Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

Abstract: Supervised partitioning is used to perform record matching. A request to identify matches between records is received. A graph representation that indicates similarities between the records is partitioned and an evaluation of the partitioning is performed according to a supervised machine learning technique to generate a confidence value in the partitioning. An indication of equivalent records according to the partitioning and the confidence value of the partitioning may be provided.

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

Abstract: Techniques for memory-efficient streaming count estimation for multisets are described. A method for memory-efficient streaming count estimation for multisets may include obtaining data from a plurality of data sources, and estimating a count for one or more attributes of the data using a telescoping count-min sketch (CMS) data structure, the telescoping CMS including at least a first table and a second table, wherein count values for the data are stored in a plurality of cells of the first table and when a cell of the first table is saturated, the count values for that cell are stored in a corresponding cell of the second table determined based at least on the cell of the first table.

Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

Abstract: Computerized methods for modifying at least one component of a clinical order are provided. The methods may include receiving a clinical order, the clinical order having a first component associated with a first phase and a second component associated with a second phase, wherein the first and second components have a first attribute in common, receiving an indication to modify the first attribute of the first component, and modifying the first attribute of the first component and the second component based on the indication received. The methods may further include associating the first and second components of the clinical order to form a cross-phase group and displaying the first and second components in association with an electronic record, e.g., an electronic medical record, in conjunction with a cross-phase group identifier to identify the components as members of the cross-phase group. Computerized systems for performing the disclosed methods are also provided.

Abstract: A data records service is configured to receive original data records and, in parallel, generate a transliterated version of the original data record into a phonetic based language. Individual fields of data records can be transliterated by identifying a primary language, generating language specific tokens for individual text portions, and transliterating the token. The records processing service can then execute matching models on both original data records and transliterated data records to detect matching data records.

Abstract: Techniques for scaling record linkage via elimination of highly overlapped blocks are described. A method for scaling record linkage via elimination of highly overlapped blocks includes identifying a first plurality of blocks based at least on a plurality of records stored in a storage service of a provider network, identifying a plurality of sets of matching blocks from the first plurality of blocks, deleting the plurality of sets of matching blocks except for a first block from each set from the plurality of sets of matching blocks, and iteratively performing dynamic blocking based at least on the first block to generate subsequent pluralities of blocks until the subsequent pluralities of blocks are below a threshold size.

Abstract: Techniques for Scalable parallel elimination of approximately subsumed sets are described. A method for Scalable parallel elimination of approximately subsumed sets includes identifying a first plurality of blocks based at least on a plurality of records stored in a storage service of a provider network, determining a plurality of subsumption relationships between blocks from the first plurality of blocks, retaining a first subset of the first plurality of blocks and demoting a second subset of the first plurality of blocks based at least on the plurality of subsumption relationships, and iteratively performing dynamic blocking based at least on the first subset of the plurality of matching blocks and the second subset of the plurality of matching blocks to generate a subsequent pluralities of blocks.

Abstract: Computerized methods for modifying at least one component of a clinical order are provided. The methods may include receiving a clinical order, the clinical order having a first component associated with a first phase and a second component associated with a second phase, wherein the first and second components have a first attribute in common, receiving an indication to modify the first attribute of the first component, and modifying the first attribute of the first component and the second component based on the indication received. The methods may further include associating the first and second components of the clinical order to form a cross-phase group and displaying the first and second components in association with an electronic record, e.g., an electronic medical record, in conjunction with a cross-phase group identifier to identify the components as members of the cross-phase group. Computerized systems for performing the disclosed methods are also provided.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the care of a patient by a multi-disciplinary care team. A graphical user interface presents one or more clinical problems associated with a patient. For each clinical problem, actionable care team icons are presented that, among other things, identify care teams responsible for caring for the clinical problem and any actions taken by the care teams to address the clinical problem.

Abstract: Methods, systems, and computer-storage media are provided for enabling a user to dynamically create associations and take actions with respect to a clinical finding associated with a patient. After selecting a clinical finding that is of interest in a first workflow application, a graphical user interface is automatically presented. The graphical user interface includes trending information for the clinical finding as well as information related to the clinical finding. The graphical user interface enables a clinician to associate the clinical finding with a current patient problem or a possible diagnosis related to the clinical finding. Additionally, the graphical user interface enables the clinician to take actions with respect to the clinical finding.

Abstract: A data records service is configured to receive original data records and, in parallel, generate a transliterated version of the original data record into a phonetic based language. Individual fields of data records can be transliterated by identifying a primary language, generating language specific tokens for individual text portions, and transliterating the token. The records processing service can then execute matching models on both original data records and transliterated data records to detect matching data records.

Abstract: Methods, systems, and computer-readable media are provided for determining and generating content items that provide patient information and content provided by, for example, a third-party content provider that is relevant to information associated with an open healthcare application. The content items are displayed in a separate display space from the healthcare application's user interface and dynamically change and update in response to changes in the information being displayed on the healthcare application's user interface. Additionally, the content items are actionable thereby enabling healthcare providers to address alerts, take actions, view supporting documentation, and the like.

Abstract: Methods, computer systems, and computer-readable storage media are provided for utilizing health-related variables to generate a current health state of a user along with a most-likely future health state of the user and an ideal future health state of the user. Graphical representations of these health states are generated and presented on a graphical user interface. The user is able to interact with the graphical representations to see the impact of the user's choices on the user's future health.