Document Detail

Early Illness Recognition Using In-home Monitoring Sensors and Multiple Instance Learning.
MedLine Citation:
PMID:  22814617     Owner:  NLM     Status:  Publisher    
Background: Many older adults in the US prefer to live independently for as long as they are able, despite the onset of conditions such as frailty and dementia. Solutions are needed to enable independent living, while enhancing safety and peace of mind for their families. Elderly patients are particularly at-risk for late assessment of cognitive changes. Objectives: We predict early signs of illness in older adults by using the data generated by a continuous, unobtrusive nursing home monitoring system. Methods: We describe the possibility of employing a multiple instance learning (MIL) framework for early illness detection. The MIL framework is suitable for training classifiers when the available data presents temporal or location uncertainties. Results: We provide experiments on three datasets that prove the utility of the MIL framework. We first tuned our algorithms on a set of 200 normal/abnormal behavior patterns produced by a dedicated simulator. We then conducted two retrospective studies on residents from the Tiger Place aging in place facility, aged over 70, which have been monitored with motion and bed sensors for over two years. The presence or absence of the illness was manually assessed based on the nursing visit reports. Conclusions: The use of simulated sensor data proved to be very useful for algorithm development and testing. The results obtained using MIL for six Tiger Place residents, an average area under the receiver operator characteristic curve (AROC) of 0.7, are promising. However, more sophisticated MIL classifiers are needed to improve the performance.
M Popescu; A Mahnot
Related Documents :
22481807 - Modelling individual human motor behaviour through model reference iterative learning c...
17954827 - Parental weight estimation of their child's weight is more accurate than other weight e...
19831097 - No sex difference in area estimation.
22121577 - Split-gate-structure 1t dram for retention characteristic improvement.
7294027 - An easy-to-use maximum-likelihood method of estimating the ascertainment probability.
25461587 - Retrieving depth-direction information from tem diffraction data under reciprocal-space...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2012-7-20
Journal Detail:
Title:  Methods of information in medicine     Volume:  51     ISSN:  0026-1270     ISO Abbreviation:  -     Publication Date:  2012 Jul 
Date Detail:
Created Date:  2012-7-20     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0210453     Medline TA:  Methods Inf Med     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Mihail Popescu, PhD, Health Management and Informatics, University of Missouri, HMI Department, 324 Clark Hall, Columbia, MO 65211, USA, E-mail:
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Oropharyngeal teratoma, a rare cause of airway obstruction in neonates.
Next Document:  Discussing Adolescent Sexual Health in African-American Churches.