Our technology

Innodem has developed a digital biomarker platform that uses eye-tracking technology to measure various aspects of brain health. The patented AI technology is embodied in two parts: the front-end App that works on an iPad Pro connected to a secure cloud-based back end.  The platform does not require any special equipment or training. Pending regulatory approval, the platform’s goal is to assist clinicians in monitoring disease status and progression so that patients living with neurodegenerative & mental disorders such as multiple sclerosis, Alzheimer’s disease and Parkinson’s disease can receive the right available treatment at the right time for better patient outcomes.

While traditional assessment methods rely heavily on subjective observations or specialized clinical tests and brain imaging, which are costly and time consuming and may lack precision and fail to capture subtle changes in disease progression, Innodem’s novel solution can offer a depth of insight and granularity previously unattainable, enabling a more nuanced understanding of individual disease trajectories and treatment responses. By harnessing this wealth of data, pharmaceutical interventions can transcend the one-size-fits-all approach, paving the way for personalized therapies tailored to each patient's unique treatment responses and disease manifestations.

Our technology is composed of two families of patents. The first one is our core technology i.e., eye tracking software technology that determines gaze positions of eyes using front-facing cameras of mobile devices in visible light.


US Patents 10713813, 10713814, 11074714, 11644898 Eye tracking method and system


A method for training a neural network for determining a gaze position of at least one eye in an initial image comprising the at least one eye. A plurality of training initial images is obtained, of which at least one training color component image is extracted, each of the training initial images respectively comprising at least one eye and a known gaze position. Those are fed into a neural network outputting a respective internal representation for each one of the at least one component image. The neural network is trained by readjusting weights in the neural network to have the respective internal representation for each one of the at least one training color component image more consistent with a respective one of the known gaze position. Once trained, the neural network is used to determine the estimated gaze position relative to a screen of an electronic device.

The second family of patents is the application of the core technology towards the detection of specific eye movement abnormalities associated with various neurological diseases.

US Patent 11503998: Method and a system for detection of eye gaze-pattern abnormalities and related neurological diseases


A method for detecting a neurological disease, the method comprising: performing a set of tasks, each task being distinct from each other and corresponding to a distinct set of features for the task, the set of tasks having a calibration task, a smooth pursuit task, an anti-saccade task and at least one of a fixation task and a pro-saccade task, wherein performing a set of tasks comprises displaying stimulus videos on a screen of an electronic device and simultaneously filming with a camera of the electronic device, the camera located in proximity to the screen, to generate a video of a user's face for each one of the stimulus videos, each one of the stimulus videos corresponding to a task of the set of tasks, a stimulus video for the smooth pursuit task comprising displaying a target in a sequence on the screen following a predetermined continuous path and the target appearing moving at a constant speed towards and from one of four extremes of the screen, prompting the user to deliberately follow the movement of the target on the screen during the smooth pursuit task, the stimulus video for the smooth pursuit task being configured for extraction of the distinct set of features for the smooth pursuit task, and a stimulus video for the anti-saccade task comprising displaying another target in a center of the screen during a fixation period followed by displaying a blank screen and then by displaying a symbol at another location on the screen during a stimulus period, the symbol pointing to a first direction, and then by displaying the symbol on the screen together with three other symbols, each one of the three other symbols pointing to a direction other than the first direction, and prompting the user to identify where the symbol pointed to during the stimulus period; providing a machine learning model for gaze predictions; based on the generated videos for the tasks and using the machine learning model, generating the gaze predictions for each video frame of each video of the user's face for each task; based on the generated gaze predictions for each video frame of each video of the user's face for each task, determining values of the set of features for each task; and based on the values of the set of features determined for each task, detecting the neurological disease using a pre-trained machine learning model.

Artificial Intelligence

Our ongoing pipeline of clinical trials is providing precious data from well phenotyped patients. This data enables our software engineering teams to develop and train various machine learning algorithms to attempt in predicting disease status and progression accurately (the goal is to be at a level equivalent to a specialized certified clinician).