Search

Background and Objectives: Nursing homes (NHs) using the Preferences for Everyday Living Inventory (PELI-NH) to assess important preferences and provide person-centered care find the number of items (72) to be a barrier to using the assessment., Research Design and Methods: Using a sample of n = 255 NH resident responses to the PELI-NH, we used the 16 preference items from the MDS 3.0 Section F to develop a machine learning recommender system to identify additional PELI-NH items that may be important to specific residents. Much like the Netflix recommender system, our system is based on the concept of collaborative filtering whereby insights and predictions (e.g., filters) are created using the interests and preferences of many users. The algorithm identifies multiple sets of "you might also like" patterns called association rules, based upon responses to the 16 MDS preferences that recommends an additional set of preferences with a high likelihood of being important to a specific resident., Results: In the evaluation of the combined apriori and logistic regression approach, we obtained a high recall performance (i.e., the ratio of correctly predicted preferences compared with all predicted preferences and nonpreferences) and high precision (i.e., the ratio of correctly predicted rules with respect to the rules predicted to be true) of 80.2% and 79.2%, respectively., Discussion and Implications: The recommender system successfully provides guidance on how to best tailor the preference items asked of residents and can support preference capture in busy clinical environments, contributing to the feasibility of delivering person-centered care.

Objectives: Nursing home (NH) residents' preferences for everyday living are the foundation for delivering individualized person-centered care. Yet, work has not examined what the most and least important preferences of nursing home residents are and if those preferences change over time., Design: This study examined the change in nursing home residents' (n = 255) preferences for everyday living over a 3-month period. Participants were recruited from 28 NHs in the suburbs of a major metropolitan East Coast area of the United States., Measures: Residents were interviewed face-to-face using the Preferences for Everyday Living Inventory-Nursing Home version at baseline (T1) and 3 months later (T2). Change was analyzed in 2 ways: (1) percentage exact agreement (eg, respondent stated "very important" at both time points) and (2) percentage of preferences that remained either important or not important between T1 and T2., Results: Sixteen preferences were rated as very or somewhat important by 90% or more of NH residents. With regard to the stability of preference ratings, findings demonstrate an average exact agreement of 59%, and an average important versus not important agreement of 82%. In addition, 68 of the 72 preferences had 70% or higher stability over time. In other words, the preference either remained "important" or "not important" to the NH resident 3 months later. Preferences in the domain of enlisting others in care had the least amount of change., Conclusion/implications: This study highlights the most important everyday living preferences of NH residents and provides assurance to care providers that the majority of preferences assessed via the PELI are both important to NH residents and stable over time. Preference-based care plans can be designed and used over a 3-month period with confidence by providers., (Copyright © 2018 AMDA – The Society for Post-Acute and Long-Term Care Medicine. Published by Elsevier Inc. All rights reserved.)