Systems and methods configured to determine a machine-readable optical code based on screen-captured video are disclosed. Exemplary implementations may: receive, via a user interface of a client computing platform, an indication to begin a screen-captured video; initiate, based on the indication, the screen-captured video; effectuate an image decoding machine configured to parse and decode images and/or the video frames for information embedded into the images and/or the video frames to: parse the video frames for a text; for individual ones of the video frames with the text, extract embedded information from the text by performing at least optical character recognition; and decode the embedded information for metadata; and effectuate, via the user interface, presentation of information derived from the metadata.