Population health: a nursing action plan.

The passage of the Affordable Care Act shifted the focus of health care from individual, patient specific, episodic care, towards health management of groups of people with an emphasis on primary and preventive care. Population health management assists to attain and maintain health while improving quality and lowering costs. The recent Catalyst for Change report creates an urgent call for harnessing the power of nurses-in our communities, schools, businesses, homes and hospitals-to build capacity for population health. Informatics Nurse Specialists are prepared to bridge roles across practice, research, education, and policy to support this call. Each year, the AMIA Nursing Informatics Working Group convenes an expert panel to reflect on the "hot topics" of interest to nursing. Not surprisingly, the 2017 topic was on the current state and challenges of population health. The following summary reflects the panel's perspectives and recommendations for action.

Measuring Nursing Value from the Electronic Health Record.

We report the findings of a big data nursing value expert group made up of 14 members of the nursing informatics, leadership, academic and research communities within the United States tasked with 1. Defining nursing value, 2. Developing a common data model and metrics for nursing care value, and 3. Developing nursing business intelligence tools using the nursing value data set. This work is a component of the Big Data and Nursing Knowledge Development conference series sponsored by the University Of Minnesota School Of Nursing. The panel met by conference calls for fourteen 1.5 hour sessions for a total of 21 total hours of interaction from August 2014 through May 2015. Primary deliverables from the bit data expert group were: development and publication of definitions and metrics for nursing value; construction of a common data model to extract key data from electronic health records; and measures of nursing costs and finance to provide a basis for developing nursing business intelligence and analysis systems.

Measuring Nursing Care Value.

The value of nursing care as well as the contribution of individual nurses to clinical outcomes has been difficult to measure and evaluate. Existing health care financial models hide the contribution of nurses; therefore, the link between the cost and quality o nursing care is unknown. New data and methods are needed to articulate the added value of nurses to patient care. The final results and recommendations of an expert workgroup tasked with defining and measuring nursing care value, including a data model to allow extraction of key information from electronic health records to measure nursing care value, are described. A set of new analytic metrics are proposed.

Powering Big Data for Nursing Through Partnership.

The Big Data Principles Workgroup (Workgroup) was established with support of the Healthcare Information and Management Systems Society. Building on the Triple Aim challenge, the Workgroup sought to identify Big Data principles, barriers, and challenges to nurse-sensitive data inclusion into Big Data sets. The product of this pioneering partnership Workgroup was the "Guiding Principles for Big Data in Nursing-Using Big Data to Improve the Quality of Care and Outcomes."

Nursing Care Value-Based Financial Models.

Nursing care makes up one of the largest expenditures in the health care system, yet patient-level nursing intensity and costs are essentially unknown. Prior efforts to define nursing care value have been stymied by a lack of available data; however, emerging information from electronic health records provide an opportunity to measure nursing care in ways that have not been possible. New metrics using these data will allow improved measurement of cost, quality, and intensity at the level of each nurse and patient across many different settings which can be used to inform operational and clinical decision making. In this article, the initial results and recommendations of an expert panel tasked with defining and measuring nursing care value as part of a larger effort to address evolving issues related to big data and nursing knowledge development are described.

The economic value of health care data.

The amount of health care data in our world has been exploding, and the ability to store, aggregate, and combine data and then use the results to perform deep analyses have become ever more important. "Big data," large pools of data that can be captured, communicated, aggregated, stored, and analyzed, are now part of every sector and function of the global economy. While most research into big data thus far has focused on the question of their volume, there is evidence that the business and economic possibilities of big data and their wider implications are important for consideration. It is even offering the possibility that health care data could become the most valuable asset over the next 5 years as "secondary use" of electronic health record data takes off.

Staffing based on evidence: can health information technology make it possible?

Health care leaders must balance nurse staffing between financial viability and quality of care. The potential to use health information technology as a tool to assess effective nurse staffing decisions is a rather new phenomena explored by some of the thought leaders in nursing informatics. This preliminary pilot study is one of a few attempts at engineering health IT to identify factors that lead to a meaningful model for predicting nurse intensity. The Pilot Study provided richness to the design of a new model Clinical Demand Index to calculate nurse intensity by: (a) identifying the factors of how nurses spend their time; (b) using health IT data mining techniques to determine data types for abstraction; and (c) identifying variables that are most closely related to nursing intensity of how nurses spend their time. The CDI Model and health IT can make staffing based on evidence a reality and thus play an important role in demonstrating that clinical data from the electronic health record can be abstracted real time and used to objectively calculate nurse intensity and continue to engineer a learning health system.

Engineering a learning healthcare system: using health information technology to develop an objective nurse staffing tool.

Nurses represent the largest proportion of direct healthcare providers. Overstaffed or understaffed units will have implications for the quality, cost, patient, and nurse satisfaction. It is vital that nurses are armed with appropriate instruments and data to help them plan and implement efficient and effective nursing teams. A compelling case is made for the association between nursing care and clinical, quality, and financial outcomes. Even though there is a great body of work on the correlation, there is little agreement on the best approach to determine the correct balance between the patient-to-nurse ratios. The sheer number of variables depicted in the literature suggests why precise evidenced based formulas are difficult to achieve. This paper will describe a practice based knowledge generation mixed methods study using detailed observation and electronic health record abstraction to generate a structural equation for use in predicting staffing needs.