Abstract: Mechanisms are provided for processing a sequential database natural language query. A process model is preprocessed to generate mapping data structure(s). The mapping data structure(s) map elements of the sequential process to other elements of the sequential process to thereby identify sequential and dependent characteristics of the sequential process. A sequential database natural language (SDNL) query interpretation engine is configured with the mapping data structure(s) and natural language processing is performed on a query to generate extracted features. The configured SDNL query interpretation engine operates on the extracted features and the mapping data structure(s) to generate intent information for the query. Executable database queries are generated based on the intent and executed on a database to return a response to the query.

Abstract: In an approach for identifying disease progression hazard ratios for given disease against diseases from an EHR database to determine top comorbidities to the given disease, a processor receives raw EHR data. A processor identifies, from the raw EHR data, a set of diseases and associated diagnosis information for each disease of the set of diseases. A processor calculates a hazard ratio for each disease pair of a set of disease pairs producing a set of hazard ratios, wherein the set of disease pairs comprises a given disease paired with each disease of the set of diseases. A processor ranks the set of hazard ratios for the given disease. A processor selects a pre-defined number of top comorbidities of the set of hazard ratios for the given disease based on the ranking. A processor outputs the pre-defined number of top comorbidities for the given disease.

Abstract: Embodiments of the present disclosure relate to facilitating decision marking in a business process. In an embodiment, process execution data associated with execution of at least one instance of a business process are obtained. At least one first target attribute available at a first target point is determined based on the process execution data. The first target point is subsequent to a first decision point of a plurality of decision points in the business process, the at least one first target attribute has a contribution in deriving a first expected outcome at the first decision point, and the first target point is a first activity point or a first decision point. A suggestion is provided which suggests incorporating the at least one first target attribute in decision making at the first decision point executed in a further instance of the business process.

Abstract: Aspects of the invention include selecting an activity as a selected activity. A method includes designating a subset of the set of activities as classes, collecting a log of inputs and outputs of each encountered activity as a data point each time the process is implemented, and extracting features from each data point that is collected to generate a feature vector from each data point. A teacher model is initialized with a first data point and updated with each data point subsequent to the first data point. A student model is initialized with a set of data points including the first data point such that every one of the classes is encountered at least once. The student model is updated with the teacher model. A set of features is input to the student model to obtain a prediction of the outcome of the selected activity.