CPC G16H 50/30 (2018.01) [G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/176 (2022.01)] | 21 Claims |
1. A computer-implemented method comprising:
receiving a request to predict one or more health metrics of a population associated with a location;
acquiring at least one image of the location via a network, by one or more processors;
identifying a plurality of built environment micro scale parameters associated with the location, based on analysis of pixels of the at least one image of the location using computer vision and a machine learning tool, by the one or more processors, to classify an object in the at least one image in one of a number n classes of the built environment micro scale parameters, wherein an output of the machine learning tool includes at least one n-dimensional vector, where each number in the at least one n-dimensional vector represents a probability that the object is of a certain class;
calculating, via the one or more processors, a quantitative measure of at least one predicted health metric of the population associated with the location based on a characteristic of at least one of the plurality of the identified built environment micro scale parameters associated with the location using at least one predictive equation correlating the characteristic of the identified built environment micro scale parameter with the one or more predicted health metrics; and
displaying, via the one or more processors, the at least one predicted health metric associated with the location.
|