Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity

Syed Monowar Hossain, Amin Ahsan Ali, Md Mahbubur Rahman, Emre Ertin, David Epstein, Ashley Kennedy, Kenzie Preston, Annie Umbricht, Yixin Chen, Santosh Kumar

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

Abstract

A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the natural free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably in the natural field environment. In this paper, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detecting drug use events in the field is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collect 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We develop a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We develop efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then apply our model on the recovery segments from these windows. Our model achieves 100% true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data.

Original languageEnglish (US)
Title of host publicationIPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)
PublisherIEEE Computer Society
Pages71-82
Number of pages12
ISBN (Print)9781479931460
DOIs
StatePublished - 2014
Event13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014 - Berlin, Germany
Duration: Apr 15 2014Apr 17 2014

Other

Other13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014
CountryGermany
CityBerlin
Period4/15/144/17/14

Fingerprint

Neurology
Recovery
Electrocardiography
Chemical activation
Health
Time series

Keywords

  • Drug Event Detection
  • Electrocardiogram
  • Wearable Sensors

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Hossain, S. M., Ali, A. A., Rahman, M. M., Ertin, E., Epstein, D., Kennedy, A., ... Kumar, S. (2014). Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity. In IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week) (pp. 71-82). [6835794] IEEE Computer Society. https://doi.org/10.1109/IPSN.2014.6846742

Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity. / Hossain, Syed Monowar; Ali, Amin Ahsan; Rahman, Md Mahbubur; Ertin, Emre; Epstein, David; Kennedy, Ashley; Preston, Kenzie; Umbricht, Annie; Chen, Yixin; Kumar, Santosh.

IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society, 2014. p. 71-82 6835794.

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

Hossain, SM, Ali, AA, Rahman, MM, Ertin, E, Epstein, D, Kennedy, A, Preston, K, Umbricht, A, Chen, Y & Kumar, S 2014, Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity. in IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)., 6835794, IEEE Computer Society, pp. 71-82, 13th IEEE/ACM International Conference on Information Processing in Sensor Networks, IPSN 2014, Berlin, Germany, 4/15/14. https://doi.org/10.1109/IPSN.2014.6846742
Hossain SM, Ali AA, Rahman MM, Ertin E, Epstein D, Kennedy A et al. Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity. In IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society. 2014. p. 71-82. 6835794 https://doi.org/10.1109/IPSN.2014.6846742
Hossain, Syed Monowar ; Ali, Amin Ahsan ; Rahman, Md Mahbubur ; Ertin, Emre ; Epstein, David ; Kennedy, Ashley ; Preston, Kenzie ; Umbricht, Annie ; Chen, Yixin ; Kumar, Santosh. / Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity. IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week). IEEE Computer Society, 2014. pp. 71-82
@inproceedings{86e5f0a808a24f52b33ff4947f358ef5,
title = "Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity",
abstract = "A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the natural free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably in the natural field environment. In this paper, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detecting drug use events in the field is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collect 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We develop a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We develop efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then apply our model on the recovery segments from these windows. Our model achieves 100{\%} true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data.",
keywords = "Drug Event Detection, Electrocardiogram, Wearable Sensors",
author = "Hossain, {Syed Monowar} and Ali, {Amin Ahsan} and Rahman, {Md Mahbubur} and Emre Ertin and David Epstein and Ashley Kennedy and Kenzie Preston and Annie Umbricht and Yixin Chen and Santosh Kumar",
year = "2014",
doi = "10.1109/IPSN.2014.6846742",
language = "English (US)",
isbn = "9781479931460",
pages = "71--82",
booktitle = "IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Identifying drug (cocaine) intake events from acute physiological response in the presence of free-living physical activity

AU - Hossain, Syed Monowar

AU - Ali, Amin Ahsan

AU - Rahman, Md Mahbubur

AU - Ertin, Emre

AU - Epstein, David

AU - Kennedy, Ashley

AU - Preston, Kenzie

AU - Umbricht, Annie

AU - Chen, Yixin

AU - Kumar, Santosh

PY - 2014

Y1 - 2014

N2 - A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the natural free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably in the natural field environment. In this paper, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detecting drug use events in the field is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collect 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We develop a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We develop efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then apply our model on the recovery segments from these windows. Our model achieves 100% true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data.

AB - A variety of health and behavioral states can potentially be inferred from physiological measurements that can now be collected in the natural free-living environment. The major challenge, however, is to develop computational models for automated detection of health events that can work reliably in the natural field environment. In this paper, we develop a physiologically-informed model to automatically detect drug (cocaine) use events in the free-living environment of participants from their electrocardiogram (ECG) measurements. The key to reliably detecting drug use events in the field is to incorporate the knowledge of autonomic nervous system (ANS) behavior in the model development so as to decompose the activation effect of cocaine from the natural recovery behavior of the parasympathetic nervous system (after an episode of physical activity). We collect 89 days of data from 9 active drug users in two residential lab environments and 922 days of data from 42 active drug users in the field environment, for a total of 11,283 hours. We develop a model that tracks the natural recovery by the parasympathetic nervous system and then estimates the dampening caused to the recovery by the activation of the sympathetic nervous system due to cocaine. We develop efficient methods to screen and clean the ECG time series data and extract candidate windows to assess for potential drug use. We then apply our model on the recovery segments from these windows. Our model achieves 100% true positive rate while keeping the false positive rate to 0.87/day over (9+ hours/day of) lab data and to 1.13/day over (11+ hours/day of) field data.

KW - Drug Event Detection

KW - Electrocardiogram

KW - Wearable Sensors

UR - http://www.scopus.com/inward/record.url?scp=84904674926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904674926&partnerID=8YFLogxK

U2 - 10.1109/IPSN.2014.6846742

DO - 10.1109/IPSN.2014.6846742

M3 - Conference contribution

AN - SCOPUS:84904674926

SN - 9781479931460

SP - 71

EP - 82

BT - IPSN 2014 - Proceedings of the 13th International Symposium on Information Processing in Sensor Networks (Part of CPS Week)

PB - IEEE Computer Society

ER -