Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

Shuo Liu; Jing Han; Estela Laporta Puyal; Spyridon Kontaxis; Shaoxiong Sun; Patrick Locatelli; Judith Dineley; Florian B. Pokorny; Gloria Dalla Costa; Letizia Leocani; Ana Isabel Guerrero; Carlos Nos; Ana Zabalza; Per Soelberg Sørensen; Mathias Buron; Melinda Magyari; Yatharth Ranjan; Zulqarnain Rashid; Pauline Conde; Callum Stewart; Amos A. Folarin; Richard JB Dobson; Raquel Bailón; Srinivasan Vairavan; Nicholas Cummins; Vaibhav A. Narayan; Matthew Hotopf; Giancarlo Comi; Björn Schuller; RADAR A.D.A.R.C.N.S. Consortium

doi:10.1016/j.patcog.2021.108403

Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

Shuo Liu^*, Jing Han, Estela Laporta Puyal, Spyridon Kontaxis, Shaoxiong Sun, Patrick Locatelli, Judith Dineley, Florian B. Pokorny, Gloria Dalla Costa, Letizia Leocani, Ana Isabel Guerrero, Carlos Nos, Ana Zabalza, Per Soelberg Sørensen, Mathias Buron, Melinda Magyari, Yatharth Ranjan, Zulqarnain Rashid, Pauline Conde, Callum StewartAmos A. Folarin, Richard JB Dobson, Raquel Bailón, Srinivasan Vairavan, Nicholas Cummins, Vaibhav A. Narayan, Matthew Hotopf, Giancarlo Comi, Björn Schuller, RADAR A.D.A.R.C.N.S. Consortium

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

28 Citations (Scopus)

Abstract

This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95.3%, a sensitivity of 100% and a specificity of 90.6%, an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate.

Original language	English
Article number	108403
Journal	PATTERN RECOGNITION
Volume	123
Early online date	26 Oct 2021
DOIs	https://doi.org/10.1016/j.patcog.2021.108403
Publication status	Published - Mar 2022

Keywords

Anomaly detection
Contrastive learning
Convolutional auto-encoder
COVID-19
Respiratory tract infection

UN SDGs

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

Access to Document

10.1016/j.patcog.2021.108403

Cite this

Liu, S., Han, J., Puyal, E. L., Kontaxis, S., Sun, S., Locatelli, P., Dineley, J., Pokorny, F. B., Costa, G. D., Leocani, L., Guerrero, A. I., Nos, C., Zabalza, A., Sørensen, P. S., Buron, M., Magyari, M., Ranjan, Y., Rashid, Z., Conde, P., ... Consortium, RADAR. A. D. A. R. C. N. S. (2022). Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder. PATTERN RECOGNITION, 123, Article 108403. https://doi.org/10.1016/j.patcog.2021.108403

@article{bcacbfe351914ea6a131a40cda68ddb5,

title = "Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder",

abstract = "This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95.3%, a sensitivity of 100% and a specificity of 90.6%, an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate.",

keywords = "Anomaly detection, Contrastive learning, Convolutional auto-encoder, COVID-19, Respiratory tract infection",

author = "Shuo Liu and Jing Han and Puyal, {Estela Laporta} and Spyridon Kontaxis and Shaoxiong Sun and Patrick Locatelli and Judith Dineley and Pokorny, {Florian B.} and Costa, {Gloria Dalla} and Letizia Leocani and Guerrero, {Ana Isabel} and Carlos Nos and Ana Zabalza and S{\o}rensen, {Per Soelberg} and Mathias Buron and Melinda Magyari and Yatharth Ranjan and Zulqarnain Rashid and Pauline Conde and Callum Stewart and Folarin, {Amos A.} and Dobson, {Richard JB} and Raquel Bail{\'o}n and Srinivasan Vairavan and Nicholas Cummins and Narayan, {Vaibhav A.} and Matthew Hotopf and Giancarlo Comi and Bj{\"o}rn Schuller and Consortium, {RADAR A.D.A.R.C.N.S.}",

note = "Funding Information: This project has received funding from the Innovative Medicines Initiative 6 1 2 Joint Undertaking under grant agreement No 115902. This Joint Undertaking receives support from the European Union{\textquoteright}s Horizon 2020 research and innovation programme and EFPIA. This communication reflects the views of the RADAR-CNS consortium and neither IMI nor the European Union and EFPIA are liable for any use that may be made of the information contained herein. Funding Information: This project has received funding from the Innovative Medicines Initiative 6 2 Joint Undertaking under grant agreement No 115902. This Joint Undertaking receives support from the European Union's Horizon 2020 research and innovation programme and EFPIA. This communication reflects the views of the RADAR-CNS consortium and neither IMI nor the European Union and EFPIA are liable for any use that may be made of the information contained herein. Publisher Copyright: {\textcopyright} 2021 Elsevier Ltd",

year = "2022",

month = mar,

doi = "10.1016/j.patcog.2021.108403",

language = "English",

volume = "123",

journal = "PATTERN RECOGNITION",

issn = "0031-3203",

publisher = "Elsevier Limited",

}

Liu, S, Han, J, Puyal, EL, Kontaxis, S, Sun, S, Locatelli, P, Dineley, J, Pokorny, FB, Costa, GD, Leocani, L, Guerrero, AI, Nos, C, Zabalza, A, Sørensen, PS, Buron, M, Magyari, M, Ranjan, Y, Rashid, Z, Conde, P, Stewart, C , Folarin, AA, Dobson, RJB, Bailón, R, Vairavan, S, Cummins, N, Narayan, VA, Hotopf, M, Comi, G, Schuller, B & Consortium, RADARADARCNS 2022, 'Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder', PATTERN RECOGNITION, vol. 123, 108403. https://doi.org/10.1016/j.patcog.2021.108403

TY - JOUR

T1 - Fitbeat

T2 - COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

AU - Liu, Shuo

AU - Han, Jing

AU - Puyal, Estela Laporta

AU - Kontaxis, Spyridon

AU - Sun, Shaoxiong

AU - Locatelli, Patrick

AU - Dineley, Judith

AU - Pokorny, Florian B.

AU - Costa, Gloria Dalla

AU - Leocani, Letizia

AU - Guerrero, Ana Isabel

AU - Nos, Carlos

AU - Zabalza, Ana

AU - Sørensen, Per Soelberg

AU - Buron, Mathias

AU - Magyari, Melinda

AU - Ranjan, Yatharth

AU - Rashid, Zulqarnain

AU - Conde, Pauline

AU - Stewart, Callum

AU - Folarin, Amos A.

AU - Dobson, Richard JB

AU - Bailón, Raquel

AU - Vairavan, Srinivasan

AU - Cummins, Nicholas

AU - Narayan, Vaibhav A.

AU - Hotopf, Matthew

AU - Comi, Giancarlo

AU - Schuller, Björn

AU - Consortium, RADAR A.D.A.R.C.N.S.

N1 - Funding Information: This project has received funding from the Innovative Medicines Initiative 6 1 2 Joint Undertaking under grant agreement No 115902. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA. This communication reflects the views of the RADAR-CNS consortium and neither IMI nor the European Union and EFPIA are liable for any use that may be made of the information contained herein. Funding Information: This project has received funding from the Innovative Medicines Initiative 6 2 Joint Undertaking under grant agreement No 115902. This Joint Undertaking receives support from the European Union's Horizon 2020 research and innovation programme and EFPIA. This communication reflects the views of the RADAR-CNS consortium and neither IMI nor the European Union and EFPIA are liable for any use that may be made of the information contained herein. Publisher Copyright: © 2021 Elsevier Ltd

PY - 2022/3

Y1 - 2022/3

N2 - This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95.3%, a sensitivity of 100% and a specificity of 90.6%, an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate.

AB - This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95.3%, a sensitivity of 100% and a specificity of 90.6%, an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate.

KW - Anomaly detection

KW - Contrastive learning

KW - Convolutional auto-encoder

KW - COVID-19

KW - Respiratory tract infection

UR - http://www.scopus.com/inward/record.url?scp=85118526881&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2021.108403

DO - 10.1016/j.patcog.2021.108403

M3 - Article

AN - SCOPUS:85118526881

SN - 0031-3203

VL - 123

JO - PATTERN RECOGNITION

JF - PATTERN RECOGNITION

M1 - 108403

ER -

Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this