Abstract
BackgroundThe Netherlands is currently investigating the feasibility of moving from fee-for-service to prospective payments for home healthcare, which would require a suitable case-mix system. In 2017, health insurers mandated a preliminary case-mix system as a first step towards generating information on client differences in relation to care use. Home healthcare providers have also increasingly adopted standardized nursing terminology (SNT) as part of their electronic health records (EHRs), providing novel data for predictive modelling.ObjectiveTo explore the predictive potential of SNT data for improvement of the existing preliminary Dutch case-mix classification for home healthcare utilization.MethodsWe extracted client-level data from the EHRs of a large home healthcare provider, including data from the existing Dutch case-mix system, SNT data (specifically, NANDA-I) and the hours of home healthcare provided. We evaluated the predictive accuracy of the case-mix system and the SNT data separately, and combined, using the machine learning algorithm Random Forest.ResultsThe case-mix system had a predictive performance of 22.4% cross-validated R-squared and 6.2% cross-validated Cumming’s Prediction Measure (CPM). Adding SNT data led to a substantial relative improvement in predicting home healthcare hours, yielding 32.1% R-squared and 15.4% CPM.DiscussionThe existing preliminary Dutch case-mix system distinguishes client needs to some degree, but not sufficiently. The results indicate that routinely collected SNT data contain sufficient additional predictive value to warrant further research for use in case-mix system design.
Highlights
As part of the far-reaching reform of long-term care (LTC) in 2015, home healthcare financing in the Netherlands shifted from a public insurance scheme to the pre-existing mandatory health insurance scheme, which is administered by private health insurers [1, 2]
The majority of clients were classified in the LT-SOM case-mix group, and the case-mix groups indicating short-term care need (ST-H and short-term care need for frail elderly (ST-F)) were the largest
Adding standardized nursing terminology (SNT) data (NANDA-I) obtained from electronic health records (EHRs) to the case-mix groups led to 15.4% Cumming’s Prediction Measure (CPM) and 32.1% R-squared, leading to a substantial relative improvement in predicting home healthcare hours
Summary
As part of the far-reaching reform of long-term care (LTC) in 2015, home healthcare financing in the Netherlands shifted from a public insurance scheme to the pre-existing mandatory health insurance scheme, which is administered by private health insurers [1, 2]. In 2017, health insurers mandated a preliminary case-mix system as a first step towards generating information on client differences in relation to care use. Objective To explore the predictive potential of SNT data for improvement of the existing preliminary Dutch case-mix classification for home healthcare utilization. Methods We extracted client-level data from the EHRs of a large home healthcare provider, including data from the existing Dutch case-mix system, SNT data (NANDA-I) and the hours of home healthcare provided. The results indicate that routinely collected SNT data contain sufficient additional predictive value to warrant further research for use in case-mix system design
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
