https://orcid.org/0000-0002-7429-3710
![Sample our Health and Social Care journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5938/TOC-Subject-Sample-2021-Health-Social-Care.jpg"})
ABSTRACT
Objective
In recent years research has identified important predictors for nursing home admission (NHA). However, as far as we know, the previous risk models use complex variable sets from many sources and the output is a single risk value. The objective of this study was to develop an NHA risk model with a variable set from single data source and richer output information.
Methods
In this study, we developed a model selecting variables only from the RAI-HC (Resident Assessment Instrument – Home Care) system. Furthermore, we used principal component analysis and K-means clustering to target proper interventions for high-risk clients.
Results
The performance of the model was close to the complex previous model (recall vs.
and specificity
vs.
). For the risk clients, three intervention clusters (deficiency in physical functionality, deficiency in cognitive functionality and depression and mood disorders) were found.
Conclusion
The NHA risk model and intervention clusters are important because they enable the identification of proper interventions for the right clients. The fact that the model with RAI-HC data alone was accurate enough simplifies the integration of the NHA risk model into practice because it uses data from one system and the algorithm can be integrated easily into the source system.
List of abbreviations
| • NHA: | = | Nursing Home Admission |
| • RAI-HC: | = | Resident Assessment Instrument-Home Care |
| • SFS: | = | Sequential Forward Selection |
| • CA: | = | Classification Accuracy |
| • AUC: | = | Area Under the Curve |
| • PCA: | = | Principal Component Analysis |
Acknowledgments
The authors would like to thank Mr. Tuomas Nenonen for his contribution to RAI assessment data acquisition.
Availability of data and materials
The dataset which we have acquired will not be shared as a supplementary file. All Python and R codes for data analysis are available upon request.
Competing interests
MN: employment (Nordic Healthcare Group), RLL, PT, and VK: employment and stockholder (Nordic Healthcare Group). Nordic Healthcare Group (NHG) is a Finnish company specialized in planning and developing health and social services, especially in Finland, Sweden, and Denmark. ES and AT declare that they have no competing interests.
Author’s contributions
MN participated in the data processing, study design, performed the literature review, programming all analyses and wrote the first draft of the paper. RLL and PT contributed to the design of the study, interpretation of the results and were involved in writing of the first draft of the paper. ES and AT participated in the design of the study and revised the paper. VK managed and supervised the study, participated in the design of the study and revised the paper. All authors read and approved the final manuscript.
Ethics approval and consent to participate
The data were provided by the city of Tampere and Pirkanmaa Hospital District who granted us the research permit and the privilege to use the data. Data were aggregated and anonymized by the data administration of the city of Tampere before they were provided to the authors. Ethics approval was not required. In Finland, ethics approval is not required for retrospective registry studies with anonymized data. Since this was a retrospective study, consent to participate was not required.
Notes
1. Tampere is the third-largest city in Finland. The percent of population over 65 years is 18.0% which is approximately same as in the other big cities in Finland (http://www.stat.fi). Also, the scope or services offered for the elderly as well as eligibility criteria for home care and nursing home care are fairly similar in all areas in Finland.
2. The data were linked to the client level using unique encrypted identifiers..