Artificial Intelligence System for Determining Drug Use through Medical Imaging
AssigneeUltrasound AI, Inc.
InventorRobert S. Bunn
Life of this patent
Estimating the term…
Abstract
Systems and methods for establishing a patient's pharmaceutical use are provided. A neural network is trained on a dataset of medical images, such as ultrasound images, that are tagged with information concerning the use of the pharmaceutical by people who were imaged to produce the medical images. The trained neural network can then be provided with medical images of a patient, and the neural network can then make a determination as to the patient's pharmaceutical use.
Claims27
A system for determining pharmaceutical use of a patient, the system comprising:
- image storage configured to store a plurality of non-invasive medical images of at least one body part of the patient;
- image analysis logic comprising a trained neural network, the image analysis logic comprising:
- first logic configured to determine, based at least in part on the plurality of non-invasive medical images, whether the patient has previously used a pharmaceutical;
- and
- second logic configured to determine, based at least in part on the plurality of non-invasive medical images, whether the patient is currently utilizing the pharmaceutical;
- a user interface configured to present at least one determination selected from the group consisting of previous pharmaceutical use and current pharmaceutical use;
- and
- a processor configured to execute the image analysis logic.
A method for determining pharmaceutical use of a patient, the method comprising:
- obtaining at least one non-invasive medical image of a body part of the patient;
- providing the at least one non-invasive medical image to a trained neural network;
- and
- receiving from the trained neural network a determination regarding pharmaceutical use of the patient, the determination comprising at least one classification selected from the group consisting of no use, previous use, current use, and abuse.
A system for determining chemical-compound exposure of a patient, the system comprising:
- image storage configured to store a plurality of non-invasive medical images of at least one body part of the patient;
- image analysis logic comprising a trained neural network, the image analysis logic configured to determine, based at least in part on the plurality of non-invasive medical images, exposure of the patient to at least one chemical compound selected from the group consisting of a pharmaceutical, an environmental toxin, a vitamin, a hormone, and a carcinogen, wherein the determination comprises a compound class determined by a physiological effect visible in the non-invasive medical images;
- a user interface configured to present the determination;
- and
- a processor configured to execute the image analysis logic.
A system for determining pharmaceutical use of a patient, the system comprising:
- image storage configured to store a plurality of ultrasound images of at least one of an ovary, adnexa, uterus, cervix, or placenta of the patient;
- image analysis logic comprising a trained neural network, configured to determine, based at least in part on the plurality of ultrasound images, whether the patient has previously used a hormone pharmaceutical and whether the patient is currently utilizing the hormone pharmaceutical;
- a user interface configured to present the determinations;
- and
- a processor configured to execute the image analysis logic.
Dependencies are inferred from the claim text.