Querying and analysis of clinical trials using probabilistic graphical models
AssigneeMicrosoft Technology Licensing, LLC
InventorsHarsh SHRIVASTAVA, Urszula Stefania CHAJEWSKA, Muhammad Arrabi
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to methods and systems that provide querying and analysis of clinical trials using probabilistic graphical models. The methods and systems train a probabilistic graphical model using clinical trial data and use the probabilistic graphical model to perform inferences in response to queries for clinical trials. The methods and systems use the probabilistic graphical model to handle multimodal datatypes of the clinical trial data and predict multiple attributes of the clinical trial for an input query.
Claims20
A method, comprising:
- training a probabilistic graphical model using clinical trial data, wherein the probabilistic graphical model represents a distribution over a domain of the clinical trial data;
- receiving a query for a new clinical trial;
- using the probabilistic graphical model to perform inference tasks in response to the query;
- and
- providing an output of the inference tasks as a response to the query.
A device, comprising:
- a memory to store data and instructions;
- and
- a processor operable to communicate with the memory, wherein the processor is operable to:
- train a probabilistic graphical model using clinical trial data, wherein the probabilistic graphical model represents a distribution over a domain of the clinical trial data;
- receive a query for a new clinical trial;
- use the probabilistic graphical model to perform inference tasks in response to the query;
- and
- provide an output of the inference tasks as a response to the query.
Dependencies are inferred from the claim text.