MEDICAL INFORMATION PROCESSING APPARATUS, MEDICAL INFORMATION PROCESSING METHOD AND NON-TRANSITORY COMPUTER-READABLE MEDIUM
According to one embodiment, a medical information processing apparatus includes processing circuitry. The processing circuitry acquires patient information relating to a target patient, environment information relating to an environment for execution, and target data relating to the target patient. processing circuitry determines, from a plurality of trained models differing from each other in processing speed and accuracy, a combination of trained models that satisfies a condition according to the patient information and the environment information.
1 . A medical information processing apparatus comprising processing circuitry configured to:
acquire patient information relating to a target patient, environment information relating to an environment for execution, and target data relating to the target patient; and
determine, from a plurality of trained models differing from each other in processing speed and accuracy, a combination of trained models that satisfies a condition according to the patient information and the environment information.
2 . The medical information processing apparatus according to claim 1 , wherein
the plurality of trained models are prepared for each of one or more analytical processing steps, and
if a task that includes a plurality of analytical processing steps is to be performed, the processing circuitry selects one trained model from the prepared plurality of trained models for each analytical processing step to determine the combination.
3 . The medical information processing apparatus according to claim 1 , wherein the processing circuitry determines the combination based on whether to prioritize the processing speed or the accuracy.
4 . The medical information processing apparatus according to claim 1 , wherein
the patient information includes vital information of the target patient, and
the environment information includes at least one of a system environment for executing a trained model or a scale of a hospital.
5 . The medical information processing apparatus according to claim 1 , wherein the processing circuitry is further configured to display information relating to an analytical processing step in progress.
6 . The medical information processing apparatus according to claim 5 , wherein the processing circuitry is further configured to display information of a selected trained model for each analytical processing step.
7 . The medical information processing apparatus according to claim 5 , wherein the processing circuitry is further configured to calculate a processing time and estimation accuracy that are assumed for the trained model,
wherein the processing circuitry displays the trained model and at least one of the processing time or the estimation accuracy in such manner that the trained model is associated with the at least one of the processing time or the estimation accuracy.
8 . The medical information processing apparatus according to claim 1 , wherein the processing circuitry is further configured to:
train a network model using, as input data, information regarding the trained models included in the combination, the patient information, the environment information, and the target data, and using, as ground truth data, feedback information relating to feedback from a user on at least one of a state during execution of an analytical processing step using the combination, or an analysis result; and
generate a trained set model.
9 . The medical information processing apparatus according to claim 8 , wherein the processing circuitry is further configured to input the patient information, the environment information, and the target data, to the trained set model and thereby output the combination of trained models.
10 . A medical information processing method, comprising:
acquiring patient information relating to a target patient, environment information relating to an environment for execution, and target data relating to the target patient; and
determining, from a plurality of trained models differing from each other in processing speed and accuracy, a combination of trained models that satisfies a condition according to the patient information and the environment information.
11 . A non-transitory computer-readable medium having recorded thereon a plurality of computer-executable instructions that cause the computer to execute the steps of:
acquiring patient information relating to a target patient, environment information relating to an environment for execution, and target data relating to the target patient; and
determining, from a plurality of trained models differing from each other in processing speed and accuracy, a combination of trained models that satisfies a condition according to the patient information and the environment information.