Intelligent processing of bulk historic patient data

Patent metadata

Field	Value
Publication number	US-2022084686-A1
Application number	US-202017019056-A
Country	US
Kind code	A1
Filing date	Sep 11, 2020
Priority date	Sep 11, 2020
Publication date	Mar 17, 2022
Grant date	—

Abstract

Aspects of the present invention disclose a method for processing bulk historical data. The method includes one or more processors identifying one or more features of messages of incoming data queries of a computing device, wherein the one or more features include structured and unstructured data. The method further includes aggregating one or more segments of bulk historic data for a plurality of individuals based at least in part on the one or more features of the messages of the incoming data queries. The method further includes determining a classification of each individual of the plurality of individuals based at least in part on the aggregated one or more segments of the bulk historic data. The method further includes prioritizing processing of the aggregated one or more segments of the bulk historic data based at least in part on the classification of each individual of the plurality of individuals.

First claim

What is claimed is:

1 . A method for processing bulk historical data, the method comprising:
identifying, by one or more processors, one or more features of messages of incoming data queries of a computing device, wherein the one or more features include structured and unstructured data; aggregating, by one or more processors, one or more segments of bulk historic data for each individual of a plurality of individuals based at least in part on the one or more features of the messages of the incoming data queries; determining, by one or more processors, a classification of each individual of the plurality of individuals based at least in part on the aggregated one or more segments of the bulk historic data; and prioritizing, by one or more processors, processing of the aggregated one or more segments of the bulk historic data based at least in part on the classification of each individual of the plurality of individuals.

2 . The method of claim 1 , further comprising:
creating, by one or more processors, one or more training sets based on the one or more features of the messages of the incoming data queries and set of criteria of two classes, wherein the two classes corresponding to a status of an individual; creating, by one or more processors, one or more testing sets based on the one or more features of the messages of the incoming data queries and the set of criteria of the two classes; and training, by one or more processors, a machine learning algorithm utilizing the one or more created training sets and testing sets.

3 . The method of claim 1 , further comprising:
extracting, by one or more processors, textual data corresponding to one or more concepts of the aggregated one or more segments of the bulk historic data of an individual of the plurality of individuals; and generating, by one or more processors, a summary of the aggregated one or more segments of the bulk historic data of the individual of the plurality of individuals based at least in part on the textual data corresponding to each of the extracted concepts.

4 . The method of claim 3 , further comprising:
identifying, by one or more processors, one or more triggering events that initiate processing of the aggregated one or more segments of bulk historic data corresponding to the individual of the plurality of individuals.

5 . The method of claim 1 , wherein prioritizing processing of the aggregated one or more segments of the bulk historic data based at least in part on the classification of each individual of the plurality of individuals, further comprises:
generating, by one or more processors, a list corresponding to a processing order of the aggregated one or more segments of the bulk historic data based at least in part on a triggering event; assigning, by one or more processors, a rank to one or more individuals of the plurality of individuals based at least in part on a probability of receiving a request to access the aggregated one or more segments of bulk historic data corresponding to the individual within a defined time period; and modifying, by one or more processors, the list corresponding to the processing order based on the assigned rank of the one or more individuals.

6 . The method of claim 1 , wherein identifying the one or more features of messages of incoming data queries of the computing device, further comprises:
determining, by one or more processors, a variable importance of each of the one or more features of messages of incoming data queries of the computing device; and selecting, by one or more processors, features of messages of incoming data queries of the computing device above a threshold value.

7 . The method of claim 1 , wherein the one or more features include demographics and patient information of structured and unstructured data and the bulk historic data is medical data of a patient.

8 . A computer program product for processing bulk historical data, the computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising: program instructions to identify one or more features of messages of incoming data queries of a computing device, wherein the one or more features include structured and unstructured data; program instructions to aggregate one or more segments of bulk historic data for each individual of a plurality of individuals based at least in part on the one or more features of the messages of the incoming data queries; program instructions to determine a classification of each individual of the plurality of individuals based at least in part on the aggregated one or more segments of the bulk historic data; and program instructions to prioritize processing of the aggregated one or more segments of the bulk historic data based at least in part on the classification of each individual of the plurality of individuals.

9 . The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, to:
create one or more training sets based on the one or more features of the messages of the incoming data queries and set of criteria of two classes, wherein the two classes corresponding to a status of an individual; create one or more testing sets based on the one or more features of the messages of the incoming data queries and the set of criteria of the two classes; and train a machine learning algorithm utilizing the one or more created training sets and testing sets.

10 . The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, to:
extract textual data corresponding to one or more concepts of the aggregated one or more segments of the bulk historic data of an individual of the plurality of individuals; and generate a summary of the aggregated one or more segments of the bulk historic data of the individual of the plurality of individuals based at least in part on the textual data corresponding to each of the extracted concepts.

11 . The computer program product of claim 10 , further comprising program instructions, stored on the one or more computer readable storage media, to:
identify one or more triggering events that initiate processing of the aggregated one or more segments of bulk historic data corresponding to the individual of the plurality of individuals.

12 . The computer program product of claim 8 , wherein the program instructions to prioritize processing of the aggregated one or more segments of the bulk historic data based at least in part on the classification of each individual of the plurality of individuals, further comprise program instructions to:
generate a list corresponding to a processing order of the aggregated one or more segments of the bulk historic data based at least in part on a triggering event; assign a rank to one or more individuals of the plurality of individuals based at least in part on a probability of receiving a request to access the aggregated one or more segments of bulk historic data corresponding to the individual within a defined time period; and modify the list corresponding to the processing order based on the assigned rank of the one or more individuals.

13 . The computer program product of claim 8 , wherein the program instructions to identify the one or more features of messages of incoming data queries of the computing device, further comprise program instructions to:
determine a variable importance of each of the one or more features of messages of incomin

Assignees

• IBM

Inventors

• Bronkalla Mark D
• Khare Amit

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N20/20

  Ensemble learning · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H50/70 Primary

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H15/00

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title