A systematic review of the clinical application of data-driven population segmentation analysis.

BACKGROUND: Data-driven population segmentation analysis utilizes data analytics to divide a heterogeneous population into parsimonious and relatively homogenous groups with similar healthcare characteristics. It is a promising patient-centric analysis that enables effective integrated healthcare interventions specific for each segment. Although widely applied, there is no systematic review on the clinical application of data-driven population segmentation analysis. METHODS: We carried out a systematic literature search using PubMed, Embase and Web of Science following PRISMA criteria. We included English peer-reviewed articles that applied data-driven population segmentation analysis on empirical health data. We summarized the clinical settings in which segmentation analysis was applied, compared and contrasted strengths, limitations, and practical considerations of different segmentation methods, and assessed the segmentation outcome of all included studies. The studies were assessed by two independent reviewers. RESULTS: We retrieved 14,514 articles and included 216 articles. Data-driven population segmentation analysis was widely used in different clinical contexts. 163 studies examined the general population while 53 focused on specific population with certain diseases or conditions, including psychological, oncological, respiratory, cardiovascular, and gastrointestinal conditions. Variables used for segmentation in the studies are heterogeneous. Most studies (n = 170) utilized secondary data in community settings (n = 185). The most common segmentation method was latent class/profile/transition/growth analysis (n = 96) followed by K-means cluster analysis (n = 60) and hierarchical analysis (n = 50), each having its advantages, disadvantages, and practical considerations. We also identified key criteria to evaluate a segmentation framework: internal validity, external validity, identifiability/interpretability, substantiality, stability, actionability/accessibility, and parsimony. CONCLUSIONS: Data-driven population segmentation has been widely applied and holds great potential in managing population health. The evaluations of segmentation outcome require the interplay of data analytics and subject matter expertise. The optimal framework for segmentation requires further research.

Probabilistic linkage to enhance deterministic algorithms and reduce data linkage errors in hospital administrative data.

 BACKGROUND: The pseudonymisation algorithm used to link together episodes of care belonging to the same patients in England (HESID) has never undergone any formal evaluation, to determine the extent of data linkage error. OBJECTIVE: To quantify improvements in linkage accuracy from adding probabilistic linkage to existing deterministic HESID algorithms. METHODS: Inpatient admissions to NHS hospitals in England (Hospital Episode Statistics, HES) over 17 years (1998 to 2015) for a sample of patients (born 13/28th of months in 1992/1998/2005/2012). We compared the existing deterministic algorithm with one that included an additional probabilistic step, in relation to a reference standard created using enhanced probabilistic matching with additional clinical and demographic information. Missed and false matches were quantified and the impact on estimates of hospital readmission within one year were determined. RESULTS: HESID produced a high missed match rate, improving over time (8.6% in 1998 to 0.4% in 2015). Missed matches were more common for ethnic minorities, those living in areas of high socio-economic deprivation, foreign patients and those with 'no fixed abode'. Estimates of the readmission rate were biased for several patient groups owing to missed matches, which was reduced for nearly all groups. CONCLUSION: Probabilistic linkage of HES reduced missed matches and bias in estimated readmission rates, with clear implications for commissioning, service evaluation and performance monitoring of hospitals. The existing algorithm should be modified to address data linkage error, and a retrospective update of the existing data would address existing linkage errors and their implications.

Utilising identifier error variation in linkage of large administrative data sources.

BACKGROUND: Linkage of administrative data sources often relies on probabilistic methods using a set of common identifiers (e.g. sex, date of birth, postcode). Variation in data quality on an individual or organisational level (e.g. by hospital) can result in clustering of identifier errors, violating the assumption of independence between identifiers required for traditional probabilistic match weight estimation. This potentially introduces selection bias to the resulting linked dataset. We aimed to measure variation in identifier error rates in a large English administrative data source (Hospital Episode Statistics; HES) and to incorporate this information into match weight calculation. METHODS: We used 30,000 randomly selected HES hospital admissions records of patients aged 0-1, 5-6 and 18-19 years, for 2011/2012, linked via NHS number with data from the Personal Demographic Service (PDS; our gold-standard). We calculated identifier error rates for sex, date of birth and postcode and used multi-level logistic regression to investigate associations with individual-level attributes (age, ethnicity, and gender) and organisational variation. We then derived: i) weights incorporating dependence between identifiers; ii) attribute-specific weights (varying by age, ethnicity and gender); and iii) organisation-specific weights (by hospital). Results were compared with traditional match weights using a simulation study. RESULTS: Identifier errors (where values disagreed in linked HES-PDS records) or missing values were found in 0.11% of records for sex and date of birth and in 53% of records for postcode. Identifier error rates differed significantly by age, ethnicity and sex (p < 0.0005). Errors were less frequent in males, in 5-6 year olds and 18-19 year olds compared with infants, and were lowest for the Asian ethic group. A simulation study demonstrated that substantial bias was introduced into estimated readmission rates in the presence of identifier errors. Attribute- and organisational-specific weights reduced this bias compared with weights estimated using traditional probabilistic matching algorithms. CONCLUSIONS: We provide empirical evidence on variation in rates of identifier error in a widely-used administrative data source and propose a new method for deriving match weights that incorporates additional data attributes. Our results demonstrate that incorporating information on variation by individual-level characteristics can help to reduce bias due to linkage error.

Integrating third-party telehealth records with the general practice electronic medical record system: a solution.

BACKGROUND: The implementation of telemonitoring at scale has been less successful than anticipated, often hindered by clinicians' perceived increase in workload. One important factor has been the lack of integration of patient generated data (PGD) with the electronic medical record (EMR). Clinicians have had problems accessing PGD on telehealth systems especially in patient consultations in primary care. OBJECTIVE: To design a method to produce a report of PGD that is available to clinicians through their routine EMR system. METHOD: We modelled a system with a use case approach using Unified Modelling Language to enable us to design a method of producing the required report. Anonymised PGD are downloaded from a third-party telehealth system to National Health Service (NHS) systems and linked to the patient record available in the hospital recording system using the patient NHS ID through an interface accessed by healthcare professionals. The telehealth data are then processed into a report using the patient record. This report summarises the readings in graphical and tabular form with an average calculated and with a recommended follow-up suggested if required. The report is then disseminated to general practitioner practices through routine document distribution pathways. RESULTS: This addition to the telehealth system is viewed positively by clinicians. It has helped to greatly increase the number of general practices using telemonitoring to manage blood pressure in NHS Lothian.

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.

Development and practice of ISMS at a Radiotherapy Hospital by using IHE Integration profiles.

Our hospital is specialized for radiation therapy and has many information devices. Various job categories are working. When we implemented an EMR, we aimed to enforce ISMS by using IHE profiles. To solve the already existed system-related problems, we selected and use some profiles (EUA, PSA, ATNA and PAM). After implementation, we audited and then some findings were pointed out. These findings are being settled by the PDCA cycle. We also found that appropriate IHE profiles were effective in the building of ISMS.

Le Bon Samaritain: A Community-Based Care Model Supported by Technology.

BACKGROUND: The effective care and well-being of a community is a challenging task especially in an emergency situation. Traditional technology-based silos between health and emergency services are challenged by the changing needs of the community that could benefit from integrated health and safety services. Low-cost smart-home automation solutions, wearable devices and Cloud technology make it feasible for communities to interact with each other, and with health and emergency services in a timely manner. OBJECTIVES: This paper proposes a new community-based care model, supported by technology, that aims at reducing healthcare and emergency services costs while allowing community to become resilient in response to health and emergency situations. METHODS: We looked at models of care in different industries and identified the type of technology that can support the suggested new model of care. Two prototypes were developed to validate the adequacy of the technology. RESULTS: The result is a new community-based model of care called 'Le Bon Samaritain'. It relies on a network of people called 'Bons Samaritains' willing to help and deal with the basic care and safety aspects of their community. Their role is to make sure that people in their community receive and understand the messages from emergency and health services. The new care model is integrated with existing emergency warning, community and health services. CONCLUSION: Le Bon Samaritain model is scalable, community-based and can help people feel safer, less isolated and more integrated in their community. It could be the key to reduce healthcare cost, increase resilience and drive the change for a more integrated emergency and care system.

Towards lifetime electronic health record implementation.

Integrated care concepts can help to diminish demographic challenges. Hereof, the use of eHealth, esp. overarching electronic health records, is recognized as an efficient approach. The article aims at rigorously defining the concept of lifetime electronic health records (LEHRs) and the identification of core factors that need to be fulfilled in order to implement such. A literature review was conducted. Existing definitions were identified and relevant factors were categorized. The derived assessment categories are demonstrated by a case study on Germany. Seven dimensions to differentiate types of electronic health records were found. The analysis revealed, that culture, regulation, informational self-determination, incentives, compliance, ICT infrastructure and standards are important preconditions to successfully implement LEHRs. The article paves the way for LEHR implementation and therewith for integrated care. Besides the expected benefits of LEHRs, there are a number of ethical, legal and social concerns, which need to be balanced.

Integrated care: an Information Model for Patient Safety and Vigilance Reporting Systems.

Quality management information systems for safety as a whole or for specific vigilances share the same information types but are not interoperable. An international initiative tries to develop an integrated information model for patient safety and vigilance reporting to support a global approach of heath care quality.

A socio-technical analytical framework on the EHR-organizational innovation interplay: Insights from a public hospital in Greece.

The healthcare sector globally is confronted with increasing internal and external pressures that urge for a radical reform of health systems' status quo. The role of technological innovations such as Electronic Health Records (EHR) is recognized as instrumental in this transition process as it is expected to accelerate organizational innovations. This is why the widespread uptake of EHR systems is a top priority in the global healthcare agenda. The successful co-deployment though of EHR systems and organizational innovations within the context of secondary healthcare institutions is a complex and multifaceted issue. Existing research in the field has made little progress thus emphasizing the need for further research contribution that will incorporate a holistic perspective. This paper presents insights about the EHR-organizational innovation interplay from a public hospital in Greece into a socio-technical analytical framework providing a multilevel set of action points for the eHealth roadmap with worldwide relevance.

Role of OpenEHR as an open source solution for the regional modelling of patient data in obstetrics.

This work investigates, whether openEHR with its reference model, archetypes and templates is suitable for the digital representation of demographic as well as clinical data. Moreover, it elaborates openEHR as a tool for modelling Hospital Information Systems on a regional level based on a national logical infrastructure. OpenEHR is a dual model approach developed for the modelling of Hospital Information Systems enabling semantic interoperability. A holistic solution to this represents the use of dual model based Electronic Healthcare Record systems. Modelling data in the field of obstetrics is a challenge, since different regions demand locally specific information for the process of treatment. Smaller health units in developing countries like Brazil or Malaysia, which until recently handled automatable processes like the storage of sensitive patient data in paper form, start organizational reconstruction processes. This archetype proof-of-concept investigation has tried out some elements of the openEHR methodology in cooperation with a health unit in Colombo, Brazil. Two legal forms provided by the Brazilian Ministry of Health have been analyzed and classified into demographic and clinical data. LinkEHR-Ed editor was used to read, edit and create archetypes. Results show that 33 clinical and demographic concepts, which are necessary to cover data demanded by the Unified National Health System, were identified. Out of the concepts 61% were reused and 39% modified to cover domain requirements. The detailed process of reuse, modification and creation of archetypes is shown. We conclude that, although a major part of demographic and clinical patient data were already represented by existing archetypes, a significant part required major modifications. In this study openEHR proved to be a highly suitable tool in the modelling of complex health data. In combination with LinkEHR-Ed software it offers user-friendly and highly applicable tools, although the complexity built by the vast specifications requires expert networks to define generally excepted clinical models. Finally, this project has pointed out main benefits enclosing high coverage of obstetrics data on the Clinical Knowledge Manager, simple modelling, and wide network and support using openEHR. Moreover, barriers described are enclosing the allocation of clinical content to respective archetypes, as well as stagnant adaption of changes on the Clinical Knowledge Manager leading to redundant efforts in data contribution that need to be addressed in future works.

An adaptive case management system to support integrated care services: Lessons learned from the NEXES project.

BACKGROUND: Extensive deployment and sustainability of integrated care services (ICS) constitute an unmet need to reduce the burden of chronic conditions. The European Union project NEXES (2008-2013) assessed the deployment of four ICS encompassing the spectrum of severity of chronic patients. OBJECTIVE: The current study aims to (i) describe the open source Adaptive Case Management (ACM) system (Linkcare®) developed to support the deployment of ICS at the level of healthcare district; (ii) to evaluate its performance; and, (iii) to identify key challenges for regional deployment of ICS. METHODS: We first defined a conceptual model for ICS management and execution composed of five main stages. We then specified an associated logical model considering the dynamic runtime of ACM. Finally, we implemented the four ICS as a physical model with an ICS editor to allow professionals (case managers) to play active roles in adapting the system to their needs. Instances of ICS were then run in Linkcare®. Four ICS provided a framework for evaluating the system: Wellness and Rehabilitation (W&R) (number of patients enrolled in the study (n)=173); Enhanced Care (EC) in frail chronic patients to prevent hospital admissions, (n=848); Home Hospitalization and Early Discharge (HH/ED) (n=2314); and, Support to remote diagnosis (Support) (n=7793). The method for assessment of telemedicine applications (MAST) was used for iterative evaluation. RESULTS: Linkcare® supports ACM with shared-care plans across healthcare tiers and offers integration with provider-specific electronic health records. Linkcare® successfully contributed to the deployment of the four ICS: W&R facilitated long-term sustainability of training effects (p<0.01) and active life style (p<0.03); EC showed significant positive outcomes (p<0.05); HH/ED reduced on average 5 in-hospital days per patient with a 30-d re-admission rate of 10%; and, Support, enhanced community-based quality forced spirometry testing (p<0.01). Key challenges for regional deployment of personalized care were identified. CONCLUSIONS: Linkcare® provided the required functionalities to support integrated care adopting an ACM model, and it showed adaptive potential for its implementation in different health scenarios. The research generated strategies that contributed to face the challenges of the transition toward personalized medicine for chronic patients.

[Integration of primary and secondary data in the Study of Health in Pomerania and description of clinical outcomes using stroke as an example]. / Die Integration von Primär- und Sekundärdaten in der Study of Health in Pomerania und die Beschreibung von klinischen Endpunkten am Beispiel Schlaganfall.

OBJECTIVE: This study describes (i) the procedure of obtaining patients' consent for secondary data usage, (ii) the complexity of integrating data from multiple sources, and (iii) the correspondence among patients' self-reports, physician reports, routine data, hospital discharge diagnosis, and cause-of-death coding regarding stroke. METHODS: Data from the first follow-up (N=3 186) of the population-based Study of Health in Pomerania (SHIP) were used. These data were combined with secondary data from the Greifswald University Hospital, the association of statutory health insurance physicians Mecklenburg-Western Pomerania, physician reports, and death certificates. RESULTS: Consent for using health-related information from all data sources in question was obtained from more than 90% of the SHIP participants. Follow-up data from at least one source were available for 2 747 (86%) participants. For 92 participants information about the occurrence of stroke was found in at least one data source. In 59 cases the event appeared in only one data source, in 24 cases the event was found in 2 sources, and for 9 participants 3 data sources reported on the event. CONCLUSION: Participants of a population-based cohort are highly willing to give consent for using their health-related information from secondary data sources. Yet, data integration is challenging due to considerable differences in data type, structure and coverage.

Antiretroviral Therapy Adherence and Use of an Electronic Shared Medical Record Among People Living with HIV.

Electronic shared medical records (SMR) are emerging healthcare technologies that allow patients to engage in their healthcare by communicating with providers, refilling prescriptions, scheduling appointments, and viewing portions of medical records. We conducted a pre-post cohort study of HIV-positive adults who used and did not use SMR in two integrated healthcare systems. We compared the difference in antiretroviral refill adherence between SMR users and age- and sex-frequency matched non-users from the 12-month period prior to SMR useto the 12-month period starting 6 months after initiation of SMR use. High adherence was maintained among SMR users (change = -0.11 %) but declined among non-users (change = -2.05 %; p = 0.003). Among SMR users, there was a steady improvement in adherence as monthly frequency of SMR use increased (p = 0.009). SMR use, particularly more frequent use, is associated with maintaining high adherence and non-use is associated with declines in adherence over time among patients with access to these online services.

[Linking claims data and beneficiary survey information to report on the quality of health care: potential, pitfalls, and perspectives]. / Routinedaten der gesetzlichen Krankenversicherung und Versichertenbefragungen in der Qualitätsberichterstattung - Potenzial, Probleme und Perspektiven.

Reports on the quality of care aim at health and patient-reported outcomes in routine clinical care. To achieve meaningful information the study designs must be robust against bias through highly selected patient populations or health care providers but also allow for adequate control of confounding. The article describes the potential and pitfalls of administrative claims data and surveys of beneficiaries. The large potential of using both sources is illustrated in the primary inpatient treatment for prostate cancer. However, linking claims data and patient survey data still leaves some problems to be addressed in the final section. Linking claims data and beneficiary survey information on patient reported outcomes overcomes sectoral barriers and allows for an integrated evaluation of pathways of care in the short-, mid- and long-term. It is economical and well suited for a variety, but not all health care problems. Future efforts might be directed towards more collaboration among sickness funds.

Construction of a linked health and social care database resource--lessons on process, content and culture.

BACKGROUND: Combining routinely collected health and social care data on older people is essential to advance both service delivery and research for this client group. Little data is available on how to combine health and social care data; this article provides an overview of a successful data linkage process and discusses potential barriers to executing such projects. METHODS AND RESULTS: We successfully obtained and linked data on older people within Dundee from three sources: Dundee Social Work Department database (30,000 individuals aged 65 years and over), healthcare data held on NHS Tayside patients by the Health Informatics Centre (400,000 individuals), Dundee, and the Dundee of Medicine for the Elderly rehabilitation database (4300 individuals). Data were linked, anonymized and transferred to a Safe Haven environment to ensuring confidentiality and strict access control. Challenges were faced around workflows, culture and documentation. Exploiting the resultant data set raises further challenges centered on database documentation, understanding the way data were collected, dealing with missing data, data validity and collection at different time periods. CONCLUSION: Routinely collected health and social care data sets can be linked, but significant process barriers must be overcome to allow successful linkage and integration of data and its full exploitation.

Risk mitigation of shared electronic records system in campus institutions: medical social work practice in singapore.

In 2013, the Singapore General Hospital (SGH) Campus initiated a shared electronic system where patient records and documentations were standardized and shared across institutions within the Campus. The project was initiated to enhance quality of health care, improve accessibility, and ensure integrated (as opposed to fragmented) care for best outcomes in our patients. In mitigating the risks of ICT, it was found that familiarity with guiding ethical principles, and ensuring adherence to regulatory and technical competencies in medical social work were important. The need to negotiate and maneuver in a large environment within the Campus to ensure proactive integrative process helped.

Enabling Person-Centric Care using linked data technologies.

Patient-Centric Care requires comprehensive visibility into the strengths and vulnerabilities of individuals and populations. The systems involved in Patient-Centric Care are numerous and heterogeneous, span medical, behavioral and social domains and must be coordinated across government and NGO stakeholders in Health Care, Social Care and more. We present a system, based on Linked Data technologies, taking first steps in making this cross-domain information accessible and fit-for-use, using minimal structure and open vocabularies. We evaluate our system through user studies.

eHealth-as-a-Service (eHaaS): a data-driven decision making approach in Australian context.

A commitment in 2010 by the Australian Federal Government to spend $466.7 million dollars on the implementation of personally controlled electronic health records (PCEHR) heralded a shift to a more effective and safer patient centric eHealth system. However, deployment of the PCEHR has met with much criticism, emphasised by poor adoption rates over the first 12 months of operation. An indifferent response by the public and healthcare providers largely sceptical of its utility and safety speaks to the complex sociotechnical drivers and obstacles inherent in the embedding of large (national) scale eHealth projects. With government efforts to inflate consumer and practitioner engagement numbers giving rise to further consumer disillusionment, broader utilitarian opportunities available with the PCEHR are at risk. This paper discusses the implications of establishing the PCEHR as the cornerstone of a holistic eHealth strategy for the aggregation of longitudinal patient information. A viewpoint is offered that the real value in patient data lies not just in the collection of data but in the integration of this information into clinical processes within the framework of a commoditised data-driven approach. Consideration is given to the eHealth-as-a-Service (eHaaS) construct as a disruptive next step for co-ordinated individualised healthcare in the Australian context.

Piloting a national laboratory electronic programme status reporting system.

The NHLS performs close to 4 million CD4 tests per annum for the public sector in South Africa through a network of 60 CD4 testing laboratories. CD4 laboratory data provides an assessment of the number of patients on ART and HIV-positive patients in the pre-ART wellness programs. This study aims to develop a laboratory based Comprehensive Care, Management and Treatment of HIV and AIDS (CCMT) programme status reporting system for CD4 testing at three health facilities in the Ekurhuleni health district using a newly developed CCMT request form, the Laboratory Information System (LIMS) and Corporate Data Warehouse (CDW). The study will generate monitoring and evaluation data to assist in the management of health facilities through a national electronic corporate data warehouse.