Data Centre Profile: The Provincial Health Data Centre of the Western Cape Province, South Africa

Abstract

Introduction: The Western Cape Provincial Health Data Centre (PHDC) consolidates person-level clinical data across government services, leveraging sustained investments in patient registration systems, a unique identifier, and maturation of administrative and clinical digital health systems.

Objectives: The PHDC supports clinical care directly through tools for clinicians which integrate patient data or identify patients in need of interventions, and indirectly through supporting operational and epidemiological analyses.

Methods: The PHDC is housed entirely within government. Data are processed from a range of source systems, usually daily, through distinct harmonisation and curation, beneficiation, and reporting processes. Linkage is predominantly through the unique identifier which doubles as a pervasive folder number, augmented by other identifiers. Further data processing includes triangulation of multiple data sources for enumerating health conditions, with assignment of certainty levels for each enumeration. Outputs include patient-specific email alerts, a web-based consolidated patient clinical viewing platform, filterable line-listings of patients with specific conditions and associated characteristics and outcomes, management reports and dashboards, and data releases in response to operational and research data requests. Strict architectural, administrative and governance processes ensure privacy protection.

Results: In the past decade 8 million unique people are recorded as having sought healthcare in the provincial public sector health services, with current utilisation at 15 million attendances or admissions a year. Cross-sectional enumeration of health conditions includes over 430 000 people with HIV, 500 000 with hypertension, 235 000 with diabetes. Annually 110 000 pregnancies and 54 000 patients with tuberculosis are enumerated. Over 50 data requests are processed each year for internal and external requesters in accordance with data request and release governance processes.

Conclusions: The single consolidated environment for person-level health data in the Western Cape has created new opportunities for supporting patient care, while improving the governance around access to and release of sensitive patient data.

Figure 1: Western Cape Provincial Health Data Centre - high level architecture

Data from various source systems (left) are acquired on either a daily or periodic basis and imported into a Staging database. Data from mHealth and partner systems are imported into a Holding database real-time through an information mediator (OpenHIM). The data in Holding are moved to Staging during the daily load. A copy of all source data is archived after import to enable the data structures to be re-built without repeating the extract from the source systems. In Staging, data are prepared for the consolidated architecture by ensuring each record has a date/time stamp, that each record can be assigned a place (e.g. health facility or community outreach region) and that, where required, the data can be mapped to a common coding system (such as ATC codes for drug data or LOINC codes for lab data). Each record is mapped to a person in the PMI using a linkage engine that compares the identifiers received from the source system to the patient identifiers in the PMI. Once data are linked and cleaned data beneficiation occurs by means of inferring health conditions (episodes), inferring health service contacts (encounters) and by pre-building of patient-level cascade reports. The prepared data are imported into the consolidated architecture which stores Patient and Clinical data in separate databases linked only by an internal unique patient key. The architecture also consists of databases for Facilities, Community-based data, providers, Administrative data, and pre-built data for Reports. Above the database layer there is the information mediator as well as reporting and analysis services from which various outputs are available to meet the 5 primary objectives: (1) Clinical Care (Single Patient Viewer), (2) Operational reporting and epidemiological analysis (provided through patient-level reports accessible on SharePoint), (3) Active Surveillance (provided through patient-level alerts and cascade reports that are updated daily, (4) Business intelligence (provided through management reports on service level utilisation), and (5) Operational analyses and clinical research (provided through bespoke extracts).

Figure 2: Inference approach for health conditions

Episodes are inferred from multiple data sources which carry evidence of a particular health condition. Evidences are categorised as Outcome, High Confidence, Weak-Moderate or Supporting and assigned a score. The example of pregnancy is presented in the figure showing how a high confidence episode is “rolled-up” or combined for an individual with a Rhesus antibody test (performed almost exclusively on pregnant women in the public sector), iron and folate dispensing (a supporting evidence) an ICD10 code (weak evidence due to unreliable clinical coding) and a live birth record in a register (outcome). From the pregnancy episode a maternal cascade is built containing details about the pregnancy, information about the infant, HIV status and transmission information, as well as co-morbidities. The cascade also links dynamically to the Single Patient Viewer so that the electronic health record and/or contact details of individuals requiring follow-up can be easily accessed.

Figure 3: Web-based clinical view (“Single Patient Viewer”) graphical integration example

Clinical data for a given patient are consolidated longitudinally in the “Single Patient Viewer”, a web-based tool for clinician-use. A graphical viewer cartoons the enumerated health conditions (orange and red in the top pane). Clicking on one of these plots laboratory tests, health service encounters, and medicines of relevance to the condition. In this example, of an HIV-infected patient presenting with very advanced disease (CD4 count of <5 cells/μl), numerous treatment interruptions and missed opportunities to change a failing treatment regimen contributed to a 3-year decline in immunological status.