International Business Machines Corporation

Gigi Yuen-Reed

Shilpa N Mahatma

Ajay Mohindra

Aleksandra Mojsilovic

Francisco Phelan Curbera

Shubir Kapoor

Shahram Ebadollahi

Ock Kee Baek

Houtan Aghili

Jianying Hu

Ping Zhang

Karthikeyan Natesan Ramamurthy

Rachita Chandra

Kevin N Tran

Jingwei Yang

Dennis Wei

Kun Lin

Hyuna Yang

Kathryn L Howard

A method, a computing system and a computer program product are provided. A model is generated and trained. The model is based on clinical data with outcomes from clinically-defined hierarchical metadata in a selected level of clinically-defined hierarchical metadata serving as an initial set of prediction targets. A score is determined for each of the prediction targets based on the generated model and the set of evaluation factors. The set of prediction targets, the generated model, and the scores for the set of prediction targets are updated until the updated scores for the updated set of prediction targets satisfy acceptance criteria. The updated generated model, using the updated set of prediction targets, is applied to predict one of a set of updated prediction targets of mutually exclusive outcome categories.

Constructing prediction targets from a clinically-defined hierarchy

Modularized data processing systems and methods for its use are provided. Processing a current job can reuse data generated for a previously processed job to the extent the two share parameter configurations. Similarly, outputs of processing modules generated during processing the previously processed job can be used as inputs to processing modules processing a current job, if the two jobs share some parameter configurations.

Job management in data processing system

Embodiments include methods, systems and computer program products for reducing feature space in analysis of medical data. Aspects include receiving patient temporal traces. Aspects also include conducting sequential pattern mining on the patient temporal traces to produce sequential features. Aspects also include clustering the sequential features with a similarity metric. Aspects also include analyzing the clustered features to predict a healthcare outcome.

Reduction of feature space for extracting events from medical data

An application as a service provided in a secure environment. A sandbox in a user's computing environment may be created. An application may be downloaded to the user's computing environment to run within the sandbox. Data sources associated with the user's computing environment may be searched and connectivity established with data registry of the data sources based on data description received with the application. The application may be run within the sandbox using the established connectivity. Metering may be performed to monitor usage of the application at the user's computing environment.

Healthcare as a service&#x2014;downloadable enterprise application

Growing community of inventors

Tampa, FL, United States of America

Gigi Yuen-Reed