Overt symptoms of many diseases often do not manifest until days after a person’s initial exposure to the causative pathogen, typically a virus or bacteria. By then, the disease may have progressed to a level at which the benefits of patient treatment are diminished, and the likelihood of pathogen exposure among a wider population is high. Doctors and public health officials would welcome warnings that enable them to begin early mitigation and containment of disease outbreaks.

Subjects with PRESAGED-enabled wearable devices could receive notifications of oncoming illnesses, such as those caused by viruses. The extra time afforded by early warning of exposure to pathogens could inform preventative measures, and could critically impact the public health response to outbreaks of diseases.

The PRE-Symptomatic AGent Exposure Detection (PRESAGED) algorithm uses real-time physiological data — such as heart electrical activity (electrocardiography, ECG), breathing rate, and temperature — to calculate the probability that a person has been exposed to a virus or bacteria. PRESAGED is designed to run on data collected from noninvasive medical sensors; for example, wearable electrocardiographs (also known as Holter monitors).

The algorithm was designed to provide both effective individual patient care resulting from early treatment, and faster, more confident implementation of public health measures, such as isolation, to improve overall population health by blunting epidemics.

Using data acquired from non-human primates, the researchers developed and tested PRESAGED for several exposure methods (intramuscular, aerosol, or intratracheal routes) to one of several viral hemorrhagic fevers, including Ebola virus, or the bacterial pathogen Y. pestis. Because PRESAGED detects a subject’s physical response to the pathogen and does not recognize biomarkers for the pathogen itself, PRESAGED currently does not differentiate or identify the viruses or bacteria.

The subjects’ physiological data were standardized to remove the effects of daily rhythms, aggregated to reduce shortterm fluctuations in data, and then provided to a supervised binary classification machine learning algorithm. The machine learning technique used can learn subtle physiological changes over time and apply them to the data analysis, thus enabling an ongoing check for signs of pathogen exposure rather than relying on a one-time “snapshot” of physiological data, such as a single blood sample analysis.

PRESAGED predicts the probability of pathogen exposure without regard to the particular pathogen, the exposure route, or pathogen dose. It has also been shown to provide early warning of exposure to entirely novel pathogens (i.e., pathogens unavailable for algorithm training), suggesting that this approach will be robust in detecting emergent diseases, such as SARS/MERS or novel flu strains, well before new training data are available.

For more information, contact the Communications and Community Outreach Office at This email address is being protected from spambots. You need JavaScript enabled to view it.; 781-981-4204.