International Business Machines Corporation

Chandramouli Maduri

Pei-Yun S Hsueh

Zhiguo Li

Ching-Hua Chen

Kenneth James Barker

Sara Rosenthal

Subhro Das

Adam R Faulkner

Si Sun

Gema Almoguera

Embodiments are provided for cognitive bias detection and correction in self-reported data. In some embodiments, a system can include a processor that executes computer-executable components stored in memory. The computer-executable components include first components that creates an ontology of bias descriptor features to identify cognitive biases. The cognitive biases can include a combination of at least one device-induced cognitive bias, at least one testing-application-induced cognitive bias, or at least one study-design-induced cognitive bias.

Cognitive bias detection and correction in self-reported data

A method, a computer program product, and a computer system predict medication adherence of a patient. The method includes identifying risk factors associated with medication adherence of the patient. The method includes determining a likely behaviour for medication adherence of the patient based on the identified risk factors and a temporal causal model. The temporal causal model is based on features of a patient cluster to which the patient belongs. The features are nodes in the temporal causal model. The likely behaviour is based on causality measures for each identified risk factor to the nodes. The method includes determining a current medication adherence value of the patient. The current medication adherence value is indicative of a ratio between an actual medication regiment and an expected medication regiment. The method includes determining a future medication adherence value of the patient based on the current medication adherence value and the causality measures.

Personalized medication non-adherence evaluation

A mechanism is provided in a data processing system to implement a personalized patient engagement engine. The personalized patient engagement engine develops a set of models for a plurality of behavioral phenotypes based on anonymized unstructured and structured patient-care management records for a plurality of patients over a period of time; matches a given patient to a behavioral phenotype; estimates a propensity of positive and/or negative behavioral responses of each of a plurality of targeted behaviors; dynamically updates personalized intervention effectiveness rankings in context for care manager and patient decision-making based on what has been shown to lead to positive responses for individuals with a similar behavioral profile; generates an intervention recommendation for the given patient based on the personalized intervention effectiveness rankings relative to the patient given an assigned goal and an individual intervention effect estimation; and provides the intervention recommendation to the care manager.

Personalized patient engagement in care management using explainable behavioral phenotypes

Growing community of inventors

Elmsford, NY, United States of America

Chandramouli Maduri