Machine Learning for Improved Diagnostics

The diagnosis and management of chronic disease is a significant challenge and burden to healthcare systems globally.EVs are an ideal diagnostic target because they are continuously released from cells and contain many different disease-specific biomarkers such as mRNA, miRNA, and proteins. EVs have been found in nearly all biological fluids including blood, urine, semen, and cerebrospinal fluid, making them promising targets for minimally-invasive diagnostic assays.

The ability to detect and measure extracellular vesicles is transforming the diagnostic landscape in a variety of fields such as immunology, neurology, cardiology, and oncology. Levels of disease-specific EVs, including exosomes, microvesicles, apoptotic bodies, and very large oncosomes are closely related to the progression of disease.

At Nanostics, we use micro-flow cytometry (µFCM) to characterize the optical properties of particles, allowing quantification of particle size, concentration, and marker abundance for millions of EVs in minutes. To accurately interpret the vast amount of information generated using µFCM technology, we use an advanced machine learning approach that provides a rapid and precise result that continuously improves with every test.

Altogether, the µFCM characterization and advanced machine learning analysis of EVs from bodily fluids makes up the EVMAP to predict disease.

The Nanostics ClarityDX platform for EV detection and analysis is set to transform the diagnostic landscape and make easy-to-use, non-invasive diagnosis of disease a reality in the near future.


Extracellular Vesicle Analysis
Machine Learning – Prediction Algorithms

Nanostics uses EVMAP to predict disease