International Business Machines Corporation

Sarah E Knoop

Peter Martin Schwarz

John T E Timm

Joshua W Hui

John T Timm

Tan Hung Marie Ng

Sunhwan Lee

Lingtao Cao

A mechanism is provided to implement a health risk assessment system for adaptively and dynamically generating a personalized questionnaire for health risk assessment of a patient. A set of responses are analyzed and a patient is grouped to an initial group that matches a similar patient group. Utilizing the initial group, an initial question is selected to present to the patient. Responsive to receiving a current response to the initial question, the current response is analyzed, the patient is grouped to a next group, and a next question is identified and presented to the patient. The process continues until a last group is reached where a scoring of possible health risks associated with the patient is performed based on each response provided by the patient and identified groupings. A final possible health risk or ranked set of possible health risks is then presented based on the scoring.

Personalized questionnaire for health risk assessment

As received, a data value of an expected input set of received data values is missing from user input. A subset of known data with data values similar to a subset of the received data values is determined. A data sample average for the missing data value is determined from data values within the subset of the known data. An initial estimate of the missing data value is initialized using the data sample average. Boundary data clusters near the initial estimate of the missing data value are identified within the subset of the known data. A data harvesting region encapsulated according to the boundary clusters is defined. Data support clusters within at least one subset of the known data inside the data harvesting region are selected. The initial estimate of the missing data value is updated based upon data of the boundary clusters and the data support clusters.

Missing value imputation using adaptive ordering and clustering analysis

A mechanism is provided for creating modules from an XML schema. The mechanism includes creating a syntax tree from a sample XML fragment of the XML schema, creating a module with a list of parameters based on the syntax tree, identifying variable pieces of information in the syntax tree to be inserted in the list of parameters with a variable sign, and inserting the variable information into the list of parameters. The mechanism includes inserting another module in the syntax tree of the module, in which the other module corresponds to another sample XML fragment and has another list of parameters, and identifying the other module with the variable sign in the syntax tree of the module. The mechanism includes inserting the other module into the list of parameters of the module in which the other module to serve as a parameter, and providing an option for constraining the module.

Modularizing complex XML data for generation and extraction

Growing community of inventors

San Jose, CA, United States of America

Sarah E Knoop