The Kolling Institute – Health Informatics Project
The Australian healthcare system generates large amounts of data from public and private clinical and non-clinical sources. The lack of connectivity across healthcare services has resulted in significant impacts on the quality of care and patient safety. Consumers, who often assume that information is shared, cannot understand why this is not done and why they have to repeat their personal details when attending public and private health providers across the same campus.
The overarching research hypothesis that is being undertaken by the Kolling Institute is that integration of data can improve the appropriateness, specificity and efficiency of healthcare delivery through inter-disciplinary research.
The Kolling Institute of Medical Research was established over 80 years ago at Royal North Shore Hospital (RNSH) in Sydney. It is one of the leading centres of health and medical research in NSW and is jointly affiliated with the University of Sydney, through the Northern Clinical School, and RNSH in the Northern Sydney Local Health District. In October 2008 Kolling Institute researchers came together in a visionary new research facility that serves as a vital catalyst for the formation of new ideas, new collaborations and new discoveries.
MKM Health was engaged to extract data from multiple sources (public and private) and to create an SQL data store in order to link the extracted data items.
The objective for some stakeholders is to improve patient care by answering clinical questions based on integrated data. For others, the goal is to provide a dashboard of linked data to support multi-disciplinary meetings by gathering all relevant data for a set of nominated patients. Data has been collected and integrated across three exemplars:
- Head and Neck Cancer
Technical and solution skills have been provided by MKM Health in order to link the information available across a number of sources of patient information. The source systems have included; Cerner eMR (including Pathology and Radiology results), McKesson’s Horizon Cardiology System, CSC’s iPharmacy, the ObstetriX maternity system, and Access and Excel databases for Oncology and Cardiology patients. Pathology results have also been incorporated by linking to private pathology providers including Douglas Hanley Moir and this data is then matched with existing data sets.
MKM Health used our Cerner application and CCL skills in order to extract data from the eMR solution for each of the three nominated exemplars. This data is stored in a central Microsoft SQL repository and is matched to data that has been extracted from other systems. Extracts have been created using a combination of direct SQL calls, SSIS load routines and real time HL7 messaging. The initial data has been extracted from the following systems:
- Head and Neck Cancer - eMR, Pharmacy, Access databases and external results
- Maternity - eMR, Pharmacy, ObstetriX
- Cardiology - eMR, McKesson and Excel databases
A secure environment was created (currently residing in the Northern Sydney Health District Data Centre), to support the hosting of the integrated applications. Data matching has been performed, either by using the provided Northern Sydney Medical Record Number, or by matching key patient details.
The integrated datasets are provided to the clinical stakeholders via a number of QlikView applications developed by MKM Health. Our consultants worked closely with clinicians and user groups in order to define the data requirements and visualisation techniques. These applications are then provided to the user base via a web browser using a comprehensive security and access model.
A research database has been created for the three exemplars containing more than 900,000 patient episodes and 500,000 associated pathology/radiology results.
This data is used to support Multi-disciplinary Team (MDT) meetings and to answer specific clinical questions, for example:
- How many of our patients are anemic just prior to birth and who are they?
- Of our patients who are discharged how many are not breast feeding and where do they live?
- How many of our patients represent following birth?
- How great is the variation in care or women in their first pregnancy?
The clinicians and Kolling Institute research staff now have an integrated view of the data which helps them to see variation in care and make informed decisions about their patients during their episode of care.
Individual dashboards and search criteria have been created in order to suit the individual exemplars.
The project is currently working with a number of other interested parties in order to integrate additional datasets, for example external ultrasound providers and private hospital providers. MKM Health continues to refine the data visualisation dashboards based on clinical input and will rollout restricted access views to appropriate users.
An ongoing operational model is also being implemented which will enable the agreed datasets to be refreshed from the production systems. It is expected that alternative analytical tools will be investigated and other research groups will become involved. For example, a group within the Institute has been engaged to conduct natural language processing on the textual patient results provided.
It is expected that when successful, the results of this research project will be extended in order to include data from other Local Health Districts.