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.
Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder / 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.; Sorensen, P. S.; Buron, M.; Magyari, M.; Ranjan, Y.; Rashid, Z.; Conde, P.; Stewart, C.; Folarin, A. A.; Dobson, R. J.; Bailon, R.; Vairavan, S.; Cummins, N.; Narayan, V. A.; Hotopf, M.; Comi, G.; Schuller, B.; Consortium, R. A. D. A. R. -C. N. S.. - In: PATTERN RECOGNITION. - ISSN 0031-3203. - 123:(2022). [10.1016/j.patcog.2021.108403]
Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder
Leocani L.;Comi G.;
2022-01-01
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
