A video is segmented into a plurality of sequences corresponding to different facial states performed by a patient in the video. For each sequence, displacement of a plurality of groups of landmarks of a face of the patient is tracked, to obtain, for each group of the plurality of groups, one or more displacement measures characterizing positions of the landmarks of the group. The one or more displacement measures corresponding to each group are provided into a corresponding neural network, to obtain a landmark feature. The neural networks corresponding to each group are different from one another. A sequence score for the sequence is determined based on a plurality of landmark features corresponding to the groups. A plurality of sequence scores are provided into a machine learning component, to obtain a patient score. A disease state of the patient is determined based on the patient score.
A computer-implemented method includes obtaining a video of a subject, the video including a plurality of frames; generating, based on the plurality of frames, a plurality of optical flows; and encoding the plurality of optical flows using an autoencoder to obtain a movement-based biomarker value of the subject.
An apparatus for monitoring changes in symptoms of a patient is described. The apparatus includes a display for displaying information to a patient; a processing system configured to output to the display at least one of audio, video or both audio and video stimuli for eliciting a reaction in the patient; an audio and video capture device for capturing audio, video or both audio and video recordings of the patient performing an action as the stimuli is output by the display; a computer vision processor configured to determine from the audio, video or both audio and video recordings, one or more reactions of the patient in response to the stimuli and during a first period of time immediately after presentation of the stimuli to the patient, wherein the first period of time is less than 250 milliseconds.
A system and method for monitoring the state of an individual. The method includes providing a stimulus to the individual, measuring a response to the provided stimulus, comparing the measured response to an expected response, and diagnosing one or more aspects of disease in accordance with the result of the comparison between the measured response and the expected response. The stimulus may be a predetermined test sequence, such as a visually displayed predetermined sequence of images, or may include observation of the physical response of the individual while performing one or more predetermined activities. Stored images or video of the individual responding to one or more test sequences may be stored in a lossy or lossless state, and thus security and de-identification may be provided to stored data. This stored data may also be de-identified in a manner to allow for the answering of the greatest number of future questions.
A61B 3/113 - Objective types, i.e. instruments for examining the eyes independent of the patients perceptions or reactions for determining or recording eye movement
A61J 1/00 - Containers specially adapted for medical or pharmaceutical purposes
G06F 19/00 - Digital computing or data processing equipment or methods, specially adapted for specific applications (specially adapted for specific functions G06F 17/00;data processing systems or methods specially adapted for administrative, commercial, financial, managerial, supervisory or forecasting purposes G06Q;healthcare informatics G16H)
A system and method for training a system for monitoring administration of medication. The method includes the steps of a method for training a medication administration monitoring apparatus, comprising the steps of defining one or more predetermined medications and then acquiring information from one or more data sources of a user administering medication. A first network is trained to recognize a first step of a medication administration sequence, and then a second network is trained to recognize a second step of a medication administration sequence based upon the training of the first network.
A medication management system is described that is operable to determine whether a user is actually following a protocol, provide additional assistance to a user, starting with instructions, video instructions, and the like, and moving up to contact from a medication administrator if it is determined that the user would need such assistance in any medical adherence situation, including clinical trial settings, home care settings, healthcare administration locations, such as nursing homes, clinics, hospitals and the like. Suspicious activity on the part of a patient or other user of the system is identified and can be noted to a healthcare provider or other service provider where appropriate.
G06F 19/00 - Digital computing or data processing equipment or methods, specially adapted for specific applications (specially adapted for specific functions G06F 17/00;data processing systems or methods specially adapted for administrative, commercial, financial, managerial, supervisory or forecasting purposes G06Q;healthcare informatics G16H)