Detecting mild cognitive loss with continuous monitoring of medication adherence

Yonghong Huang, Deniz Erdogmus, Zhengdong Lu, Todd K. Leen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes an approach for detecting early cognitive loss using medication adherence behavior. We investigate the discriminative power of a comprehensive set of recurrent medication timing features extracted from time-of-day and inter-dose timing statistics. We adopt information theoretic measures for feature ranking for initial dimensionality reduction and conduct exhaustive leave-one-out cross validation for final feature selection and regularization. The selected feature set is subjected to a support vector machine for classification. The results demonstrate that patterns of adherence based on the data from relatively unobtrusive behavior monitoring can make reliable inference for mild cognitive loss individuals.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages609-612
Number of pages4
DOIs
StatePublished - 2008
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: Mar 31 2008Apr 4 2008

Other

Other2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period3/31/084/4/08

Fingerprint

time measurement
ranking
Monitoring
inference
Support vector machines
Feature extraction
Statistics
statistics
dosage

Keywords

  • Cognitive loss detection
  • Continuous monitoring
  • Medication adherence
  • Pattern recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Huang, Y., Erdogmus, D., Lu, Z., & Leen, T. K. (2008). Detecting mild cognitive loss with continuous monitoring of medication adherence. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 609-612). [4517683] https://doi.org/10.1109/ICASSP.2008.4517683

Detecting mild cognitive loss with continuous monitoring of medication adherence. / Huang, Yonghong; Erdogmus, Deniz; Lu, Zhengdong; Leen, Todd K.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 609-612 4517683.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, Y, Erdogmus, D, Lu, Z & Leen, TK 2008, Detecting mild cognitive loss with continuous monitoring of medication adherence. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4517683, pp. 609-612, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517683
Huang Y, Erdogmus D, Lu Z, Leen TK. Detecting mild cognitive loss with continuous monitoring of medication adherence. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. p. 609-612. 4517683 https://doi.org/10.1109/ICASSP.2008.4517683
Huang, Yonghong ; Erdogmus, Deniz ; Lu, Zhengdong ; Leen, Todd K. / Detecting mild cognitive loss with continuous monitoring of medication adherence. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2008. pp. 609-612
@inproceedings{28b625f7e82c4dafa98b677e81db7eee,
title = "Detecting mild cognitive loss with continuous monitoring of medication adherence",
abstract = "This paper describes an approach for detecting early cognitive loss using medication adherence behavior. We investigate the discriminative power of a comprehensive set of recurrent medication timing features extracted from time-of-day and inter-dose timing statistics. We adopt information theoretic measures for feature ranking for initial dimensionality reduction and conduct exhaustive leave-one-out cross validation for final feature selection and regularization. The selected feature set is subjected to a support vector machine for classification. The results demonstrate that patterns of adherence based on the data from relatively unobtrusive behavior monitoring can make reliable inference for mild cognitive loss individuals.",
keywords = "Cognitive loss detection, Continuous monitoring, Medication adherence, Pattern recognition",
author = "Yonghong Huang and Deniz Erdogmus and Zhengdong Lu and Leen, {Todd K.}",
year = "2008",
doi = "10.1109/ICASSP.2008.4517683",
language = "English (US)",
isbn = "1424414849",
pages = "609--612",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Detecting mild cognitive loss with continuous monitoring of medication adherence

AU - Huang, Yonghong

AU - Erdogmus, Deniz

AU - Lu, Zhengdong

AU - Leen, Todd K.

PY - 2008

Y1 - 2008

N2 - This paper describes an approach for detecting early cognitive loss using medication adherence behavior. We investigate the discriminative power of a comprehensive set of recurrent medication timing features extracted from time-of-day and inter-dose timing statistics. We adopt information theoretic measures for feature ranking for initial dimensionality reduction and conduct exhaustive leave-one-out cross validation for final feature selection and regularization. The selected feature set is subjected to a support vector machine for classification. The results demonstrate that patterns of adherence based on the data from relatively unobtrusive behavior monitoring can make reliable inference for mild cognitive loss individuals.

AB - This paper describes an approach for detecting early cognitive loss using medication adherence behavior. We investigate the discriminative power of a comprehensive set of recurrent medication timing features extracted from time-of-day and inter-dose timing statistics. We adopt information theoretic measures for feature ranking for initial dimensionality reduction and conduct exhaustive leave-one-out cross validation for final feature selection and regularization. The selected feature set is subjected to a support vector machine for classification. The results demonstrate that patterns of adherence based on the data from relatively unobtrusive behavior monitoring can make reliable inference for mild cognitive loss individuals.

KW - Cognitive loss detection

KW - Continuous monitoring

KW - Medication adherence

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=51449083114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449083114&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517683

DO - 10.1109/ICASSP.2008.4517683

M3 - Conference contribution

SN - 1424414849

SN - 9781424414840

SP - 609

EP - 612

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -