Methods and systems for detecting patient characteristics in an infant care station
AssigneeGE Precision Healthcare LLC
InventorsMohammad Khair, Kalaivani Manickam, Steven M. Falk, Nagapriya Kavoori Sethumadhavan, Rajendra Naik
Life of this patent
Estimating the term…
Abstract
In one example, an infant care station can include a camera for capturing video data and a processor configured to execute instructions that can obtain the video data from the camera for a patient. The processor can also generate a point cloud based on the video data and train, using the point cloud as input, a first set of artificial intelligence instructions to detect one or more patient characteristics. Additionally, the processor can generate an output representing the one or more patient characteristics based on the first set of artificial intelligence instructions.
Claims20
An infant care station comprising:
- a camera for capturing video data;
- and
- a processor configured to execute instructions to:
- obtain the video data from the camera for a patient;
- generate a point cloud based on the video data, the point cloud defines discrete data points in XYZ vertices that are usable as a finite element model to estimate a body volume and a body surface area of the patient;
- train, using the point cloud as input, a first set of artificial intelligence instructions to detect one or more patient characteristics;
- and
- generate an output representing the one or more patient characteristics based on the first set of artificial intelligence instructions.
A method comprising:
- obtaining video data from a camera for a patient in an infant care station;
- generating a point cloud based on the video data, the point cloud defines discrete data points in XYZ vertices that are usable as a finite element model to estimate a body volume and a body surface area of the patient;
- training, using the point cloud as input, a first set of artificial intelligence instructions to detect one or more patient characteristics, wherein the one or more patient characteristics comprises a body length, a head circumference, a body joint segment length, a body volume, a body surface area, or a body density of the patient;
- and
- generating an output representing the one or more patient characteristics based on the first set of artificial intelligence instructions.
A non-transitory computer-readable media comprising a plurality of instructions that, in response to execution by a processor, cause the processor to:
- obtain video data from a camera for a patient;
- generate a point cloud based on the video data, the point cloud defines discrete data points in XYZ vertices that are usable as a finite element model to estimate a body volume and a body surface area of the patient;
- train, using the point cloud as input, a first set of artificial intelligence instructions to detect one or more patient characteristics;
- generate an output representing the one or more patient characteristics based on the first set of artificial intelligence instructions;
- and
- provide a positive stimulus to the patient in response to detecting a negative stimulus based at least in part on the one or more patient characteristics, the positive stimulus comprising vestibular, somatosensory, tactile, or auditory stimuli.
Dependencies are inferred from the claim text.