Superclass-conditional gaussian mixture model for personalized prediction on dialysis events
A computer-implemented method for model building is provided. The method includes receiving a training set of medical records and model hyperparameters. The method further includes initializing an encoder as a Dual-Channel Combiner Network (DCNN) and initialize distribution related parameters. The method also includes performing, by a hardware processor, a forward computation to (1) the DCNN to obtain the embeddings of the medical records, and (2) the distribution related parameters to obtain class probabilities. The method additionally includes checking by a convergence evaluator if the iterative optimization has converged. The method further includes performing model personalization responsive to model convergence by encoding the support data of a new patient and using the embeddings and event subtype labels to train a personalized classifier.
1 . A computer-implemented method for model building, comprising:
receiving a training set of dialysis records and model hyperparameters;
initializing an encoder, as a Dual-Channel Combiner Network (DCCN), and distribution related parameters;
building a model using a forward computation to (1) the encoder to obtain embeddings of the dialysis records by using a multilayer perceptron (MLP) of the DCCN to encode static patient profiles of the dialysis records and one or more Long Short-Term Memories (LSTMs) of the DCCN to encode temporal patient status features of the medical records, and (2) the distribution related parameters to obtain membership probabilities of a plurality of classes;
manipulating the embeddings of the dialysis records with the distribution related parameters to enable adaptation of the model to a fine-grained multi-class task;
performing iterative optimization of the model between (1) a step for obtaining posterior probabilities indicative of membership probabilities of the embeddings in one or more subclasses of each class of the plurality of classes, and (2) a step for obtaining updated encoder and distribution related model parameters while fixing one or more of the obtained posterior probabilities; and
personalizing the model responsive to convergence of the iterative optimization with a final set of updated encoder and distribution related model parameters by encoding support data of a new dialysis patient to obtain new embeddings and using the new embeddings and event subtype labels including different unstable patterns of blood pressure to train a personalized classifier for the new dialysis patient that is configured to perform the fine-grained multi-class task.
2 . The computer-implemented method of claim 1 , wherein the forward computation comprises computing a loss function with the embeddings and the membership probabilities of the plurality of classes for optimization.
3 . The computer-implemented method of claim 1 , further comprising performing model testing by encoding test data of the new dialysis patient and using the embeddings and the personalized classifier to predict event subtypes.
4 . The computer-implemented method of claim 3 , wherein the predicted event subtypes are used to support decision making for dialysis treatment planning.
5 . The computer-implemented method of claim 3 , further comprising performing a dialysis event on a patient responsive to the predicted event subtypes.
6 . The computer-implemented method of claim 1 , wherein outputs of the static channel and the temporal channel are concatenated and projected to a compact embedding used for prediction by a combination layer of the encoder.
7 . A non-transitory computer program product for model building, the non-transitory computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
receiving a training set of dialysis records and model hyperparameters;
initializing an encoder, as a Dual-Channel Combiner Network (DCCN), and distribution related parameters;
building, using a hardware processor, a model using a forward computation to (1) the encoder to obtain embeddings of the dialysis records by using a multilayer perceptron (MLP) of the DCCN to encode static patient profiles of the medical records and one or more Long Short-Term Memories (LSTMs) of the DCCN to encode temporal patient status features of the medical records, and (2) the distribution related parameters to obtain membership probabilities of a plurality of classes;
manipulating the embeddings of the dialysis records with the distribution related parameters to enable adaptation of the model to a fine-grained multi-class task;
performing iterative optimization of the model between (1) a step for obtaining posterior probabilities indicative of membership probabilities of the embeddings in one or more subclasses of each class of the plurality of classes, and (2) a step for obtaining updated encoder and distribution related model parameters while fixing one or more of the obtained posterior probabilities;
personalizing the model responsive to convergence of the iterative optimization with a final set of updated encoder and distribution related model parameters by encoding support data of a new dialysis patient to obtain new embeddings and using the new embeddings to train a personalized classifier for the new dialysis patient that is configured to perform the fine-grained multi-class task.
8 . The non-transitory computer program product of claim 7 , wherein the forward computation comprises computing a loss function with the embeddings and the membership probabilities of the plurality of classes for optimization.
9 . The non-transitory computer program product of claim 7 , further comprising performing model testing by encoding test data of the new dialysis patient and using the embeddings and the personalized classifier to predict event subtypes.
10 . The non-transitory computer program product of claim 9 , further comprising performing a dialysis event on a patient responsive to the predicted event subtypes.
11 . The non-transitory computer program product of claim 7 , wherein outputs of the static channel and the temporal channel are concatenated and projected to a compact embedding used for prediction by a combination layer of the encoder.
12 . A computer processing system for model building, comprising:
a memory device for storing program code; and
a hardware processor operatively coupled to the memory device for storing program code to
receive a training set of dialysis records and model hyperparameters;
initialize an encoder, as a Dual-Channel Combiner Network (DCCN), and distribution related parameters;
build, by the hardware processor, a model using a forward computation to (1) the encoder to obtain embeddings of the dialysis records by using a multilayer perceptron (MLP) of the DCCN to encode static patient profiles of the medical records and one or more Long Short-Term Memories (LSTMs) of the DCCN to encode temporal patient status features of the medical records, and (2) the distribution related parameters to obtain membership probabilities of a plurality of classes;
manipulate the embeddings of the dialysis records with the distribution related parameters to enable adaptation of the model to a fine-grained multi-class task;
perform iterative optimization of the model between (1) a step for obtaining posterior probabilities indicative of membership probabilities of the embeddings in one or more subclasses of each class of the plurality of classes, and (2) a step for obtaining updated encoder and distribution related model parameters while fixing one or more of the obtained posterior probabilities; and
personalize the model responsive to convergence of the iterative optimization with a final set of updated encoder and distribution related model parameters by encoding support data of a new dialysis patient to obtain new embeddings and using the new embeddings to train a personalized classifier for the new dialysis patient that is configured to perform the fine-grained multi-class task.
13 . The computer processing system of claim 12 , wherein the forward computation comprises computing a loss function with the embeddings and the membership probabilities of the plurality of classes for optimization.
14 . The computer processing system of claim 12 , wherein the processor further runs the program code to perform model testing by encoding test data of the new dialysis patient and using the embeddings and the personalized classifier to predict event subtypes.
15 . The computer processing system of claim 14 , wherein the processor further runs the program code to control performing a dialysis event on a dialysis patient responsive to the predicted event subtypes.
16 . The computer processing system of claim 12 , wherein outputs of the static channel and the temporal channel are concatenated and projected to a compact embedding used for prediction by a combination layer of the encoder.