Abstract: A computer-implemented method, system, and non-transitory, computer-readable medium that performs operations including obtaining alerts representing signals in a computing system and corresponding feedback indicators, indicating an association of the alert for the represented signal. The computing system can connect to a computing platform that includes a data mining engine. The operations include identifying a first subset of negative alerts, determining a first set of alert attributes, determining a type of model to analyze the alert attributes for signals represented by the alerts and analyzing, by the model, the first set of alert attributes to identify a subset of alert attributes with likelihoods representing alert attributes that caused the negative association of the alert. The operations include filtering the alerts to exclude a second subset of the alerts based on the likelihood of negative association, and providing for output, a set of alerts that exclude the second subset of the alerts.

Abstract: A rule training system and methods are provided that are configured to generate machine learning rules for fraud detection based on an automated feature selection by a rule creation system. The system includes a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform rule creation operations which include accessing a training dataset, performing a data preprocessing and a data sampling on the training dataset, obtaining a plurality of features from the processed and sampled dataset using a feature engineering operation, selecting a subset of features from the plurality of features using simulated annealing operations, generating the plurality of detection rules using the subset of features, iteratively selecting from the plurality of detection rules, and evaluating a rule performance of each rule in those selected.

Abstract: A computer-implemented method, system, and non-transitory, computer-readable medium that performs operations including obtaining alerts representing signals in a computing system and corresponding feedback indicators, indicating an association of the alert for the represented signal. The computing system can connect to a computing platform that includes a data mining engine. The operations include identifying a first subset of negative alerts, determining a first set of alert attributes, determining a type of model to analyze the alert attributes for signals represented by the alerts and analyzing, by the model, the first set of alert attributes to identify a subset of alert attributes with likelihoods representing alert attributes that caused the negative association of the alert. The operations include filtering the alerts to exclude a second subset of the alerts based on the likelihood of negative association, and providing for output, a set of alerts that exclude the second subset of the alerts.

Abstract: The personal pandemic proximity index system and method include a data ingestion pipeline configured to receive location data associated with disease-positive cases, a data processing module configured to clean and process the received data, a personal pandemic proximity module configured to determine a numerical personal pandemic proximity index value associated with an individual having an interaction at an address relative to the location data, and a graphical user interface configured to present, to a patient care team, the numerical personal pandemic proximity index value, which may include a modified workflow to limit the spread of disease.

Abstract: This specification discloses extrusion cooked vegetable protein compositions made from a mixture of legume proteins. The proteins come from the same type of legume but are processed differently. The extrusion cooked vegetable protein composition hydrates rapidly and at ambient conditions while maintaining firmness. This specification discloses a legume protein mixture useful as a feedstock for making an extrusion cooked vegetable protein compositions of the type described in this specification. This specification discloses extruder conditions for using a legume protein mixture feedstock to make an extrusion cooked vegetable protein compositions of the type described in this specification.

Abstract: The technology disclosed in this specification pertains to a deamidated pea protein isolates, processes for making a deamidated pea protein isolate, and use of the deamidated pea protein isolate in food and beverage compositions. The disclose deamidated pea protein isolates have dissolution properties that are significantly improved compared to non-deamidated pea protein isolates. Furthermore, the deamidated protein isolates maintain good dissolution properties throughout storage.

Abstract: A clinical insight and decision support visualization tool includes a data ingestion logic module that automatically accesses, in real-time, electronic health data of a plurality of trauma patients being treated by a care team at a healthcare institution. The tool further includes a data analysis module that automatically applies at least one predictive model to analyze the processed patient data and determine a current mortality risk score value for each patient, and a user interface module that presents real-time and historical information for each trauma patient including a current mortality risk score value, a categorization of the current mortality risk score value, top contributors to the current mortality risk score value and their respective values, and a trend plot of historic mortality risk score values.

Abstract: The personal pandemic proximity index system and method include a data ingestion pipeline configured to receive location data associated with disease-positive cases, a data processing module configured to clean and process the received data, a personal pandemic proximity module configured to determine a numerical personal pandemic proximity index value associated with an individual having an interaction at an address relative to the location data, and a graphical user interface configured to present, to a patient care team, the numerical personal pandemic proximity index value, which may include a modified workflow to limit the spread of disease.

Abstract: A community vulnerability index dashboard includes a data ingestion logic module configured to automatically receive real-time and non-real-time data from a variety of sources including education agencies, law enforcement, health services agencies, healthcare agencies, medical insurance agencies, housing and transportation agencies, childcare licensing agencies, and non-emergency citywide services. The dashboard includes a data processing module that extracts and process the ingested data, and a data analysis logic module that analyzes the processed data to determine values for indicators and an overall vulnerability index value based on the values of the plurality of indicators to provide insight into the lives of residents living in a community on a block group level. The dashboard includes a data presentation dashboard interface to display an interactive choropleth map of the overall vulnerability index and indicator values on a block group level for the community of interest.

Abstract: A machine learning system for healthcare applications comprises a data ingestion pipeline configured to automatically receive patient data including stored data from an EHR database and real-time data from a plurality of data sources, the data including, EHR records, claims data, and social determinants of health data; a data processing module configured to clean, extract, and process the received patient data; at least one predictive model configured to analyze the cleaned and processed data and determine a risk score for each patient; a configuration file defining the predictive model execution parameters; a tuning module configured to adjust parameters of the predictive model, including variables, thresholds, and coefficients; a retraining module configured to make further adjustments of the predictive model to remove inherent data biases; and a dashboard and reporting module configured to present the risk score to a patient care team.

Abstract: Described are methods of removing phospholipids and other off-flavor-causing compounds from edible proteins using a cyclodextrin treatment. The methods include treating soy protein with cyclodextrins such as ?-cyclodextrin to form cyclodextrin-compound complexes and then separating the resulting complexes from the protein. Optionally, prior to treating the protein with cyclodextrin, the protein is sonicated and then treated with a phospholipase, such as phospholipase A2. Versions of the methods described herein are capable of removing more than 99% of phospholipids from soy protein.

Abstract: A shelf stable, confectionary food product having a core and a confectionary coating. The core is formed from dehydrated crumbs, such as dehydrated cake crumbs sweetened with sugar, and a shortening-based matrix comprising shortening and water. When the dehydrated crumbs are combined with the shortening-based matrix, the crumbs rehydrate. The food product has a shelf life at room temperature of more than one month, such as more than 3 months, or more than 6 months, or up to 9 months.

Abstract: A shelf stable, confectionary food product having a core and a confectionary coating. The core is formed from dehydrated crumbs, such as dehydrated cake crumbs sweetened with sugar, and a shortening-based matrix comprising shortening and water. When the dehydrated crumbs are combined with the shortening-based matrix, the crumbs rehydrate. The food product has a shelf life at room temperature of more than one month, such as more than 3 months, or more than 6 months, or up to 9 months.

Abstract: Described are methods of removing phospholipids and other off-flavor-causing compounds from edible proteins using a cyclodextrin treatment. The methods include treating soy protein with cyclodextrins such as ?-cyclodextrin to form cyclodextrin-compound complexes and then separating the resulting complexes from the protein. Optionally, prior to treating the protein with cyclodextrin, the protein is sonicated and then treated with a phospholipase, such as phospholipase A2. Versions of the methods described herein are capable of removing more than 99% of phospholipids from soy protein.