Pose-based identification of weakness

1 . A computer-implemented method, comprising:

receiving, using at least one processor, one or more video recordings of one or more subjects;

extracting, using the at least one processor, one or more features from each of the one or more video recordings, the one or more features corresponding to one or more bodily joints of the one or more subjects;

training, using the at least one processor, one or more models based on the extracted features to identify a weakness in the one or more bodily joints; and

applying, using the at least one processor, the trained model to a first video recording in the one or more video recordings of a first subject in the one or more subjects, and determining, using the applied model, whether a weakness is present in one or more bodily joints of the first subject wherein the applying includes determining one or more spatial coordinates corresponding to a position of one or more bodily joints of the first subject;

generating, using the at least one processor, a covariance of the determined one or more spatial coordinates;

executing, using the at least one processor, one or more machine learning processes and/or one or more deep learning processes, using the generated covariance; and

determining, using the at least one processor, whether a weakness is present in one or more bodily joints of the first subject based on the executed one or more machine learning processes and/or the executed one or more deep learning processes.

2 . The method according to claim 1 , wherein the extracted one or more features correspond to one or more spatial coordinates of the one or more bodily joints.

3 . The method according to claim 1 , wherein the one or more features are extracted from a predetermined portion of the first video recording of the first subject.

4 . The method according to claim 1 , wherein the first video recording of the first subject is obtained while the first subject is positioned at rest.

5 . The method according to claim 1 , wherein a presence of a weakness is determined using the one or more spatial coordinates corresponding to the position of one or more bodily joints of the first subject.

6 . The method according to claim 1 , wherein the training includes comparing one or more spatial coordinates corresponding to a position of at least one bodily joint of the first subject to one or more spatial coordinates corresponding to a position of at least another bodily joint of the first subject.

7 . The method according to claim 6 , wherein a presence of a weakness is determined based on the comparing.

8 . The method according to claim 1 , further comprising generating one or more user interfaces displaying one or more heat maps identifying at least one of a presence and an absence of an abnormality in one or more bodily joints of the first subject.

9 . The method according to claim 8 , wherein a weakness in the one or more bodily joints of the first subject is determined based on at least one of the presence and the absence of the abnormality.

10 . The method according to claim 1 further comprising

triggering, using the at least one processor, a generation of one or more alerts based on the determining whether a weakness is present in one or more bodily joints of the first subject; and

generating, using the at least one processor, one or more user interfaces for displaying the one or more alerts.

11 . The method according to claim 1 , further comprising determining the first subject is experiencing at least one neurological event based on a determination that a weakness is present in one or more bodily joints of the first subject.

12 . The method according to claim 11 , wherein the at least one neurological event includes an acute stroke, an ischemic stroke, a hemorrhagic stroke, a transient ischemic attack, a warning stroke, a mini-stroke, and/or any combination thereof.

13 . The method according to claim 1 , wherein at least one of the receiving, the extracting, the training, and the applying is performed in substantially real time.

14 . A system comprising:

at least one programmable processor; and

a non-transitory machine-readable medium storing instructions that, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

receiving, using at least one processor, one or more video recordings of one or more subjects;

extracting, using the at least one processor, one or more features from each of the one or more video recordings, the one or more features corresponding to one or more bodily joints of the one or more subjects;

training, using the at least one processor, one or more models based on the extracted features to identify a weakness in the one or more bodily joints; and

applying, using the at least one processor, the trained model to a first video recording in the one or more video recordings of a first subject in the one or more subjects, and determining, using the applied model, whether a weakness is present in one or more bodily joints of the first subject, wherein the applying includes determining one or more spatial coordinates corresponding to a position of one or more bodily joints of the first subject;

generating, using the at least one processor, a covariance of the determined one or more spatial coordinates;

executing, using the at least one processor, one or more machine learning processes and/or one or more deep learning processes, using the generated covariance; and

determining, using the at least one processor, whether a weakness is present in one or more bodily joints of the first subject based on the executed one or more machine learning processes and/or the executed one or more deep learning processes.

15 . The system according to claim 14 , wherein the extracted one or more features correspond to one or more spatial coordinates of the one or more bodily joints.

16 . The system according to claim 14 , wherein the one or more features are extracted from a predetermined portion of the first video recording of the first subject.

17 . The system according to claim 14 , wherein the first video recording of the first subject is obtained while the first subject is positioned at rest.

18 . The system according to claim 14 , wherein the applying includes determining one or more spatial coordinates corresponding to a position of one or more bodily joints of the first subject.

19 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

receiving, using at least one processor, one or more video recordings of one or more subjects;

extracting, using the at least one processor, one or more features from each of the one or more video recordings, the one or more features corresponding to one or more bodily joints of the one or more subjects;

training, using the at least one processor, one or more models based on the extracted features to identify a weakness in the one or more bodily joints; and

applying, using the at least one processor, the trained model to a first video recording in the one or more video recordings of a first subject in the one or more subjects, and determining, using the applied model, whether a weakness is present in one or more bodily joints of the first subject, wherein the applying includes determining one or more spatial coordinates corresponding to a position of one or more bodily joints of the first subject;

generating, using the at least one processor, a covariance of the determined one or more spatial coordinates;

executing, using the at least one processor, one or more machine learning processes and/or one or more deep learning processes, using the generated covariance; and

determining, using the at least one processor, whether a weakness is present in one or more bodily joints of the first subject based on the executed one or more machine learning processes and/or the executed one or more deep learning processes.