Detecting pathogen exposure during the non-symptomatic incubation period using physiological data
Name
fphys-12-691074.pdf
Size
5.42 MB
Format
Adobe PDF
Checksum (MD5)
34c5fc2499a65968e3cdd207a1064bce
Author(s)
Davis, Shakti K.
Milechin, Lauren
Patel, Tejash
Hernandez, Mark
Ciccarelli, Gregory A.
Samsi, Siddharth
Hensley, Lisa
Goff, Arthur
Trefry, John
Johnston, Sara
Date Issued
September 2021
Journal
Frontiers in Physiology
Publisher
Cold Spring Harbor Laboratory
Citation
Davis, Shakti et al. "Detecting pathogen exposure during the non-symptomatic incubation period using physiological data." Frontiers in Physiology 12 (September 2021): 691074. © 2021 Davis et al.
Version
Final published version
Abstract
Early pathogen exposure detection allows better patient care and faster implementation of public health measures (patient isolation, contact tracing). Existing exposure detection most frequently relies on overt clinical symptoms, namely fever, during the infectious prodromal period. We have developed a robust machine learning based method to better detect asymptomatic states during the incubation period using subtle, sub-clinical physiological markers. Starting with high-resolution physiological waveform data from non-human primate studies of viral (Ebola, Marburg, Lassa, and Nipah viruses) and bacterial Y. pestis exposure, we processed the data to reduce short-term variability and normalize diurnal variations, then provided these to a supervised random forest classification algorithm and post-classifier declaration logic step to reduce false alarms. In most subjects detection is achieved well before the onset of fever; subject cross-validation across exposure studies (varying viruses, exposure routes, animal species, and target dose) lead to 51h mean early detection (at 0.93 area under the receiver-operating characteristic curve [AUCROC]). Evaluating the algorithm against entirely independent datasets for Lassa, Nipah, and Y. pestis exposures un-used in algorithm training and development yields a mean 51h early warning time (at AUCROC=0.95). We discuss which physiological indicators are most informative for early detection and options for extending this capability to limited datasets such as those available from wearable, non-invasive, ECG-based sensors.
MIT Department
Lincoln Laboratory
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3389/fphys.2021.691074
