System and method for determining veracity of patient diagnoses within one or more electronic health records

Patent metadata

Field	Value
Publication number	US-10643750-B2
Application number	US-201414216230-A
Country	US
Kind code	B2
Filing date	Mar 17, 2014
Priority date	Mar 15, 2013
Publication date	May 5, 2020
Grant date	May 5, 2020

Abstract

A system and method, using one or more dimensions, that assesses the veracity of a diagnosis presently in a health care record is disclosed. The system assesses the veracity of a diagnosis based on a set of dimension values and a set of weightings. The system also provides a user interface to health care providers/caregivers to review the assessment made by the system and may include a feedback mechanism so that the system may adjust the weighting of the dimensions and improve the assessment of the diagnosis made by the system.

First claim

The invention claimed is:

1. A system for optimizing a veracity score for a particular diagnosis of a plurality of diagnoses associated with a patient, the system comprising:
a plurality of healthcare provider units, each of which comprise a display;
a store that stores, for each of the plurality of diagnoses associated with the patient, a set of weighting coefficients, a set of dimensions, and a function;
a computer server comprising executable software instructions, which when executed configure the computer server to:
retrieve a health record of a patient from at least one of the plurality of healthcare provider units and generate a diagnosis veracity score for each of the plurality of diagnoses contained in the health record of the patient, wherein the plurality of diagnoses comprises the particular diagnosis;
for the particular diagnosis:
retrieve from the store a set of values, wherein each of the set of values is associated with one of the set of dimensions for the particular diagnosis from the health record, wherein each of said set of values is selected to reflect the likelihood that the associated dimension in the set of dimensions represents a reliable indicator of the particular diagnosis, said set of dimensions comprising: the type of entity which recorded the diagnosis, the date of the diagnosis, medications taken to date that suggest the particular diagnosis, and lab values that suggest the particular diagnosis;
retrieve from the store the set of weighting coefficients for the particular diagnosis wherein each dimension has a weighting coefficient associated with it, and wherein each of the weighting coefficients is selected to reflect the likelihood that the associated dimension of the set of dimensions is a reliable indicator of the particular diagnosis relative to other dimensions in the set of dimensions;
retrieve from the store the function for the particular diagnosis, wherein said function comprises said weighting coefficients and dimensions;
determine automatically a veracity score for the particular diagnosis by multiplying each of the retrieved weighting coefficients with the associated retrieved dimension to arrive at a value and applying each of the values to the retrieved function, wherein said veracity score is a numerical percentage value;
generate, for the particular diagnosis, a visualization dashboard for display on the display of at least one of the healthcare provider units, said visualization dashboard comprising:
a table comprising:
a set of dimensions for the particular diagnosis; and
a set of values for the set of dimensions for the particular diagnosis;
wherein each of the set of dimensions for the particular diagnosis are associated within the table with one of the set of values;

the particular diagnosis veracity score; and
a caregiver evaluation tool for providing feedback regarding the particular diagnosis veracity score, wherein said caregiver evaluation tool comprises a prompt for receiving a user selection of true or false; and

receive a caregiver evaluation comprising the user selection of true or false by way of the caregiver evaluation tool and automatically optimize the set of weighting coefficients for the particular diagnosis by modifying one or more of the set of weighting coefficients which are subsequently stored in the store based upon the received caregiver evaluation to improve the accuracy of the veracity score;

wherein the function for the particular diagnosis is a logistic regression, a weighted function, or an exponential function.

2. The system of claim 1 , wherein the computer server executes software instructions to infer a new diagnosis not contained in the health record based on the veracity score of the new diagnosis.

3. The system of claim 1 , wherein the computer server executes software instructions to determine the veracity of each diagnosis of the patient contained in all health records for a patient.

Assignees

• Humana Inc

Inventors

• Ghouri Ahmed

Classifications

• G16H50/70 Primary

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

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G06N3/08

  Learning methods · CPC title

• G16H50/20

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