| CPC G16H 50/20 (2018.01) [G16H 10/60 (2018.01); G16H 20/10 (2018.01); G16H 40/67 (2018.01)] | 21 Claims |
|
1. A method comprising:
receiving, by a first user device associated with a subject, a subject-specific data set corresponding to the subject, the subject-specific data set including or identifying:
a type of hemophilia;
treatment type;
demographic data; and
a photograph of a part of the subject or information derived based on the photograph of the part of the subject;
transmitting, by the first user device via a network, at least part of the subject-specific data set to a central artificial-intelligence system;
processing, by the central artificial-intelligence system, the at least part of the subject-specific data set using a classifier model to identify one or more population-level machine-learning models from among a set of population-level machine-learning models, each of the set of population-level machine-learning models including a machine-learning model trained using a training set corresponding to a set of other subjects with hemophilia;
receiving, by the first user device, one or more indications identifying one or more times at which a treatment of the treatment type was administered to the subject;
transmitting, by the first user device via the network, the one or more indications to the central artificial-intelligence system;
predicting, by the central artificial-intelligence system, a hemophilia-pertinent time course for the subject using the one or more indications and a data-processing workflow, wherein the data-processing workflow uses a population-level machine-learning model of the one or more population-level machine-learning models to predict the hemophilia-pertinent time course;
collecting sensor data using a second user device associated with the subject, wherein the second user device comprises one or more sensors selected from the group consisting of an accelerometer, a gyroscope, a GPS sensor, and a physiological sensor to collect the sensor data;
transmitting, by the second user device via the network, the sensor data to the first user device;
generating, by the first user device, a representation of the sensor data collected at the second user device associated with the subject;
transmitting, by the first user device via the network, the representation of the sensor data to the central artificial-intelligence system;
determining, by the central artificial-intelligence system based on the representation of the sensor data and the predicted hemophilia-pertinent time course, a transformed data-processing workflow, wherein the representation of the sensor data is used to infer a physical activity of the subject across a time period during which the sensor data was received or a time period ending at a time at which the sensor data was received, the transformed data-processing workflow uses another population-level machine-learning model associated with the physical activity of the one or more population-level machine-learning models to generate hemophilia-pertinent predictions for the subject;
generating, by the central artificial-intelligence system, a hemophilia-pertinent prediction for the subject using the transformed data-processing workflow;
transmitting, by the central artificial-intelligence system via the network, the hemophilia-pertinent prediction to the first user device; and
outputting, by the first user device, a result corresponding to the hemophilia-pertinent prediction.
|