Back

Application of a Multiplicative Cascade Model to Detect the Early Signs of SARS-CoV-2 Infection Using Heart Rate Data

Heath, R. A.

2022-10-30 epidemiology
10.1101/2022.10.27.22281632 medRxiv
Show abstract

BackgroundWrist-worn devices can keep track of a persons daily health status, including those likely to become infected with the SARS-CoV-2 virus. Technological solutions using mobile devices are being developed to predict the time course of COVID-19. ObjectiveIn this proof-of-concept study, we use heart rate data to detect the first sign of infection in people who have been diagnosed with COVID-19 and to monitor the time-course of the illness. MethodsThe heart-rate data were analysed using a multiplicative cascade driven by a Gaussian process. This provides two parameters, mean and standard deviation, which when combined with similar parameters estimated from control series, provide a Health Index. ResultsFor 90% of 31 cases, the Health Index tracked COVID-19 infection with the virus and subsequent recovery. The first-sign of COVID-19 was detected on average nine days before symptoms were reported. ConclusionsEarly detection of COVID-19 may lead to a reduction in the spread of the virus. The Heath Indexs potential use for the early detection of complications arising from Long COVID would be an important innovation.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 4%
31.8%
Similar papers in this journal
2
Scientific Reports
○ 3612 papers in training set
Top 6%
8.1%
Similar papers in this journal
3
Biomedical Signal Processing and Control
○ 22 papers in training set
Top 0.1%
6.4%
Similar papers in this journal
4
JMIRx Med
◐ 32 papers in training set
Top 0.2%
4.5%
Similar papers in this journal
50% of probability mass above
5
PLOS Digital Health
● 106 papers in training set
Top 2%
3.5%
Similar papers in this journal
6
Journal of Medical Internet Research
◐ 87 papers in training set
Top 0.9%
2.8%
7
PLOS Computational Biology
● 1863 papers in training set
Top 12%
2.4%
8
BMC Research Notes
○ 33 papers in training set
Top 0.2%
2.2%
9
Sensors
○ 43 papers in training set
Top 0.5%
2.2%
10
JMIR Formative Research
◐ 33 papers in training set
Top 0.7%
2.2%
11
IEEE Access
● 35 papers in training set
Top 0.6%
2.1%
12
Heliyon
○ 152 papers in training set
Top 4%
1.4%
13
Royal Society Open Science
● 214 papers in training set
Top 4%
1.4%
14
Computers in Biology and Medicine
○ 128 papers in training set
Top 3%
1.2%
15
IEEE Journal of Biomedical and Health Informatics
● 37 papers in training set
Top 0.8%
1.2%
16
Physiological Measurement
○ 14 papers in training set
Top 0.3%
1.2%
17
Epidemiology and Infection
◐ 89 papers in training set
Top 2%
1.1%
18
npj Digital Medicine
○ 118 papers in training set
Top 3%
1.1%
19
JAMIA Open
◐ 42 papers in training set
Top 1%
1.0%
20
Journal of The Royal Society Interface
● 235 papers in training set
Top 3%
1.0%
21
Biology Methods and Protocols
◐ 61 papers in training set
Top 2%
1.0%
22
Applied Sciences
○ 25 papers in training set
Top 0.8%
0.9%
23
Journal of Clinical Medicine
○ 97 papers in training set
Top 4%
0.9%
24
JMIR mHealth and uHealth
◐ 11 papers in training set
Top 0.3%
0.6%
25
BMC Medical Research Methodology
○ 47 papers in training set
Top 1%
0.6%
26
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 6%
0.6%
27
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
● 12 papers in training set
Top 0.2%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.