Dataset Information

A Machine Learning Recommender System to Tailor Preference Assessments to Enhance Person-Centered Care Among Nursing Home Residents.

ABSTRACT: 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.

SUBMITTER: Gannod GC

PROVIDER: S-EPMC6326251 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Recommender System to Tailor Preference Assessments to Enhance Person-Centered Care Among Nursing Home Residents.

Gannod Gerald C GC Abbott Katherine M KM Van Haitsma Kimberly K Martindale Nathan N Heppner Alexandra A

The Gerontologist 20190101 1

<h4>Background and objectives</h4>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.<h4>Research design and methods</h4>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 ...[more]

PMID: 29790930

Similar Datasets

Project description:Background and objectivesNursing home (NH) staff mealtime care approaches are associated with behaviors of residents with dementia, but their impact on food intake remains unexplored. This study examined the role of staff person-centered and task-centered approaches and resident positive, neutral, and challenging behaviors on food intake.Research design and methodsVideotaped mealtime observations (N = 160) involving 36 staff and 27 residents (53 unique staff-resident dyads) in 9 NHs were coded using the refined Cue Utilization and Engagement in Dementia mealtime video-coding scheme. The dependent variable was resident food intake. The independent variables were staff person-centered approaches that support resident abilities, staff-resident (dyadic) interactions, and dining environments, staff task-centered approaches, and resident positive, neutral, and challenging behaviors. Resident challenging behaviors included mealtime functional impairments and resistive behaviors. Linear mixed modeling was used. Moderating effects of staff approaches, food type, and length of dyadic mealtime interactions (ie, video duration) were examined.ResultsThe relationship between food intake and resident mealtime functional impairments was moderated by food type (p < .001). The relationship between food intake and resident resistive behaviors was moderated by food type (p = .002) and staff person-centered verbal approaches (p = .001). The relationships between food intake and staff person-centered nonverbal approaches (p = .003) and resident positive/neutral nonverbal behaviors (p = .004) were moderated by the length of dyadic mealtime interactions.Discussion and implicationsFood intake was associated with staff person-centered approaches and resident positive/neutral and challenging behaviors. Findings emphasize the importance of facilitating positive dyadic interactions using individualized, context-based, multifaceted, person-centered care. Future research on temporal and causal relationships is warranted in larger diverse samples.

Project description:IntroductionMealtime is a critical daily activity to ensure nutrition, hydration, function and socialisation. Interactions between staff and residents during mealtimes are complex and dynamic processes including verbal and/or nonverbal communication that can be positive/neutral or challenging. This study examined characteristics of and relationships between person-centred and task-centred care and positive/neutral and challenging mealtime behaviours in persons with dementia.MethodsThis study was a secondary behavioural analyses of videotaped mealtime observations (n = 110) involving 42 unique staff-resident dyads (29 staff and 25 residents with dementia) in nine nursing homes. The refined Cue Utilization and Engagement in Dementia mealtime video-coding scheme was used to code videos during 2019-2020. Dependent variables representing resident mealtime behaviours included positive verbal behaviours, positive/neutral nonverbal behaviours, functional impairments (nonverbal) and resistive behaviours (verbal and nonverbal). Independent variables were staff person-centred and task-centred approaches (verbal and nonverbal). Relationships between resident mealtime behaviours and staff approaches were examined using bivariate analysis and logistic regression.ResultsStaff person-centred verbal approaches were associated with resident positive verbal behaviours (OR = 1.38, 95% CI = 1.09-1.76), functional impairments (OR = 0.81, 95% CI = 0.66-1.00) and resistive behaviours (OR = 1.65, 95% CI = 1.18-2.31). Staff person-centred nonverbal approaches were associated with resident functional impairments (OR = 1.33, 95% CI = 1.02-1.74). Staff task-centred approaches were not associated with resident positive/neutral or challenging mealtime behaviours.ConclusionThis study characterised staff approaches and resident behaviours during mealtime care and provided preliminary support on associations between staff person-centred approaches and resident positive and challenging behaviours. Person-centred mealtime care practice is recommended by focusing on support of common, challenging behaviours and reinforcement of positive behaviours with adequate consideration of individual needs and preferences.

Dataset Information

A Machine Learning Recommender System to Tailor Preference Assessments to Enhance Person-Centered Care Among Nursing Home Residents.

Publications

A Machine Learning Recommender System to Tailor Preference Assessments to Enhance Person-Centered Care Among Nursing Home Residents.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets