POKE-R – Using Analytics to Reduce Patient Harm
Major events and surgeries are not the only sources of trauma during a hospital encounter. Many small, less invasive events such as shots, line placements, blood draws, and imaging studies happen throughout a patient’s hospital stay.
Many of these less traumatic events have the potential to negatively impact patient outcomes by increasing the risk of hospital-acquired infections through skin invasions and exposure to organisms, reducing the patient experience by causing pain and frustration, increasing cost and causing other complications. The goal of this project is to reduce such events when they are not clinically required.
This is an analytics project so this goal is facilitated by making accurate and meaningful information available to the appropriate personnel. This includes timely information to clinicians so they can alter treatment, and retrospective trend analysis to enable and track performance improvement and identify opportunities for additional process improvement.
Improving Patient Care Through Analytics
Use of advanced electronic health record (EHR) systems has grown rapidly in the United States.
This has created an abundance of data previously unavailable for analysis. Many health organizations now have reporting systems for operational key performance indicators (KPIs) and regulatory metrics and data warehouse systems for analytics. However, using this increasing information as meaningful knowledge to increase quality of care remains a challenge.
This paper provides our experience utilizing an enterprise data warehouse and business intelligence tools to improve clinical outcomes for patients.
Avoiding pain, unnecessary interventions and reducing costs in the PICU
Avoiding pain, unnecessary interventions and reducing costs in the PICU – a structured approach.
The Virtual Enterprise Data Warehouse For Healthcare
Healthcare organizations have access to more data than ever before. Healthcare analytics is a vital tool for healthcare organizations and hospitals to analyze performance, identify opportunities to improve, make informed decisions, and comply with government and payor regulations.
However, the field of medicine and the political and regulatory landscape are constantly changing, thus these requirements and opportunities rapidly evolve. The traditional best practice solution for business analytics is to organize and consolidate the data into a dimensional data warehouse for analytics purposes. Due to the size of the data, the number of disparate sources and the volume of analytics needs, the overhead to create and maintain such a data warehouse is becoming prohibitive.
In this paper, we introduce a virtual data warehouse solution that combines the design and modelling principles of traditional dimensional modelling with data virtualization and in-memory database architectures to create a system which is more agile, flexible and scalable.
Managing Evolving Code Sets and Integration of Multiple Data Sources in Health Care Analytics
This paper presents our industry experience related to developing data warehouses for healthcare analytics. With the rapid advancement of medical record digitization, there is a very large amount of information available for analysis.
With the heavy focus on driving down health care costs, managing preventive care and improving patient outcomes and satisfaction, there is a growing emphasis on healthcare metrics and analytics. The information for a single patient’s history is composed of data from every hospital, provider, lab, pharmacy and insurance company the patient has encountered. This information needs to be viewed as a whole to accurately analyze the patient’s health. In turn, each patient’s complete health information is needed to accurately evaluate the performance of his or her providers.
This paper will address some challenges we have faced when merging and correlating these diverse data sources. We will provide our solutions and experience addressing key challenges including code set integration and migration and patient identification.