Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating waveforms conditioned on phoneme sequences. In one aspect, a method comprises: obtaining a phoneme sequence; processing the phoneme sequence using an encoder neural network to generate a hidden representation of the phoneme sequence; generating, from the hidden representation, a conditioning input; initializing a current waveform output; and generating a final waveform output that defines an utterance of the phoneme sequence by a speaker by updating the current waveform output at each of a plurality of iterations, wherein each iteration corresponds to a respective noise level, and wherein the updating comprises, at each iteration: processing (i) the current waveform output and (ii) the conditioning input using a noise estimation neural network to generate a noise output; and updating the current waveform output using the noise output and the noise level for the iteration.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a sequence generation neural network. One of the methods includes obtaining a batch of training examples; for each of the training examples: processing the training network input in the training example using the neural network to generate an output sequence; for each particular output position in the output sequence: identifying a prefix that includes the system outputs at positions before the particular output position in the output sequence, for each possible system output in the vocabulary, determining a highest quality score that can be assigned to any candidate output sequence that includes the prefix followed by the possible system output, and determining an update to the current values of the network parameters that increases a likelihood that the neural network generates a system output at the position that has a high quality score.

Abstract: In clinical documentation, mere documentation of a condition in a patient's records may not be enough. To be considered sufficiently documented, the patient's record needs to show that no documentation drop-offs (DDOs) have occurred over the course of the patient's stay. However, DDOs can be extremely difficult to detect. To solve this problem, the invention trains time-sensitive deep learning (DL) models on a per condition basis using actual and/or synthetic patient data. Utilizing an ontology, grouped concepts can be generated on the fly from real-time hospital data and used to generate time-series data that can then be analyzed by trained time-sensitive DL models to determine whether a DDO for a condition has occurred during the stay. Non-time-sensitive models can be used to detect all the conditions documented during the stay. Outcomes from the models can be compared to determine whether to notify a user that a DDO has occurred.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.

Abstract: A method includes receiving training data comprising a plurality of pairs of images. Each pair comprises a noisy image and a denoised version of the noisy image. The method also includes training a multi-task diffusion model to perform a plurality of image-to-image translation tasks, wherein the training comprises iteratively generating a forward diffusion process by predicting, at each iteration in a sequence of iterations and based on a current noisy estimate of the denoised version of the noisy image, noise data for a next noisy estimate of the denoised version of the noisy image, updating, at each iteration, the current noisy estimate to the next noisy estimate by combining the current noisy estimate with the predicted noise data, and determining a reverse diffusion process by inverting the forward diffusion process to predict the denoised version of the noisy image. The method additionally includes providing the trained diffusion model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sequence modeling. One of the methods includes receiving an input sequence having a plurality of input positions; determining a plurality of blocks of consecutive input positions; processing the input sequence using a neural network to generate a latent alignment, comprising, at each of a plurality of input time steps: receiving a partial latent alignment from a previous input time step; selecting an input position in each block, wherein the token at the selected input position of the partial latent alignment in each block is a mask token; and processing the partial latent alignment and the input sequence using the neural network to generate a new latent alignment, wherein the new latent alignment comprises, at the selected input position in each block, an output token or a blank token; and generating, using the latent alignment, an output sequence.

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

Abstract: In clinical documentation, mere documentation of a condition in a patient's records may not be enough. To be considered sufficiently documented, the patient's record needs to show that no documentation drop-offs (DDOs) have occurred over the course of the patient's stay. However, DDOs can be extremely difficult to detect. To solve this problem, the invention trains time-sensitive deep learning (DL) models on a per condition basis using actual and/or synthetic patient data. Utilizing an ontology, grouped concepts can be generated on the fly from real-time hospital data and used to generate time-series data that can then be analyzed by trained time-sensitive DL models to determine whether a DDO for a condition has occurred during the stay. Non-time-sensitive models can be used to detect all the conditions documented during the stay. Outcomes from the models can be compared to determine whether to notify a user that a DDO has occurred.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating network outputs using insertion operations.

Abstract: A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

Abstract: A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

Abstract: A patient case may be evaluated whenever new information is received or as scheduled. Evaluation may include resolving a Diagnosis-Related Group (DRG) code and determining a CDI scoring approach based at least in part on a result from the resolving. Resolving a DRG code may include determining whether a DRG code is associated with the patient case. If no DRG code is found, the system may search for an International Classification of Diseases code or ask a user to select or assign a DRG code. Using the determined CDI scoring approach, a first score may be generated and adjusted by at least one of length of stay, documentation accuracy, payer, patient location, documentation novelty, review timing, case size, or documentation sufficiency. The adjusted score may be normalized and presented to a CDI specialist, perhaps with multiple CDI scores in a sorted order.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.

Abstract: A patient case may be evaluated whenever new information is received or as scheduled. Evaluation may include resolving a Diagnosis-Related Group (DRG) code and determining a CDI scoring approach based at least in part on a result from the resolving. Resolving a DRG code may include determining whether a DRG code is associated with the patient case. If no DRG code is found, the system may search for an International Classification of Diseases code or ask a user to select or assign a DRG code. Using the determined CDI scoring approach, a first score may be generated and adjusted by at least one of length of stay, documentation accuracy, payer, patient location, documentation novelty, review timing, case size, or documentation sufficiency. The adjusted score may be normalized and presented to a CDI specialist, perhaps with multiple CDI scores in a sorted order.

Abstract: A computer-implemented method for training a neural network that is configured to generate a score distribution over a set of multiple output positions. The neural network is configured to process a network input to generate a respective score distribution for each of a plurality of output positions including a respective score for each token in a predetermined set of tokens that includes n-grams of multiple different sizes. Example methods described herein provide trained neural networks which produce results with improved accuracy compared to the state of the art, e.g. translations that are more accurate compared to the state of the art, or more accurate speech recognition compared to the state of the art.

Abstract: A building management system including a local power system that delivers power to devices at a location, a data collector system coupled to the local power system, to monitor aggregate power used at a location, including at least one circuit based sensor configured to collect power usage data, each of the at least one sensors being clamped onto a circuit basis, and a data transmitter coupled to the at least one sensor and communicating the collected power usage data over a network to a cloud analyzer system, a tracker application configured to provide real-time reporting, alerts, and control via the network, and to be executed by a processor in an operating system (OS), in a native or virtual environment, wherein the tracker interacts with an analysis engine to map out energy use inside of a building on an individual circuit basis.