Diabetes onset and progression prediction using a computerized model

Patent metadata

Field	Value
Publication number	US-2016357934-A1
Application number	US-201514942592-A
Country	US
Kind code	A1
Filing date	Nov 16, 2015
Priority date	Nov 14, 2014
Publication date	Dec 8, 2016
Grant date	—

Abstract

The disclosed computerized system and method facilitates predicting the onset of diabetes or symptom progression in those patients already suffering from the disease. The computerized system and method applies steps to segment the population by predefined member characteristics. Once segmented, the computerized system and method applies a plurality of prediction models to the segmented population data to provide a ranking of members of the population that indicates the likelihood of onset or progression of diabetes for each member.

First claim

What is claimed is:

1 . A method for predicting the onset of diabetes in a population without diabetes comprising:
receiving health related patient data from a plurality of sources; performing an extraction process upon the received data to extract features that describe at least one patient; processing the extracted data using a summarization process, a standardization process, and a filtration process; segmenting the processed data according to data characteristics; and applying a plurality of models to the segmented data that identify the relationships between characteristics of the data and onset of diabetes for at least one patient.

2 . The method of claim 1 , wherein the plurality of models applied comprise at least one of a neural network, logistic regression, or a decision tree.

3 . The method of claim 1 , wherein the model applied is selected by verifying each of the plurality of models using holdout data to determine the accuracy of each model and the model with the greatest accuracy is selected.

4 . The method of claim 1 , wherein the received data comprises at least one of: health surveys received from a group of individuals, data representing demographics of the group of individuals, data comprising summarized medical lab test results for the group of individuals, insurance claims by members of the group of individuals for medical care, insurance claims by members of the group for pharmacy services, and consumer data regarding the members.

5 . The method of claim 1 , wherein the extracted features comprise at least one of: a patient's demographic profile, a patient's clinical profile, a patient's behavior profile, a patient's medication profile, and disease progression profiles.

6 . The method of claim 1 , wherein the plurality of models are applied in response to a user input selection.

7 . A method for predicting the progression of diabetes in patients with diabetes comprising:
receiving health related data from a plurality of sources; performing an extraction process upon the received data to extract features that describe at least one patient; processing the extracted data using a summarization process, a standardization process, and a filtration process; segmenting the processed data according to data characteristics; and applying a plurality of models to the segmented data which identify the relationships between characteristics of the data and progression of diabetes in patients with diabetes.

8 . The method of claim 7 , wherein the progression is represented by an index comprising a plurality of complications associated with diabetes.

9 . The method of claim 7 , wherein application of the model produces a list of patients arranged progressively from a low severity range to a medium to a high severity range on a scale of progression of diabetes.

10 . The method of claim 7 , wherein application of the model identifies patients at risk of progressing from lower severity level to a high severity level.

11 . The method of claim 7 , wherein the plurality of models applied comprise at least one of a neural network, logistic regression, or a decision tree.

12 . The method of claim 7 , wherein the model applied is selected by verifying each of the plurality of models using holdout data to determine the accuracy of each model and the model with the greatest accuracy is selected.

13 . The method of claim 7 , wherein the received data comprises at least one of:
health surveys received from a group of individuals, data representing demographics of the group of individuals, data comprising summarized medical lab test results for the group of individuals, insurance claims by members of the group of individuals for medical care, insurance claims by members of the group for pharmacy services, and consumer data regarding the members.

14 . The method of claim 7 , wherein the extracted features comprise at least one of: a patient's demographic profile, a patient's clinical profile, a patient's behavior profile, a patient's medication profile, and disease progression profiles.

15 . The method of claim 7 , wherein the plurality of models are applied in response to a user input selection.

Assignees

• Humana Inc

Inventors

• Dong Yanting
• Fan Jing
• Chiguluri Vinay
• Gopal Vipin

Classifications

• G06F19/366

  Physics · mapped topic

• G06F19/3437

  Physics · mapped topic

• G06F19/363

  Physics · mapped topic

• G06F19/345

  Physics · mapped topic

• G06F19/3431 Primary

  Physics · mapped topic