Abstract: A method of assigning parent-of-origin to a haplotype, a sub-haplotype or an allele associated with a haplotype. Chromosome-length haplotypes of a genome are generated and a differential methylation status of at least one imprinted differentially methylated region (iDMR) associated with each one of the autosomal chromosomes is determined. The differential methylation status of the at least one iDMR is used to assign parent-of-origin for each one of the chromosome-length haplotypes.

Abstract: Various embodiments of the present disclosure provide machine learning model-based risk prediction and treatment pathway prioritization for entities associated with a respective disparity group. Example embodiments are configured to generate, using a risk prediction model, an individual risk score for an entity of a disparity group associated with an entity cohort. Example embodiments are also configured to generate, using a disparity risk adjustment model, a disparity adjusted risk score for the entity based on the individual risk score. Example embodiments are also configured to initiate various prediction-based actions for the entity based on a comparison between the disparity adjusted risk score and a risk score threshold. Example embodiments are also configured to generate a phenotypic profile for the entity based on an evaluation data object and an image-based evaluation data object for the entity and generate a prediction-based action sequence for the entity based on the phenotypic profile.

Abstract: A method may include receiving information associated with a transmission of data. The method may include determining a classification for the information associated with the transmission of data. Based on the classification and in response to a trigger, the method may include formatting a portion of the information into a first schema associated with a location service. The method may also include transmitting a request for location information corresponding to the portion of the information to the location service according to the first schema. The method may include receiving, from the location service, the location information according to the first schema and formatting the location information from the first schema to a second schema associated with the computing device. The method may include updating the information associated with the transmission of data to include the location information.

Abstract: Various embodiments of the present disclosure provide computer forecasting techniques for forecasting holistic, categorical improvement predictions. The techniques may include generating a predictive quality performance measure based on (i) an evaluation entity of a plurality of evaluation entities within an entity group and (ii) a quality metric of a plurality of quality metrics corresponding to a categorical ranking scheme for the entity group. The techniques include using an action-specific causal inference model to generate a metric-specific predictive impact measure. The techniques include generating a metric-level categorical improvement prediction and a categorical improvement prediction for the entity group with respect to the categorical ranking scheme based on a weighted aggregation of the metric-level categorical improvement prediction and a plurality of metric-level categorical improvement predictions respectively corresponding the plurality of quality metrics.

Abstract: Various embodiments of the present disclosure provide computer forecasting techniques for forecasting holistic, causal risk-based scores. The techniques may include generating a predictive risk-based opportunity score for an evaluation entity based on (i) a plurality of engagement scores and (ii) a plurality of predictive risk scores respectively corresponding to a plurality of predictive entities within an entity cohort associated with the evaluation entity. Using action-specific causal inference models, a predictive impact score of a prediction-based action on the evaluation entity is generated and used to generate a causal gap closure score for the evaluation entity based on a gap closure rate associated with the evaluation entity. The techniques include generating a causal risk-based impact score for the prediction-based action and the evaluation entity based on the predictive risk-based opportunity score, the predictive impact score, and a predictive improvement measure.

Abstract: Various embodiments of the present disclosure provide computer forecasting techniques for initiating presentation of an interactive user interface. The techniques may include receiving one or more candidate prediction-based actions and generating a plurality of causal risk-based impact scores with respect to a candidate prediction-based action. The techniques include generating a plurality of causal quality-based impact scores and an action sequence for a plurality of evaluation entities and generating a causal net impact score based on (i) an aggregation of the plurality of causal risk-based impact scores and the plurality of causal quality-based impact scores and (ii) a sequence impact metric corresponding to the action sequence. The techniques include generating a sequence ranking for the action sequence and initiating a presentation of an interactive user interface reflective of the action sequence and the sequence ranking.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using a multi-context convolutional self-attention machine learning framework that comprises a shared token embedding machine learning model, a plurality of context-specific self-attention machine learning models, and a cross-context representation inference machine learning model, where each context-specific self-attention machine learning model is configured to generate, for each input text token of an input text sequence, a context-specific token representation using a context-specific self-attention mechanism that is associated with the respective distinct context window size for the context-specific self-attention machine learning model.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis using semi-structured input data. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis using semi-structured input data using at least one of techniques using inferred codified fields and temporally-arranged codified fields.

Abstract: A method of assigning parent-of-origin to a haplotype, a sub-haplotype or an allele associated with a haplotype. Chromosome-length haplotypes of a genome are generated and a differential methylation status of at least one imprinted differentially methylated region (iDMR) associated with each one of the autosomal chromosomes is determined. The differential methylation status of the at least one iDMR is used to assign parent-of-origin for each one of the chromosome-length haplotypes.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations using a multi-context convolutional self-attention machine learning framework that comprises a shared token embedding machine learning model, a plurality of context-specific self-attention machine learning models, and a cross-context representation inference machine learning model, where each context-specific self-attention machine learning model is configured to generate, for each input text token of an input text sequence, a context-specific token representation using a context-specific self-attention mechanism that is associated with the respective distinct context window size for the context-specific self-attention machine learning model.

Abstract: A method comprises: obtaining a current initial image generated by an image generator of an imaging device based on current input signals of sensors of the imaging device; and applying a transformation model to the current initial image to generate a current transformed image, wherein the transformation model is a machine-learning model that has been trained to generate transformed images that more closely resemble reference images generated by a reference image generator.

Abstract: Systems and methods are disclosed for predicting diagnoses in medical records. A method includes receiving one or more documents, wherein the one or more documents include medical records. An optical character recognition (OCR) engine is used to extract text from the one or more documents. A natural language processing (NLP) model is used to determine one or more predictions and attention scores for one or more tokens in the one or more documents, wherein each of the one or more tokens represents a word in the extracted text. The one or more tokens are aggregated based on the one or more attention scores to construct sentences. The constructed sentences are presented to a user via a graphical user interface of a device.

Abstract: Various embodiments of the present disclosure provide cohort prediction and activity forecasting techniques for implementing improved population analytics in various prediction domains. The techniques may include generating a documented parameter rate for an entity cohort and a predicted parameter rate for the entity cohort based on a plurality of entity-specific parameter scores. The techniques include generating a predicted documentation error for the entity cohort based on a comparison between the documented parameter rate and the predicted parameter rate and, responsive to the predicted documentation error, initiating, using one or more cohort-specific causal models, the performance of an error correction action for the entity cohort.

Abstract: A hydrogen storage device is described. The hydrogen storage device comprises a heater/cooler module (6) and a pressure containment vessel (1) defining an interior volume and having within it: a thermally conducting network (4) having a face in thermal contact with the heater/cooler module (6), the shape of the thermally conducting network (4) being a fractal geometry in two or three dimensions; optionally a metal foam in thermal contact with the thermally conducting network (4); and a hydrogen storage material (5) in thermal contact with the thermally conducting network (4).

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing (NLP) operations on multi-segment documents. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform NLP operations on multi-segment documents by generating document segmentation machine learning models, using document segmentation machine learning models to determine document segments of input multi-segment documents, enabling adaptive multi-segment summarization of multi-segment documents, and enabling guided interaction with multi-segment documents.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for allocating resources. The method comprises receiving, by a computing device using a resource allocation machine learning framework, historical data comprising one or more causal variables corresponding to one or more actions or inactions with respect to one or more resource-requesting entities and one or more outcomes of one or more actions, identifying, by the computing device, given ones of one or more resource-requesting entity subgroups based at least in part on the one or more causal effect predictions, and performing, by the computing device, one or more prediction-based actions based at least in part on the identification of the given one or more resource-requesting entity subgroups.

Abstract: A method of assigning parent-of-origin to a haplotype, a sub-haplotype or an allele associated with a haplotype. Chromosome-length haplotypes of a genome are generated and a differential methylation status of at least one imprinted differentially methylated region (iDMR) associated with each one of the autosomal chromosomes is determined. The differential methylation status of the at least one iDMR is used to assign parent-of-origin for each one of the chromosome-length haplotypes.

Abstract: A training method for training neural networks to determine a magnetic susceptibility distribution of a sample may include: storing a simulated magnetic susceptibility map of the sample, generating a modified magnetic susceptibility map by combining an influence of one or more external magnetic susceptibility sources with the simulated magnetic susceptibility map and storing the modified magnetic susceptibility maps. The method may include generating a first training image by applying a quantitative susceptibility mapping model the modified magnetic susceptibility map and storing the first training image, applying the first neural network to the first image and a second neural network to an output of the first neural network and changing network parameters of the first and the second neural network depending on a deviation of an output of the second artificial neural network from the simulated magnetic susceptibility map.

Abstract: There is a need for more effective and efficient predictive data analysis. This need can be addressed by, for example, solutions for performing cross-temporal predictive data analysis. In one example, a method includes determining a time-adjusted encoding for each temporal unit of a group of temporal units, processing each time-adjusted encoding using a cross-temporal encoding machine learning model to generate a cross-temporal encoding of the group of temporal units, and performing one or more prediction-based actions based at least in part on the cross-temporal encoding.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for converting a multilabel classification model into a sequence of a plurality of binary classification models based on a plurality of label subgroups associated with the multilabel classification model, where the label subgroups comprise an optimal subgroup size, the optimal subgroup size is generated by optimizing an optimization measure defined by a subgroup size variable and a total inner group correlation measure, and identifying label membership to a particular subgroup by using a mixed integer linear program model.