal ART outcomes studies and supports the continued development of potentially powerful linked clinical-public health databases.

Indirect Comparisons and Network Meta-Analyses

BACKGROUND

Systematic reviews provide a structured summary of the results of trials that have been carried out on any particular subject. If the data from multiple trials are sufficiently homogenous, a meta-analysis can be performed to calculate pooled effect estimates. Traditional meta-analysis involves groups of trials that compare the same two interventions directly (head to head). Lately, however, indirect comparisons and network metaanalyses have become increasingly common.

METHODS

Various methods of indirect comparison and network meta-analysis are presented and discussed on the basis of a selective review of the literature. The main assumptions and requirements of these methods are described, and a checklist is provided as an aid to the evaluation of published indirect comparisons and network meta-analyses.

RESULTS

When no head-to-head trials of two interventions are available, indirect comparisons and network metaanalyses enable the estimation of effects as well as the simultaneous analysis of networks involving more than two interventions. Network meta-analyses and indirect comparisons can only be useful if the trial or patient characteristics are similar and the observed effects are sufficiently homogeneous. Moreover, there should be no major discrepancy between the direct and indirect evidence. If trials are available that compare each of two treatments against a third one, but not against each other, then the third intervention can be used as a common comparator to enable a comparison of the other two.

CONCLUSION

Indirect comparisons and network metaanalyses are an important further development of traditional meta-analysis. Clear and detailed documentation is needed so that findings obtained by these new methods can be reliably judged.

An Associative Memory Model for Integration of Fragmented Research Data and Identification of Treatment Correlations in Breast Cancer Care

A major challenge in advancing scientific discoveries using data-driven clinical research is the fragmentation of relevant data among multiple information systems. This fragmentation requires significant data-engineering work before correlations can be found among data attributes in multiple systems. In this paper, we focus on integrating information on breast cancer care, and present a novel computational approach to identify correlations between administered drugs captured in an electronic medical records and biological factors obtained from a tumor registry through rapid data aggregation and analysis. We use an associative memory (AM) model to encode all existing associations among the data attributes from both systems in a high-dimensional vector space. The AM model stores highly associated data items in neighboring memory locations to enable efficient querying operations. The results of applying AM to a set of integrated data on tumor markers and drug administrations discovered anomalies between clinical recommendations and derived associations.

LORD: a phenotype-genotype semantically integrated biomedical data tool to support rare disease diagnosis coding in health information systems

Characterizing a rare disease diagnosis for a given patient is often made through expert's networks. It is a complex task that could evolve over time depending on the natural history of the disease and the evolution of the scientific knowledge. Most rare diseases have genetic causes and recent improvements of sequencing techniques contribute to the discovery of many new diseases every year. Diagnosis coding in the rare disease field requires data from multiple knowledge bases to be aggregated in order to offer the clinician a global information space from possible diagnosis to clinical signs (phenotypes) and known genetic mutations (genotype). Nowadays, the major barrier to the coding activity is the lack of consolidation of such information scattered in different thesaurus such as Orphanet, OMIM or HPO. The Linking Open data for Rare Diseases (LORD) web portal we developed stands as the first attempt to fill this gap by offering an integrated view of 8,400 rare diseases linked to more than 14,500 signs and 3,270 genes. The application provides a browsing feature to navigate through the relationships between diseases, signs and genes, and some Application Programming Interfaces to help its integration in health information systems in routine.

Linking 2006 Census and hospital data in Canada

BACKGROUND

Record linkage is commonly used in health research to fill data gaps. This study summarizes the linkage of the 2006 Census of Population (excluding Quebec) to hospital data from the Discharge Abstract Database (DAD).

DATA AND METHODS

Hierarchical deterministic exact matching was employed to link 2006 Census and DAD (2006/2007, 2007/2008 and 2008/2009) data, based on linkage keys derived from three variables common to both files-date of birth, postal code and sex. The full census file (short-form; 23.4 million) was used for record linkage; the 20% file (long-form; 4.65 million) representing the study cohort was used for validation. Linked files were compared across jurisdictions, years and other selected covariates in terms of eligibility for linkage, keys linked, and linkage and coverage rates.

RESULTS

Overall, 80% of linkage keys identified in the DAD were linked to the 2006 Census. The percentage of long-form census respondents linked to at least one hospital record ranged between 5% and 8% across jurisdictions; linkage rates were higher among known high users of hospital services: older age groups, lower-income individuals, and Aboriginal people. In general, the linked census file represents the majority of hospital events that occurred during the study period. Coverage rates (weighted/unweighted) varied by geography and age group, with lower weighted rates for the territories and some younger age groups.

INTERPRETATION

With hierarchical deterministic exact matching, census data can be linked to multiple years of DAD data. Incorporation of updated postal codes from tax files reduced linkage rate attrition over time. Lower coverage rates for the territories and younger age groups suggest that these populations may be underrepresented in the linked files.

Design and implementation of a privacy preserving electronic health record linkage tool in Chicago

OBJECTIVE

To design and implement a tool that creates a secure, privacy preserving linkage of electronic health record (EHR) data across multiple sites in a large metropolitan area in the United States (Chicago, IL), for use in clinical research.

METHODS

The authors developed and distributed a software application that performs standardized data cleaning, preprocessing, and hashing of patient identifiers to remove all protected health information. The application creates seeded hash code combinations of patient identifiers using a Health Insurance Portability and Accountability Act compliant SHA-512 algorithm that minimizes re-identification risk. The authors subsequently linked individual records using a central honest broker with an algorithm that assigns weights to hash combinations in order to generate high specificity matches.

RESULTS

The software application successfully linked and de-duplicated 7 million records across 6 institutions, resulting in a cohort of 5 million unique records. Using a manually reconciled set of 11 292 patients as a gold standard, the software achieved a sensitivity of 96% and a specificity of 100%, with a majority of the missed matches accounted for by patients with both a missing social security number and last name change. Using 3 disease examples, it is demonstrated that the software can reduce duplication of patient records across sites by as much as 28%.

CONCLUSIONS

Software that standardizes the assignment of a unique seeded hash identifier merged through an agreed upon third-party honest broker can enable large-scale secure linkage of EHR data for epidemiologic and public health research. The software algorithm can improve future epidemiologic research by providing more comprehensive data given that patients may make use of multiple healthcare systems.

Accuracy and completeness of patient pathways--the benefits of national data linkage in Australia

BACKGROUND

The technical challenges associated with national data linkage, and the extent of cross-border population movements, are explored as part of a pioneering research project. The project involved linking state-based hospital admission records and death registrations across Australia for a national study of hospital related deaths.

METHODS

The project linked over 44 million morbidity and mortality records from four Australian states between 1st July 1999 and 31st December 2009 using probabilistic methods. The accuracy of the linkage was measured through a comparison with jurisdictional keys sourced from individual states. The extent of cross-border population movement between these states was also assessed.

RESULTS

Data matching identified almost twelve million individuals across the four Australian states. The percentage of individuals from one state with records found in another ranged from 3-5%. Using jurisdictional keys to measure linkage quality, results indicate a high matching efficiency (F measure 97 to 99%), with linkage processing taking only a matter of days.

CONCLUSIONS

The results demonstrate the feasibility and accuracy of undertaking cross jurisdictional linkage for national research. The benefits are substantial, particularly in relation to capturing the full complement of records in patient pathways as a result of cross-border population movements. The project identified a sizeable 'mobile' population with hospital records in more than one state. Research studies that focus on a single jurisdiction will under-enumerate the extent of hospital usage by individuals in the population. It is important that researchers understand and are aware of the impact of this missing hospital activity on their studies. The project highlights the need for an efficient and accurate data linkage system to support national research across Australia.

Testing of Electronic Healthcare Record images and reports viewer

Electronic Health Record (EHR) is a distributed system that results from the cooperation of several heterogeneous and autonomous subsystems. It improves health care by enabling access to prior diagnostic information to assist in health decisions. We focus on the image and imaging report visualization component that needs to interoperate with several other systems to enable healthcare professionals visualize a patient's imaging record. We propose and describe an environment that has been built and used to facilitate the development of the viewer component. This environment has also been used to test and verify the interoperability of the viewer component with other EHR components in accordance with the Integrating the Healthcare Enterprise (IHE) technical framework. It has also been used to demonstrate functionalities, to educate end users, and to train maintenance and test engineers. Moreover, it has been used for acceptance testing as part of an EHR deployment project. We also discuss the challenges we faced in constructing the testing data and describe the software developed to automatically populate the test environment with valid data.

Benefits of an automatic patient dose registry system for interventional radiology and cardiology at five hospitals of the Madrid area

The purpose of this article is to present the results of connecting the interventional radiology and cardiology laboratories of five university hospitals to a unique server using an automatic patient dose registry system (Dose On Line for Interventional Radiology, DOLIR) developed in-house, and to evaluate its feasibility more than a year after its introduction. The system receives and stores demographic and dosimetric parameters included in the MPPS DICOM objects sent by the modalities to a database. A web service provides a graphical interface to analyse the information received. During 2013, the system processed 10 788 procedures (6874 cardiac, 2906 vascular and 1008 neuro interventional). The percentages of patients requiring clinical follow-up due to potential tissue reactions before and after the use of DOLIR are presented. The system allowed users to verify in real-time, if diagnostic (or interventional) reference levels are fulfilled.

Toward a complete dataset of drug-drug interaction information from publicly available sources

Although potential drug-drug interactions (PDDIs) are a significant source of preventable drug-related harm, there is currently no single complete source of PDDI information. In the current study, all publically available sources of PDDI information that could be identified using a comprehensive and broad search were combined into a single dataset. The combined dataset merged fourteen different sources including 5 clinically-oriented information sources, 4 Natural Language Processing (NLP) Corpora, and 5 Bioinformatics/Pharmacovigilance information sources. As a comprehensive PDDI source, the merged dataset might benefit the pharmacovigilance text mining community by making it possible to compare the representativeness of NLP corpora for PDDI text extraction tasks, and specifying elements that can be useful for future PDDI extraction purposes. An analysis of the overlap between and across the data sources showed that there was little overlap. Even comprehensive PDDI lists such as DrugBank, KEGG, and the NDF-RT had less than 50% overlap with each other. Moreover, all of the comprehensive lists had incomplete coverage of two data sources that focus on PDDIs of interest in most clinical settings. Based on this information, we think that systems that provide access to the comprehensive lists, such as APIs into RxNorm, should be careful to inform users that the lists may be incomplete with respect to PDDIs that drug experts suggest clinicians be aware of. In spite of the low degree of overlap, several dozen cases were identified where PDDI information provided in drug product labeling might be augmented by the merged dataset. Moreover, the combined dataset was also shown to improve the performance of an existing PDDI NLP pipeline and a recently published PDDI pharmacovigilance protocol. Future work will focus on improvement of the methods for mapping between PDDI information sources, identifying methods to improve the use of the merged dataset in PDDI NLP algorithms, integrating high-quality PDDI information from the merged dataset into Wikidata, and making the combined dataset accessible as Semantic Web Linked Data.

Using personal health insurance numbers to link the Canadian Cancer Registry and the Discharge Abstract Database

BACKGROUND

Linking cancer registry and administrative data can reveal health care use patterns among cancer patients. The Canadian Cancer Registry (CCR) contains personal health insurance numbers (HINs) that facilitate linkage to hospitalization information in the Discharge Abstract Database (DAD).

DATA AND METHODS

Valid HINs, captured in the CCR or obtained through probabilistic linkages to provincial health insurance registries, were used to deterministically link prostate, female breast, colorectal and lung cancers diagnosed from 2005 through 2008 with the DAD for fiscal years 2004/2005 to 2010/2011.

RESULTS

At least 98% of tumours diagnosed from 2005 through 2008 had valid HINs in the CCR or obtained through probabilistic linkages. For provinces submitting day surgeries to the DAD, linkage rates to at least one DAD record were higher for female breast (95.6% to 98.1%), colorectal (96.9% to 98.7%) and lung cancers (92.8% to 96.3%) than for prostate cancers (77.2% to 91.6%). Among linked records, agreement was high for sex (99% or more) and complete date of birth (97% or more); the likelihood of a consistent diagnosis in the CCR and on at least one linked DAD record was higher for female breast (86.8% to 97.2%), colorectal (94.6% to 97.7%) and lung cancers (90.3% to 95.5%) than for prostate cancers (77.4% to 87.8%).

INTERPRETATION

Deterministically linking the CCR and DAD using personal HINs is a feasible and valid approach to obtaining hospitalization information about cancer patients.

Quantification of NSW Ambulance Record Linkages with Multiple External Datasets

This study has two aims: 1) to describe linkage rates between ambulance data and external datasets for "episodes of care" and "patient only" linkages in New South Wales (NSW), Australia; and 2) to detect and report any systematic issues with linkage that relate to patients, and operational or clinical variables that may introduce bias in subsequent studies if not adequately addressed. During 2010-11, the Centre for Health Record Linkage (CHeReL) in NSW, linked the records for patients attended by NSW Ambulance paramedics for the period July 2006 to June 2009, with four external datasets: Emergency Department Data Collection; Admitted Patient Data Collection; NSW Registry of Births, Deaths and Marriages death registration data; and the Australian Bureau of Statistics mortality data. This study reports linkage rates in terms of those "expected" to link and those who were "not expected" to link with external databases within 24 hours of paramedic attendance. Following thorough data preparation processes, 2,041,728 NSW Ambulance care episodes for 1,116,509 patients fulfilled the inclusion criteria. The overall episode-specific hospital linkage rate was 97.2%. Where a patient was not transported to hospital following paramedic care, 8.6% of these episodes resulted in an emergency department attendance within 24 hours. For all care episodes, 5.2% linked to a death record at some time within the 3-year period, with 2.4% of all death episodes occurring within 7 days of a paramedic encounter. For NSW Ambulance episodes of care that were expected to link to an external dataset but did not, nonlinkage to hospital admission records tended to decrease with age. For all other variables, issues relating to rates of linkage and nonlinkage were more indiscriminate. This quantification of the limitations of this large linked dataset will underpin the interpretation and results of ensuing studies that will inform future clinical and operational policies and practices at NSW Ambulance.

DyKOSMap: A framework for mapping adaptation between biomedical knowledge organization systems

BACKGROUND

Knowledge Organization Systems (KOS) and their associated mappings play a central role in several decision support systems. However, by virtue of knowledge evolution, KOS entities are modified over time, impacting mappings and potentially turning them invalid. This requires semi-automatic methods to maintain such semantic correspondences up-to-date at KOS evolution time.

METHODS

We define a complete and original framework based on formal heuristics that drives the adaptation of KOS mappings. Our approach takes into account the definition of established mappings, the evolution of KOS and the possible changes that can be applied to mappings. This study experimentally evaluates the proposed heuristics and the entire framework on realistic case studies borrowed from the biomedical domain, using official mappings between several biomedical KOSs.

RESULTS

We demonstrate the overall performance of the approach over biomedical datasets of different characteristics and sizes. Our findings reveal the effectiveness in terms of precision, recall and F-measure of the suggested heuristics and methods defining the framework to adapt mappings affected by KOS evolution. The obtained results contribute and improve the quality of mappings over time.

CONCLUSIONS

The proposed framework can adapt mappings largely automatically, facilitating thus the maintenance task. The implemented algorithms and tools support and minimize the work of users in charge of KOS mapping maintenance.

Reuse of EHRs to Support Clinical Research in a Hospital of Reference

Most hospitals have already implemented information systems and Electronic Health Records (EHRs), but the reuse of such data for research is still infrequent. We present a pilot project on the exploitation of clinical information from a Spanish hospital database in the context of the European Medical Information Framework project (EMIF). Specific use cases such as patients with diabetes mellitus type 2, obesity and dementia were assessed, by exploiting EHR data integrated from several separated clinical databases. The possibility to analyse the features of specific groups of patients based on their diagnosis codes can provide new data about relationships between different conditions that can contribute for decision-making, healthcare and research.

Process assessment by automated computation of healthcare quality indicators in hospital electronic health records: a systematic review of indicators

The objective of the work is to extract healthcare process quality indicators from the literature, and to evaluate which of them could be automatically computed using routinely collected data from electronic health records (EHRs). A minimal set of data commonly available in EHRs is first defined. The initial bibliographic query enables to identify 8,744 papers, among which 126 papers describe 440 process indicators. 22.3% of indicators can be automatically computed. The computation of the indicators mostly require diagnoses (99%), drug prescriptions (59%), medical procedures (48%), administrative data (30%), laboratory results (20%), free-text reports with basic keyword research (19%), linkage with the patient's previous stays (11%) and dependence assessment (3%). 77.7% of indicators cannot be automatically computed, mostly because they require a linkage with outpatient data (61%), structured data that are usually not available (43%), unstructured data (26%) or the trace of an information that was given to the patient (8%).

A "pivot" Model to set up Large Scale Rare Diseases Information Systems: Application to the Fibromuscular Dysplasia Registry

The SIR-FMD project is a partnership between the Department of Genetics and Reference Centre for Rare Vascular Diseases at the Georges Pompidou European Hospital in Paris and the Medical Informatics and Knowledge Engineering Laboratory of Inserm. Its aim is to use an ontological approach to implement an information system for the French Fibromuscular Dysplasia Registry. The existing data was dispersed in numerous databases, which had been created independently. These databases have different structures and contain data of diverse quality. The project aims to provide generic solutions for the management of the communication of medical data. The secondary objective is to demonstrate the applicability of these generic solutions in the field of rare diseases (RD) in an operational context. The construction of the French FMD registry was a multistep process. A secure platform has been available since the beginning of November 2013. The medical records of 471 patients from the initial dataset provided by the HEGP-Paris, France have been included, and are accessible from a secure user account. Users are organized into a collaborative group, and can access patient groups. Each electronic patient record contains more than 2,200 items. The problem of semantic interoperability has become one of the major challenges for the development of applications requiring the sharing and reuse of data. The information system component of the SIR-FMD project has a direct impact on the standardisation of coding of rare diseases and thereby contributes to the development of e-Health.

Developing an Electronic Medical Record for Interlinked Care Services in Haiti

A large clinical care and research organization in Haiti required an electronic medical record system (EMR) to serve the needs of its 30 interlinked clinical programs. After assessing available open source software, the local team designed and implemented a modular proprietary EMR that is improving data quality and patient care. Despite the many benefits of existing open source medical record systems, clinical centers with complex workflow patterns--even those in resource-limited settings--should consider developing sustainable, local systems that fit their care model.

Oncotherapy: A System for Requesting Chemotherapy Protocols

A clinical decision support system is able to provide oncologists with suitable treatment options at the moment of decision making regarding which chemotherapy protocol is the best to apply to a particular oncological case. The National Cancer Institute has created a Guidelines Committee that establishes therapeutical options for each clinical case. The Health Informatics Department has developed Oncotherapy, a knowledge database that incorporates information provided by the Guidelines Committee. Oncotherapy includes a tailored information repository to provide oncologists in the public health system with the chemotherapy protocols available given three types of data: clinical diagnosis, clinical stage and therapy criteria. The protocol selected by the treating oncologist is sent back to Oncotherapy, which may create new knowledge that can be incorporated into the knowledge database. In this way, the system supports making the best decision according to the chemotherapy protocol options available. Furthermore, it can warn of errors that could result from mistakenly chosen therapies.

A Platform to Collect Structured Data from Multiple EMRs

Adoption and use of Electronic Medical Records (EMRs) is continuing to rise across Canada, leading to more data being generated. These data, however, are not being captured in a standardized manner, they are not available for research, surveillance or health system management, and they are not having a real-time impact on healthcare providers at the point of care. Multiple stakeholders, including researchers and system evaluators, require easy access to high quality, structured data. As current EMRs are not able to effectively meet their needs, we engaged multiple stakeholders to assist in designing a solution. A total of 90 stakeholders from various backgrounds participated in an iterative joint design process. After incorporating the feedback of all stakeholders, we developed the design for a scalable platform for capturing structured, evidence-based data from all EMRs in Canada for research, health system management, clinical decision support and other purposes. We discuss the design specification for our proposed solution and explain how, using clinical forms, we can not only capture structured, high quality data from multiple EMRs, but also provide real-time guideline advice to providers at the point of care. The scalability of this proposed solution across multiple diseases and multiple EMRs is also explained. We further discuss the benefits and limitations of this proposed solution to several key stakeholder groups and address issues of privacy and security.