Topic models for automated motor analysis in schizophrenia patients

Talia Tron; Yehezkel S. Resheff; Mikhail Bazhmin; Abraham Peled; Alexander Grinsphoon; Daphna Weinshall

doi:10.1109/BSN.2018.8329678

Topic models for automated motor analysis in schizophrenia patients

Talia Tron, Yehezkel S. Resheff, Mikhail Bazhmin, Abraham Peled, Alexander Grinsphoon, Daphna Weinshall

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Wearable devices fitted with various sensors are increasingly being used for the automatic and continuous tracking and monitoring of patients. Only first steps have been taken in the field of psychiatric care, where long term tracking of patient behavior holds the promise to help practitioners to better understand both individual patients, and the disorders in general. In this paper we use topic models for unsupervised analysis of movement activity of schizophrenia patients in a closed ward setting. Results demonstrate that features computed on the basis of this analysis differentially characterize interesting sub-populations of schizophrenia patients. Positive-signs schizophrenia sub-population was found to have high motor richness and low typicallity, while negative-signs patients had low motor richness and lower typicality. In addition we design a classifier which correctly classified up to 80% of the clinical sub-population (f-score=0.774) based on motor features.

Original language	American English
Title of host publication	2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	140-143
Number of pages	4
ISBN (Electronic)	9781538611098
DOIs	https://doi.org/10.1109/BSN.2018.8329678
State	Published - 2 Apr 2018
Event	15th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018 - Las Vegas, United States Duration: 4 Mar 2018 → 7 Mar 2018

Publication series

Name	2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018
Volume	2018-January

Conference

Conference	15th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018
Country/Territory	United States
City	Las Vegas
Period	4/03/18 → 7/03/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BSN.2018.8329678

Cite this

Tron, T., Resheff, Y. S., Bazhmin, M., Peled, A., Grinsphoon, A., & Weinshall, D. (2018). Topic models for automated motor analysis in schizophrenia patients. In 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018 (pp. 140-143). (2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BSN.2018.8329678

Tron, Talia ; Resheff, Yehezkel S. ; Bazhmin, Mikhail et al. / Topic models for automated motor analysis in schizophrenia patients. 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 140-143 (2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018).

@inproceedings{f8d0e6bb62e342caad05dcbaf8069be9,

title = "Topic models for automated motor analysis in schizophrenia patients",

abstract = "Wearable devices fitted with various sensors are increasingly being used for the automatic and continuous tracking and monitoring of patients. Only first steps have been taken in the field of psychiatric care, where long term tracking of patient behavior holds the promise to help practitioners to better understand both individual patients, and the disorders in general. In this paper we use topic models for unsupervised analysis of movement activity of schizophrenia patients in a closed ward setting. Results demonstrate that features computed on the basis of this analysis differentially characterize interesting sub-populations of schizophrenia patients. Positive-signs schizophrenia sub-population was found to have high motor richness and low typicallity, while negative-signs patients had low motor richness and lower typicality. In addition we design a classifier which correctly classified up to 80% of the clinical sub-population (f-score=0.774) based on motor features.",

author = "Talia Tron and Resheff, {Yehezkel S.} and Mikhail Bazhmin and Abraham Peled and Alexander Grinsphoon and Daphna Weinshall",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 15th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018 ; Conference date: 04-03-2018 Through 07-03-2018",

year = "2018",

month = apr,

day = "2",

doi = "10.1109/BSN.2018.8329678",

language = "American English",

series = "2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "140--143",

booktitle = "2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018",

address = "United States",

}

Tron, T, Resheff, YS, Bazhmin, M, Peled, A, Grinsphoon, A & Weinshall, D 2018, Topic models for automated motor analysis in schizophrenia patients. in 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018. 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 140-143, 15th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018, Las Vegas, United States, 4/03/18. https://doi.org/10.1109/BSN.2018.8329678

Topic models for automated motor analysis in schizophrenia patients. / Tron, Talia; Resheff, Yehezkel S.; Bazhmin, Mikhail et al.
2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 140-143 (2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018; Vol. 2018-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Topic models for automated motor analysis in schizophrenia patients

AU - Tron, Talia

AU - Resheff, Yehezkel S.

AU - Bazhmin, Mikhail

AU - Peled, Abraham

AU - Grinsphoon, Alexander

AU - Weinshall, Daphna

PY - 2018/4/2

Y1 - 2018/4/2

N2 - Wearable devices fitted with various sensors are increasingly being used for the automatic and continuous tracking and monitoring of patients. Only first steps have been taken in the field of psychiatric care, where long term tracking of patient behavior holds the promise to help practitioners to better understand both individual patients, and the disorders in general. In this paper we use topic models for unsupervised analysis of movement activity of schizophrenia patients in a closed ward setting. Results demonstrate that features computed on the basis of this analysis differentially characterize interesting sub-populations of schizophrenia patients. Positive-signs schizophrenia sub-population was found to have high motor richness and low typicallity, while negative-signs patients had low motor richness and lower typicality. In addition we design a classifier which correctly classified up to 80% of the clinical sub-population (f-score=0.774) based on motor features.

AB - Wearable devices fitted with various sensors are increasingly being used for the automatic and continuous tracking and monitoring of patients. Only first steps have been taken in the field of psychiatric care, where long term tracking of patient behavior holds the promise to help practitioners to better understand both individual patients, and the disorders in general. In this paper we use topic models for unsupervised analysis of movement activity of schizophrenia patients in a closed ward setting. Results demonstrate that features computed on the basis of this analysis differentially characterize interesting sub-populations of schizophrenia patients. Positive-signs schizophrenia sub-population was found to have high motor richness and low typicallity, while negative-signs patients had low motor richness and lower typicality. In addition we design a classifier which correctly classified up to 80% of the clinical sub-population (f-score=0.774) based on motor features.

UR - http://www.scopus.com/inward/record.url?scp=85049674367&partnerID=8YFLogxK

U2 - 10.1109/BSN.2018.8329678

DO - 10.1109/BSN.2018.8329678

M3 - Conference contribution

AN - SCOPUS:85049674367

T3 - 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018

SP - 140

EP - 143

BT - 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018

Y2 - 4 March 2018 through 7 March 2018

ER -

Tron T, Resheff YS, Bazhmin M, Peled A, Grinsphoon A, Weinshall D. Topic models for automated motor analysis in schizophrenia patients. In 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 140-143. (2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2018). doi: 10.1109/BSN.2018.8329678

Topic models for automated motor analysis in schizophrenia patients

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this