Abstract: Techniques are described for training and/or utilizing sub-agent machine learning models to generate candidate dialog responses. In various implementations, a user-facing dialog agent (202, 302), or another component on its behalf, selects one of the candidate responses which is closest to user defined global priority objectives (318). Global priority objectives can include values (306) for a variety of dialog features such as emotion, confusion, objective-relatedness, personality, verbosity, etc. In various implementations, each machine learning model includes an encoder portion and a decoder portion. Each encoder portion and decoder portion can be a recurrent neural network (RNN) model, such as a RNN model that includes at least one memory layer, such as a long short-term memory (LSTM) layer.

Abstract: A method (100) for generating a textual description of a medical image, comprising: receiving (130) a medical image of an anatomical region, the image comprising one or more abnormalities; segmenting (140) the anatomical region in the received medical image from a remainder of the image; identifying (150) at least one of the one or more abnormalities in the segmented anatomical region; extracting (160) one or more features from the identified abnormality; generating (170), using the extracted features and a trained text generation model, a textual description of the identified abnormality; and reporting (180), via a user interface of the system, the generated textual description of the identified abnormality.

Abstract: Techniques are described for training and/or utilizing sub-agent machine learning models to generate candidate dialog responses. In various implementations, a user-facing dialog agent (202, 302), or another component on its behalf, selects one of the candidate responses which is closest to user defined global priority objectives (318). Global priority objectives can include values (306) for a variety of dialog features such as emotion, confusion, objective-relatedness, personality, verbosity, etc. In various implementations, each machine learning model includes an encoder portion and a decoder portion. Each encoder portion and decoder portion can be a recurrent neural network (RNN) model, such as a RNN model that includes at least one memory layer, such as a long short-term memory (LSTM) layer.

Abstract: A method (100) for generating a textual description of a medical image, comprising: receiving (130) a medical image of an anatomical region, the image comprising one or more abnormalities; segmenting (140) the anatomical region in the received medical image from a remainder of the image; identifying (150) at least one of the one or more abnormalities in the segmented anatomical region; extracting (160) one or more features from the identified abnormality; generating (170), using the extracted features and a trained text generation model, a textual description of the identified abnormality; and reporting (180), via a user interface of the system, the generated textual description of the identified abnormality.

Abstract: A system (1000) for automated question answering, including: semantic space (210) generated from a corpus of questions and answers; a user interface (1030) configured to receive a question; and a processor (1100) comprising: (i) a question decomposition engine (1050) configured to decompose the question into a domain, a keyword, and a focus word; (ii) a question similarity generator (1060) configured to identify one or more questions in a semantic space using the decomposed question; (iii) an answer extraction and ranking engine (1080) configured to: extract, from the semantic space, answers associated with the one or more identified questions; and identify one or more of the extracted answers as a best answer; and (iv) an answer tuning engine (1090) configured to fine-tune the identified best answer using one or more of the domain, keyword, and focus word; wherein the fine-tuned answer is provided to the user via the user interface.

Abstract: A method for determining the answer to a query in a document, including: encoding, by an encoder, the query and the document; generating a query-aware context encodings G by a bidirectional attention system using the encoded query and the encoded document; performing a hierarchical self-attention on the query aware document by a hierarchical self-attention system by applying a word to word attention and a word to sentence attention mechanism resulting in a matrix M; and determining the starting word and the ending word of the answer in the document by a span detector based upon the matrix M.

Abstract: Techniques are described herein for training and applying memory neural networks, such as “condensed” memory neural networks (“C-MemNN”) and/or “average” memory neural networks (“A-MemNN”). In various embodiments, the memory neural networks may be iteratively trained using training data in the form of free form clinical notes and clinical reference documents. In various embodiments, during each iteration of the training, a so-called “condensed” memory state may be generated and used as part of the next iteration. Once trained, a free form clinical note associated with a patient may be applied as input across the memory neural network to predict one or more diagnoses or outcomes of the patient.

Abstract: Techniques are described herein for drawing conclusions using free form texts and external resources. In various embodiments, free form input data (202) may be segmented (504) into a plurality of input data segments. A first input data segment may be compared (510) with an external resource (304) to identify a first candidate conclusion. A reinforcement learning trained agent (310) may be applied (512) to make a first determination of whether to accept or reject the first candidate conclusion. Similar actions may be performed with a second input data segment to make a second determination of whether to accept or reject a second candidate conclusion. A final conclusion may be presented (522) based on the first and second determinations of the reinforcement learning trained agent with respect to at least the first candidate conclusion and the second candidate conclusion.

Abstract: The described embodiments relate to systems, methods, and apparatus for providing a multimodal deep memory network (200) capable of generating patient diagnoses (222). The multimodal deep memory network can employ different neural networks, such as a recurrent neural network and a convolution neural network, for creating embeddings (204, 214, 216) from medical images (212) and electronic health records (206). Connections between the input embeddings (204) and diagnoses embeddings (222) can be based on an amount of attention that was given to the images and electronic health records when creating a particular diagnosis. For instance, the amount of attention can be characterized by data (110) that is generated based on sensors that monitor eye movements of clinicians observing the medical images and electronic health records.

Abstract: Techniques are described herein for training and applying memory neural networks, such as “condensed” memory neural networks (“C-MemNN”) and/or “average” memory neural networks (“A-MemNN”). In various embodiments, the memory neural networks may be iteratively trained using training data in the form of free form clinical notes and clinical reference documents. In various embodiments, during each iteration of the training, a so-called “condensed” memory state may be generated and used as part of the next iteration. Once trained, a free form clinical note associated with a patient may be applied as input across the memory neural network to predict one or more diagnoses or outcomes of the patient.

Abstract: The present disclosure relates to preserving context in a conversation between a user (101) and a digital assistant device (102). During training, the digital assistant device (102) is provided with a plurality of conversations having a plurality of dialogues. Each of the plurality of dialogue is assigned an ID based on a context. Further, two or more test queries having a same context is provided as input and the two are more queries are assigned an ID based on the context. Thereafter, the digital assistant device (102) is configured to retrieve one or more dialogues from the plurality of dialogues where the ID of the one or more dialogues match the ID of the two or more queries. In real-time, one or more queries are received and based on a context of the one or more queries, one or more dialogues are retrieved and are provided to the user.

Abstract: A medical information retrieval system comprises a natural language processing system that processes a vocal user query to identify key words and phrases. These key words and phrases are provided to an inferencing engine that provides a set of knowledge-based inferences from medical knowledge sources, based on these key words and phrases. Thereafter, these knowledge-based inferences are provided to an information retrieval engine that retrieves a corresponding plurality of medical articles based on these knowledge-based inferences, and ranks each with respect to the knowledge-based inferences. A summary engine receives the ranked articles and creates a model based on the topical keywords and candidate sentences found in the highly ranked articles. A paraphrase engine processes the candidate sentences to provide a summary response based on a knowledge-based paraphrase model. An audio output device renders the summary report as the response to the user's original vocal query.

Abstract: Techniques described herein relate to semi-supervised training and application of stacked autoencoders and other classifiers for predictive and other purposes. In various embodiments, a semi-supervised model (108) may be trained for sentence classification, and may combine what is referred to herein as a “residual stacked de-noising autoencoder” (“RSDA”) (220), which may be unsupervised, with a supervised classifier (218) such as a classification neural network (e.g., a multilayer perceptron, or “MLP”). In various embodiments, the RSDA may be a stacked denoising autoencoder that may or may not include one or more residual connections. If present, the residual connections may help the RSDA “remember” forgotten information across multiple layers. In various embodiments, the semi-supervised model may be trained with unlabeled data (for the RSDA) and labeled data (for the classifier) simultaneously.

Abstract: Instructions (108) cause a processor (104) to: classify a clinical report for a subject under evaluation by one of anatomical organ or disease; identify and retrieve clinical reports for the same subject from the healthcare data source(s); group the retrieved clinical report by one of anatomical organ or disease; select a group of the clinical report, wherein the group includes reports for a same or related one of the anatomical organ or the disease; build a model that predicts semantic relationships between nodes in the reports in the selected group of reports based on one or more of extracted parameters or keywords; compare one of the parameter values or the keywords across the reports using the model; construct a graphical timeline of the reports; highlight differences in the parameter values or the keywords based on a result of the compare; and visually present the graphical timeline with the highlighted differences.

Abstract: Methods and systems for generating text from a haptic-based input. The system may include an interface for receiving a haptic-based input and a processor executing instructions stored on a memory and providing a model. The model is configured to at least receive the haptic-based input and supply a text describing the haptic-based input using the interface.

Abstract: Embodiments of present disclosure disclose method and system for generating a medical image based on a textual data in a medical report. For generation, a textual data from each of one or more medical reports of the patient is retrieved. The textual data comprises one or more medical events and corresponding one or more attributes associated with each of the one or more medical reports. Further, a matching score for each of plurality of reference images is computed based on the textual data, using a first machine learning model. Upon computing the matching score, one or more images are selected from the plurality of reference images based on the matching score associated with each of the plurality of reference images. The medical image for the patient is generated based on the one or more images and the textual data using a second machine learning model.

Abstract: Techniques are provided for generating and applying a granular attention hierarchical neural network model to classify a document. In various embodiments, data indicative of the document may be obtained (102) and processed (104) into a first layer of two or more layers of a hierarchical network model using a dual granularity attention mechanism to generate first layer output data, wherein the dual granularity attention mechanism weighs some portions of the data indicative of the document more heavily. Some portions of the data indicative of the document are integrated into the hieratical network model during training of the dual granularity attention mechanism. The first layer output data may be processed (106) in the second of two or more layers of the hierarchical network model to generate second layer output data. A classification label can be generated (108) from the second layer output data.

Abstract: Techniques are described for training and/or utilizing sub-agent machine learning models to generate candidate dialog responses. In various implementations, a user-facing dialog agent (202, 302), or another component on its behalf, selects one of the candidate responses which is closest to user defined global priority objectives (318). Global priority objectives can include values (306) for a variety of dialog features such as emotion, confusion, objective-relatedness, personality, verbosity, etc. In various implementations, each machine learning model includes an encoder portion and a decoder portion. Each encoder portion and decoder portion can be a recurrent neural network (RNN) model, such as a RNN model that includes at least one memory layer, such as a long short-term memory (LSTM) layer.

Abstract: Methods and systems for generating a question from free text. The system is trained on a corpus of data and receives a tuple consisting of a paragraph (free text), a focused fact, and a question type. The system implements a language model to find the most optimal combination of words to return a question for the paragraph about the focused fact.

Abstract: Various embodiments described herein relate to a method, system, and non-transitory machine-readable medium including one or more of the following: extracting a first concept from input data presented for processing by a downstream function; identifying external data from an external resource based on the first concept; extracting a second concept from the external data; revising the first concept based on the second concept to produce a revised concept, wherein revising includes: applying a machine learning agent to determine whether to keep the first concept or adopt the second concept, and adopting the second concept in place of the first concept for use as the revised concept based on a decision by the machine learning agent to adopt the second concept; and further processing the revised concept according to the downstream function to generate an output.