Systems and methods for tremor detection and quantification

Inventors

Davis, Randall • Medlock, Catherine • Musicus, Bruce • Oppenheim, Alan V. • Penney, Dana L. • Souillard-Mandar, William A.

Assignees

Linus Health Inc

Abstract

Systems and methods are disclosed for detecting tremors in a subject. One method comprises receiving data from a digital device, the data comprising a plurality of digital device positions and a plurality of timestamps, each timestamp in the plurality of timestamps being associated with a digital device position in the plurality of digital device positions. The method further comprises determining a plurality of frequencies of hand movements of the subject based on the plurality of digital device positions and plurality of timestamps. The method further comprises determining a subportion of the data corresponding to frequencies of hand movements above a low tremor threshold, and determining a magnitude of tremors of the subject's hand based, at least in part, on the subportion of the data.

Core Innovation

A system and associated computer-implemented method detect tremors in a hand of a subject while the subject makes a drawing with a digital pen on an electronic device. The system obtains a plurality of digital pen positions at a sampling rate of at least 75 times per second during the drawing, where each digital pen position has x and y coordinates and is associated with a timestamp. The method determines a plurality of frequencies of movements based on the digital pen positions and timestamps, and determines a subportion of the data corresponding to one or more frequencies of hand movements above a low tremor frequency threshold.

Tremor magnitude is determined based, at least in part, on the selected subportion of data using filtered velocity information. The method determines a bandpass or high-pass filtered velocity signal by passing the subportion of the data through a bandpass or high-pass filter and a first derivative filter, and determines low-pass filtered velocity data. The tremor magnitude is determined based, at least in part, on portions of the bandpass or high-pass filtered velocity signal that are perpendicular to the low-pass filtered velocity data, and the sampling rate varies based on a velocity of the digital pen.

In embodiments for cognitive assessment, the analysis is further constrained to frequencies above a low tremor threshold and below a high tremor threshold, and the method determines a magnitude of tremors based, at least in part, on a normalized bandpass filtered velocity signal. The method then determines a degree of cognitive impairment based, at least in part, on the magnitude of tremors. The drawing is a clockface, and the method may further determine one or more perimeter lines in a portion of the data depicting a perimeter of the clockface and determine tremor magnitude based, at least in part, on the perimeter lines.

Claims Coverage

The independent claims cover a system, a non-transitory computer readable medium, and a computer-implemented method for detecting hand tremors using digital pen x,y position data with timestamps. Across these claims, the main inventive features include movement frequency determination from pen trajectories, selection of data above or between tremor frequency thresholds, filtered velocity-based tremor magnitude determination, normalization of filtered velocity based on expected average velocity derived from drawing time, and clockface-based drawing constraints. One independent claim extends tremor magnitude into a determination of degree of cognitive impairment.

Overall, the independent claims center on tremor detection from digital pen movement trajectories by deriving movement frequencies from x,y positions with timestamps, selecting data based on tremor-frequency thresholds, computing tremor magnitude using bandpass/high-pass filtered velocity including perpendicular components relative to low-pass velocity, optionally normalizing the bandpass velocity using expected average velocity based on drawing time, and using a clockface drawing constraint. One independent claim further uses the resulting tremor magnitude to determine a degree of cognitive impairment.

Stated Advantages

Documented Applications