Abstract: Dual machine translators are trained by generating a translated medical image by operation of an illustrative model on an original medical record, generating information based on whether the translated medical image is natural in a modality of medical imaging, producing a back-translated medical record by operation of an interpretive model on the translated medical image, calculating a reward by comparing the back-translated medical record to the original medical record, updating parameters of the illustrative model in response to the information and the reward, and updating parameters of the interpretive model in response to the reward.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate a transformation of a model of an entity by a model of a plurality of entities are provided. According to an embodiment, a computer-implemented method can comprise identifying a plurality of parameters of a model of a plurality of entities; generating a model of an entity based on collected data of an operation of the entity, wherein the model of the entity comprises a subset of the plurality of parameters; and transforming the model of the entity based the model of the plurality of entities such that a first result from the model of the plurality of entities and a second result from the model of the entity have a relationship that satisfies a defined criterion, given same values used for the subset of the plurality of parameters.

Abstract: Mechanisms are provided for training a hybrid machine learning (ML) computer model to simulate a biophysical system of a patient and predict patient classifications based on results of simulating the biophysical system. A mechanistic model is executed to generate a training dataset. A surrogate ML model is trained to replicate logic of the mechanistic computer model and generate patient feature outputs based on surrogate ML model input parameters. A transformation ML model is trained to transform patient feature outputs of the surrogate ML model into a distribution of patient features. A generative ML model is trained to encode samples from a uniform distribution of input patient data into mechanistic model parameter inputs that are coherent to the target distribution of patient features and are input to the surrogate ML model. Input patient data for a patient is processed through the ML models to predict a patient classification for the patient.

Abstract: Embodiments of the present invention are directed to a systems and methods for registration of pulse wave signal and determining arterial pressure. A non-limiting example of the system includes a strain gauge sensor. A non-limiting example of the method includes receiving, to a processor, a first pressure pulse signal from a first strain gauge sensor. The method also includes receiving, to the processor, a second pressure pulse signal from a second strain gauge sensor. The method also includes determining a pulse transit time between the first strain gauge sensor and the second strain gauge sensor based at least in part upon the first pressure pulse signal and the second pressure pulse signal. The method also includes determining an arterial pressure based at least in part upon the pulse transit time.

Abstract: Dual machine translators are trained by generating a translated medical image by operation of an illustrative model on an original medical record, generating information based on whether the translated medical image is natural in a modality of medical imaging, producing a back-translated medical record by operation of an interpretive model on the translated medical image, calculating a reward by comparing the back-translated medical record to the original medical record, updating parameters of the illustrative model in response to the information and the reward, and updating parameters of the interpretive model in response to the reward.

Abstract: Mechanisms are provided for training a hybrid machine learning (ML) computer model to simulate a biophysical system of a patient and predict patient classifications based on results of simulating the biophysical system. A mechanistic model is executed to generate a training dataset. A surrogate ML model is trained to replicate logic of the mechanistic computer model and generate patient feature outputs based on surrogate ML model input parameters. A transformation ML model is trained to transform patient feature outputs of the surrogate ML model into a distribution of patient features. A generative ML model is trained to encode samples from a uniform distribution of input patient data into mechanistic model parameter inputs that are coherent to the target distribution of patient features and are input to the surrogate ML model. Input patient data for a patient is processed through the ML models to predict a patient classification for the patient.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate a transformation of a model of an entity by a model of a plurality of entities are provided. According to an embodiment, a computer-implemented method can comprise identifying a plurality of parameters of a model of a plurality of entities; generating a model of an entity based on collected data of an operation of the entity, wherein the model of the entity comprises a subset of the plurality of parameters; and transforming the model of the entity based the model of the plurality of entities such that a first result from the model of the plurality of entities and a second result from the model of the entity have a relationship that satisfies a defined criterion, given same values used for the subset of the plurality of parameters.

Abstract: Embodiments of the present invention are directed to a systems and methods for registration of pulse wave signal and determining arterial pressure. A non-limiting example of the system includes a strain gauge sensor. A non-limiting example of the method includes receiving, to a processor, a first pressure pulse signal from a first strain gauge sensor. The method also includes receiving, to the processor, a second pressure pulse signal from a second strain gauge sensor. The method also includes determining a pulse transit time between the first strain gauge sensor and the second strain gauge sensor based at least in part upon the first pressure pulse signal and the second pressure pulse signal. The method also includes determining an arterial pressure based at least in part upon the pulse transit time.