Abstract: A computer apparatus to assist diagnosis of a patient including: a memory storing instructions for execution and an output for results of a processor that provides a patient builder and a vertex filter. Where the builder inputs patient data including historical clinical; and open data, and to create a patient clinical object, PCO, graph; and a full patient graph PCOs for each patient. The filter includes: a context builder to build a domain based on a specification and open data; a context-based vertex filter ranking vertices in the full patient graph based on domain affiliation, retaining any vertices with high domain affiliation; and computing a similarity between the patient PCO and other PCOs in the full patient graph using the retained vertices; and a patient ranker ranks the PCOs according to t similarity where the output lists patients similar to the patient to suggest patient diagnoses.

Abstract: A system and method to input patient data including previous diagnosis, drugs, symptoms and treatment, open data and expert knowledge, and to use these inputs to create a patient clinical object (PCO), biomedical knowledge and rule based knowledge graphs, and to enrich the PCO using the biomedical knowledge graph. A meta diagnosis predictor is to use the PCO and the biomedical knowledge graph and/or the rule based knowledge graph in plural predictors of a diagnosis-based predictor to provide a set of diagnoses based on previous diagnoses, a drug-based predictor to provide a set of diagnoses based on drugs taken by the patient, a symptom-based predictor to provide a set of diagnoses based on symptoms of the patient and a treatment-based predictor to provide a set of diagnoses based on the treatments. Any of the sets of diagnoses may be combined to give a predicted primary diagnosis for the patient.

Abstract: A computer apparatus to identify healthcare resources used by a patient given a potential diagnosis, the apparatus comprising: a memory storing instructions for execution by a processor, the processor configured by the instructions to implement an impact estimator to: receive a patient clinical object, PCO, which represents the patient in the form of a graph, and includes previous healthcare resource utilization, HCRU, information of the patient as a patient HCRU subgraph; receive an HCRU knowledge graph, HCRU KG, associating healthcare resources with medical services; receive potential diagnosis information from a clinician; identify and extract potential healthcare resources and services in the HCRU KG associated with the potential diagnosis to form an HCRU subgraph associated with the potential diagnosis; and to perform graph analysis on the HCRU subgraph associated with the potential diagnosis and the patient HCRU subgraph to obtain an updated patient HCRU subgraph taking the potential diagnosis into acco

Abstract: A computer apparatus to identify healthcare resources used by a medical institution, comprising: a memory storing instructions for execution by a processor, the processor configured by the instructions to provide: a knowledge graph builder; and a knowledge graph customizer; wherein: the knowledge graph builder is arranged to input open data and clinician information, to generate a set of medical services terms and a set of medical resources terms from the open data and clinician information, and to associate the medical resources with the medical services to build a knowledge graph; and the knowledge graph customizer is arranged to match the knowledge graph with records of the medical institution to provide a customized subgraph of the knowledge graph which is specific to the medical institution.

Abstract: Embodiments include a system for reconciling input datasets with a model ontology, the system comprising a processor coupled to a memory, to execute: a model ontology storage process, storing a model ontology graph defining a concept hierarchy, the concept hierarchy comprising nodes at various levels. The processor and memory further to execute: a user interface process, receiving, via a user interface, user input assignments of nodes from upper levels of the concept hierarchy to input datasets with particular properties from among the lower level nodes. The processor and memory further to execute an input dataset reconciliation process using the concept hierarchy and a record of historical user input assignments to determine which higher level nodes to assign to a new input dataset, based on the lower level nodes represented in the new input dataset.

Abstract: A system including a healthcare risk engine to provide a healthcare risk knowledge graph from open data and knowledge data related to risk by using risk-related terms to retrieve documents from open data and by extracting the healthcare risk knowledge graph as entities from the documents and links between the entities. A patient risk graph predictor predicts risks for a patient by combining information in a Patient Clinical Object (PCO) with entities in the healthcare risk knowledge graph to produce a patient risk graph. An impact estimator estimates an impact of a treatment by taking the treatment and adjacent nodes from the healthcare risk knowledge graph to form a healthcare treatment subgraph, finding an entity and adjacent nodes in the patient risk graph to form a patient treatment subgraph, providing an impact graph by combining the patient treatment subgraph and the healthcare treatment subgraph, and retaining resultant linked nodes.

Abstract: An array of registered entity property-value pairs representing a registered entity are stored in a data storage system. Each of the pairs includes a property label representing a property and a value range of the property. For each identifier property-value, an identifier property label, uniquely identifying the registered entity, and an identifier value representing a value of the identifier property are stored. A dataset is acquired with dataset property-value pairs for each of a first set of acquired dataset entities, where each pair includes a property label representing a property and a value representing a value range of the property. An identifier property-value pair matching an acquired dataset property-value pair for the acquired dataset entity is identified and then the acquired dataset property-value pairs are consolidated into the array of registered entity property-value pairs.

Abstract: A system for assessing patient risk using open data and input of knowledge data, the system including a healthcare knowledge data input to receive open data and a knowledge input to accept input of knowledge data relating to risk; a healthcare risk engine to provide a healthcare risk knowledge graph from the open data and knowledge data by using input of risk-related terms to retrieve documents from the open data and by extracting the healthcare risk knowledge graph as entities from the documents corresponding to risk-related terms, as well as links between the entities. A patient risk graph prediction module predicts risks for a patient by combining information in a Patient Clinical Object (PCO) with entities in the healthcare risk knowledge graph to produce a patient risk graph.

Abstract: A software service execution system includes: a software library storing software services, each obtaining and processing input data from a specified input URI (uniform resource identifier) and outputting the result to a specified output URI; a metadata graph representing the software services, each being identifiable by a predicate defining a relationship between a subject vertex and an object vertex, the subject vertex storing the specified input URI and being linked by a directed edge labelled with the predicate to the object vertex storing the specified output URI; a metadata graph query interface receiving a query requesting a queried vertex, linked by a defined traversal path along one or more edges to a source vertex; a software service execution controller controlling the execution of the software services identified by specified predicates labelling edges on the defined traversal path, in an order determined by the defined traversal path.

Abstract: A microservice-based data processing apparatus, including: a type register, storing a list of types, a type being a semantic concept expression; and microservices each comprising an annotation of an input type and output types from the list; processing logic transforming input data expressed by the input type into output data expressed by the output types; and a messaging mechanism for inputting data, via a message, to a microservice, the mechanism defining a message format for structuring the messages. The format includes a first field specifying the data being input; and a second field specifying a type, from the list of types, semantically expressing the concept instantiated by the data. Each microservice includes a controller to receive a message from the mechanism having the format, and to respond by executing the logic when the type specified by the second field matches the input type of the microservice.

Abstract: A software service execution apparatus comprising a registry of software services, each service to execute a data processing function in the registry; a controller, to receive a processing request defining requested data processing functions, compose an execution schedule of software services from the software services identified, fulfill the data processing request by identifying a software service that matches the requested data processing function, include the identified software service in the execution schedule, and control execution of the schedule. The apparatus further comprises a machine learning mechanism configured to maintain a record of the composing.

Abstract: A data processing apparatus including a library, storing software services, each executing a data processing function; a user interface receiving commands, expressed in a language and defining a data processing target and a data processing request; and a parser. The parser extracting from each command: the request from the language; and the target. A knowledge base maintaining a record of the request and the target; a scheduler obtaining the request from the parser, and compiling a schedule to fulfill the request; a controller controlling execution of the schedule, the target being the input data to the execution, and to output a result; and a result processor obtaining the result, and, based on records of requests and targets, to identify a request candidate, and to output to the user as a selectable command in the language, via the user interface, the candidate with the result defined as a data processing target.

Abstract: A data property recognition apparatus, includes a storage unit; a model data acquisition processor acquiring a plurality of model sets of data entries, each data entry individually representing an identified property common to the model set and being of a data type common to the model set; a feature vector generation processor receiving an input set of data entries, recognizing a data type common to the input set of data entries from among a plurality of supported data types, selecting a set of statistical characteristics representing the input set of data entries in dependence upon the recognised data type, generating a value of each of the selected set of statistical characteristics from the input set of data entries, and outputting a feature vector composed of the generated values of statistical characteristics.

Abstract: A data storage system a process including: storing an array of registered entity property-value pairs representing the registered entity where each of the pairs includes a property label representing a property and a value range of the property; storing an entry of one identifier property-value pair where each pair includes an identifier property label uniquely identifying the registered entity, and an identifier value representing a value of the identifier property; acquiring a dataset having acquired dataset property-value pairs for each of a first set of acquired dataset entities, where each pair includes a property label representing a property and a value representing a value range of the property; identifying an identifier property-value pair matching an acquired dataset property-value pair for the acquired dataset entity; and consolidating the acquired dataset property-value pairs into the array of registered entity property-value pairs.

Abstract: An event learner using machine intelligence includes an inputter to receive sample event patterns; an information retriever to retrieve terms information and to identify entities and predicates from the terms information; and a comparator to compare the identified entities and predicates against the sample event patterns, to generate a plurality of refined event patterns using the identified entities and predicates and the sample event patterns. An event extractor includes a selector to select raw information from a plurality of heterogeneous sources; a reformatter to identify entities and predicates in the raw information, and to generate reformatted information indicating the entities and predicates; and an analyser to analyse the reformatted information using the plurality of refined event patterns and, when an event matching a refined event pattern is identified, to store the event.

Abstract: An apparatus, method and program for generating a multiple-event pattern query for use in the retrieval of event information. The apparatus comprises: an inputter to receive an input query from a user; a retriever to analyze the received input query, and to retrieve an event query template from an event template database on the basis of the analysis; a pattern query formulation unit to receive the retrieved event query template, and to modify the event query template using the received input query to formulate the multiple-event pattern query; and a transmitter to transmit the multiple-event pattern query to an event information source, such that events matching the multiple-event pattern query may be identified.

Abstract: An apparatus, method and program categorizing extracted events using a plurality of refined event patterns, and storing events matching a pattern in event storage; retrieving that match a pattern from the storage, to identify entities in the events, an event time of occurrence, and determine if events relate to the same occurrence, if the reconciliation determines that events relate to the same occurrence, reconciling the events retaining only a single event relating to an occurrence; receiving a query from a user, to reformat the query into a multiple-event pattern query, and semantically annotating the retained events, such that no information from the plural stored events relating to the same occurrence is lost, and receiving the pattern query to identify events matching the pattern query, and storing the events as a multiple event query response in a multiple event storage.

Abstract: Embodiments include a system for reconciling input datasets with a model ontology, the system comprising a processor coupled to a memory, to execute: a model ontology storage process, storing a model ontology graph defining a concept hierarchy, the concept hierarchy comprising nodes at various levels. The processor and memory further to execute: a user interface process, receiving, via a user interface, user input assignments of nodes from upper levels of the concept hierarchy to input datasets with particular properties from among the lower level nodes. The processor and memory further to execute an input dataset reconciliation process using the concept hierarchy and a record of historical user input assignments to determine which higher level nodes to assign to a new input dataset, based on the lower level nodes represented in the new input dataset.

Abstract: A data property recognition apparatus, includes a reference data storage unit storing a plurality of model sets of data entries, each data entry individually representing a property common to the model set, stored in association with a reference feature vector and a descriptor of the property; a query processor obtaining a query set of data entries; a feature vector generation processor generating a value of each of the set of statistical characteristics for the query set, and outputting a query feature vector composed of the generated values of statistical characteristics; a comparison processor executing vector comparisons between the query feature vector and the plurality of stored reference feature vectors, and ranking the descriptors; a property descriptor selection processor selecting a best match descriptor based on the ranking of the descriptors; and a reconciled data manager adding the query set to a reconciled data storage unit.

Abstract: A software service execution system includes: a software library storing software services, each obtaining and processing input data from a specified input URI (uniform resource identifier) and outputting the result to a specified output URI; a metadata graph representing the software services, each being identifiable by a predicate defining a relationship between a subject vertex and an object vertex, the subject vertex storing the specified input URI and being linked by a directed edge labelled with the predicate to the object vertex storing the specified output URI; a metadata graph query interface receiving a query requesting a queried vertex, linked by a defined traversal path along one or more edges to a source vertex; a software service execution controller controlling the execution of the software services identified by specified predicates labelling edges on the defined traversal path, in an order determined by the defined traversal path.