Classifying Text-Based Computer Interactions for Health Monitoring

Lisa M. Vizer, Andrew Sears

Research output: Contribution to journalShort survey

4 Citations (Scopus)

Abstract

Detecting early trends indicating cognitive decline can allow older adults to better manage their health, but current assessments present barriers precluding the use of such continuous monitoring by consumers. To explore the effects of cognitive status on computer interaction patterns, the authors collected typed text samples from older adults with and without pre-mild cognitive impairment (PreMCI) and constructed statistical models from keystroke and linguistic features for differentiating between the two groups. Using both feature sets, they obtained a 77.1 percent correct classification rate with 70.6 percent sensitivity, 83.3 percent specificity, and a 0.808 area under curve (AUC). These results are in line with current assessments for MC - a more advanced disease - but using an unobtrusive method. This research contributes a combination of features for text and keystroke analysis and enhances understanding of how clinicians or older adults themselves might monitor for PreMCI through patterns in typed text. It has implications for embedded systems that can enable healthcare providers and consumers to proactively and continuously monitor changes in cognitive function.

Original languageEnglish (US)
Article number7310820
Pages (from-to)64-71
Number of pages8
JournalIEEE Pervasive Computing
Volume14
Issue number4
DOIs
StatePublished - Oct 1 2015

Fingerprint

Linguistics
Embedded systems
Health
Monitoring
Statistical Models

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

@article{bcfdad62b97441448b0e5682b9e42c79,
title = "Classifying Text-Based Computer Interactions for Health Monitoring",
abstract = "Detecting early trends indicating cognitive decline can allow older adults to better manage their health, but current assessments present barriers precluding the use of such continuous monitoring by consumers. To explore the effects of cognitive status on computer interaction patterns, the authors collected typed text samples from older adults with and without pre-mild cognitive impairment (PreMCI) and constructed statistical models from keystroke and linguistic features for differentiating between the two groups. Using both feature sets, they obtained a 77.1 percent correct classification rate with 70.6 percent sensitivity, 83.3 percent specificity, and a 0.808 area under curve (AUC). These results are in line with current assessments for MC - a more advanced disease - but using an unobtrusive method. This research contributes a combination of features for text and keystroke analysis and enhances understanding of how clinicians or older adults themselves might monitor for PreMCI through patterns in typed text. It has implications for embedded systems that can enable healthcare providers and consumers to proactively and continuously monitor changes in cognitive function.",
author = "Vizer, {Lisa M.} and Andrew Sears",
year = "2015",
month = "10",
day = "1",
doi = "10.1109/MPRV.2015.85",
language = "English (US)",
volume = "14",
pages = "64--71",
journal = "IEEE Pervasive Computing",
issn = "1536-1268",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Classifying Text-Based Computer Interactions for Health Monitoring. / Vizer, Lisa M.; Sears, Andrew.

In: IEEE Pervasive Computing, Vol. 14, No. 4, 7310820, 01.10.2015, p. 64-71.

Research output: Contribution to journalShort survey

TY - JOUR

T1 - Classifying Text-Based Computer Interactions for Health Monitoring

AU - Vizer, Lisa M.

AU - Sears, Andrew

PY - 2015/10/1

Y1 - 2015/10/1

N2 - Detecting early trends indicating cognitive decline can allow older adults to better manage their health, but current assessments present barriers precluding the use of such continuous monitoring by consumers. To explore the effects of cognitive status on computer interaction patterns, the authors collected typed text samples from older adults with and without pre-mild cognitive impairment (PreMCI) and constructed statistical models from keystroke and linguistic features for differentiating between the two groups. Using both feature sets, they obtained a 77.1 percent correct classification rate with 70.6 percent sensitivity, 83.3 percent specificity, and a 0.808 area under curve (AUC). These results are in line with current assessments for MC - a more advanced disease - but using an unobtrusive method. This research contributes a combination of features for text and keystroke analysis and enhances understanding of how clinicians or older adults themselves might monitor for PreMCI through patterns in typed text. It has implications for embedded systems that can enable healthcare providers and consumers to proactively and continuously monitor changes in cognitive function.

AB - Detecting early trends indicating cognitive decline can allow older adults to better manage their health, but current assessments present barriers precluding the use of such continuous monitoring by consumers. To explore the effects of cognitive status on computer interaction patterns, the authors collected typed text samples from older adults with and without pre-mild cognitive impairment (PreMCI) and constructed statistical models from keystroke and linguistic features for differentiating between the two groups. Using both feature sets, they obtained a 77.1 percent correct classification rate with 70.6 percent sensitivity, 83.3 percent specificity, and a 0.808 area under curve (AUC). These results are in line with current assessments for MC - a more advanced disease - but using an unobtrusive method. This research contributes a combination of features for text and keystroke analysis and enhances understanding of how clinicians or older adults themselves might monitor for PreMCI through patterns in typed text. It has implications for embedded systems that can enable healthcare providers and consumers to proactively and continuously monitor changes in cognitive function.

UR - http://www.scopus.com/inward/record.url?scp=84946402553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946402553&partnerID=8YFLogxK

U2 - 10.1109/MPRV.2015.85

DO - 10.1109/MPRV.2015.85

M3 - Short survey

AN - SCOPUS:84946402553

VL - 14

SP - 64

EP - 71

JO - IEEE Pervasive Computing

JF - IEEE Pervasive Computing

SN - 1536-1268

IS - 4

M1 - 7310820

ER -