Sight | The future of blood diagnostics is here

Combining AI and innovative hardware to deliver accurate 5-part differential CBC results in a compact analyzer

Small but powerful

OLO. Complete blood count from a fingerprick and two drops of blood

Compact, easy to use, and cost effective in low-volume settings, with 510(k) clearance for use in moderately complex labs.

Blood diagnostics, meet machine vision

Combining patented sample preparation with machine-vision detection, OLO delivers diagnostic accuracy, simplicity and reliability.

Accurate
results

Simple to
operate

Reliable

Our test kit

The testing process begins with a easy-to-follow sample preparation from either finger-prick or venous draw. Our foil-sealed kit contains everything you need.

Ready in seconds

The manual staining workflow has been replaced by a self-contained unit that is sample-ready in seconds. Just two drops of blood is all it takes. Patented technology is used to form a standardized monolayer of cells.

Self-contained
consumable

Rapid
preparation

Patented live
monolayer

Smart vision

Once inserted into the instrument, the sample is rapidly imaged using a specialized multi-channel microscope. The accuracy of the images allows Sight’s algorithms to carefully differentiate cells as well as identify various anomalies.

Rapid
scan

Rapid
preparation

Powerful analysis

The scanned images are analyzed using machine vision and AI techniques.

Sight’s advanced algorithm was first developed in 2012 to detect malaria, and the same methods have now been applied to CBC testing

Small but powerful

Sight’s algorithm analyzes characteristics like cell size, shape, and intracellular morphology. Accurate results are delivered in minutes, displayed on-screen and available for printout and mail.

Advanced
algorithm

Machine
learning

CBC
parameters

Company history

Our history
The story of OLO began five years ago with the introduction of Sight’s advanced algorithms to detect Malaria.
The innovative solution enabled quick and accurate diagnoses using digital fluorescent microscopy and computer vision algorithms.