Abstract: A method for assessing video recordings of movement disorders with privacy protection functions includes: obtaining movement disorder assessment video; performing face-swapping to the subject in the video; identifying key points in the video after face-swapping; determination of the movement feature for assisting diagnosis of diseases according to the changes of the key points with respect to recording time. The movement disorder assessment video is processed to obtain a face-swapped video, which can retain the person's facial expression while the subject has the appearance of a public figure, thereby achieving the purpose of protecting person privacy. By extracting the key points of the human body from the movement disorder assessment video, and monitoring the changes of the key points with the video progress, the movement feature related to the disease can be determined, and the quantifiable key diagnostic indicators of the disease can be obtained.

Abstract: A method for assessing video recordings of movement disorders with privacy protection functions includes: obtaining movement disorder assessment video; performing face-swapping to the subject in the video; identifying key points in the video after face-swapping; determination of the movement feature for assisting diagnosis of diseases according to the changes of the key points with respect to recording time. The movement disorder assessment video is processed to obtain a face-swapped video, which can retain the person's facial expression while the subject has the appearance of a public figure, thereby achieving the purpose of protecting person privacy. By extracting the key points of the human body from the movement disorder assessment video, and monitoring the changes of the key points with the video progress, the movement feature related to the disease can be determined, and the quantifiable key diagnostic indicators of the disease can be obtained.

Abstract: A system, method, and apparatus for identifying optimal or near optimal complex stimulation waveforms for a neurostimulator device or neuromodulation device are disclosed. An example method includes using a dueling bandits algorithm with correlation among stimulation arms to select a batch of stimulation arms for sequential application to a patient during a therapy session. Each of the stimulation arms specifies complex stimulation waveform parameter values. Feedback from applying the stimulation arms to the patient is recorded and used to update feedback reward values corresponding to at least some of the stimulation arms using a stimulation arm correlation index. A second batch of stimulations arms is selected based upon the updated feedback reward values and applied to a patient. The method is iteratively repeated over a number of therapy sessions until an optimal or near optimal batch of stimulation arms (defining complex stimulation waveforms) is determined.

Abstract: A system, method, and apparatus for identifying optimal or near optimal complex stimulation waveforms for a neurostimulator device or neuromodulation device are disclosed. An example method includes using a dueling bandits algorithm with correlation among stimulation arms to select a batch of stimulation arms for sequential application to a patient during a therapy session. Each of the stimulation arms specifies complex stimulation waveform parameter values. Feedback from applying the stimulation arms to the patient is recorded and used to update feedback reward values corresponding to at least some of the stimulation arms using a stimulation arm correlation index. A second batch of stimulations arms is selected based upon the updated feedback reward values and applied to a patient. The method is iteratively repeated over a number of therapy sessions until an optimal or near optimal batch of stimulation arms (defining complex stimulation waveforms) is determined.