Constructing the Nursing Value Model Using Readily Available Datasets: Putting the Puzzle Pieces Together

The Nursing Value Model (NVM) is a data framework model developed to measure the value of nursing care at the patient level. The NVM was constructed by multiple datasets extracted and assembled from various sources, such as the hospital electronic health records (EHR) and administrative data. Yet, very few studies have examined this model. As such, this study aimed to introduce how to construct NVM using available health care data, and discuss the feasibility of doing so by describing the insights and pitfalls during the development of the dataset. Data from 5 sources were used to build the dataset used to explore the NVM to estimate patient-level nursing cost estimation. Five aspects of data acquisition and synthesis are described: (a) each dataset acquisition, (b) the data wrangling process, (c) dataset construction, (d) data integrability, and (e) the strengths and weaknesses of each dataset. Six datasets from four different data sources were collected and merged, constructing the final dataset used for the NVM. Unique codes for nurses and patients were not always uniform, making the data complex and difficult to merge. To compute nursing value for the future, data systems need to be designed to collect, organize, and synthesize data easily.