Expert knowledge for modeling functional health from sensor data

S.M.B. Robben, M.C. Pol, B.M. Buurman, B.J.A. Kröse

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)

Abstract

Background: ICT based solutions are increasingly introduced for active and healthy ageing. In this context continuous monitoring of older adults with domestic sensor systems has been suggested to provide important information about their functional health. However, there is not yet a solid model for the interpretation of the sensor data.

Objectives: The aim of our study is to define a set of predictors of functional health that can be measured with domestic sensors and to determine thresholds that identify relevant changes in these predictors.

Methods: On the basis of literature we develop a model that relates functional health predictors to features derived from sensor data. The parameters of this model are determined on the basis of a study among health experts (n = 38). The use of the full model is illustrated with three cases.

Results: We identified 25 predictors and their attributes. For 12 of them that can be measured with passive infrared motion sensors we determined their parameters: the attribute thresholds and the urgency thresholds.

Conclusions: With the parametrized predictors in the model, domestic sensors can be deployed to assess functional health in a standardized way. Three case examples showed how the model can be used as a screening instrument for functional decline
Original languageEnglish
Pages (from-to)516-524
Number of pages9
JournalMethods of information in medicine
Volume55
Issue number6
Early online date20 Jun 2016
DOIs
Publication statusPublished - 2016

Cite this