Forecasting eye condition progression for eye patients

Patent metadata

Field	Value
Publication number	US-10667680-B2
Application number	US-201715418667-A
Country	US
Kind code	B2
Filing date	Jan 27, 2017
Priority date	Dec 9, 2016
Publication date	Jun 2, 2020
Grant date	Jun 2, 2020

Abstract

Aspects extend to methods, systems, and computer program products for forecasting eye condition progression for eye patients. When a patient visits an eye practitioner, the patient (or when appropriate their guardian) may be interested in the current eye condition as well as a prediction of eye condition progression in the future and/or as the patient ages. Aspects of the invention can be used to predict the progress of an eye condition for a patient (e.g., a child) at a number of different post-examination times after an examination. Predicting the progress of an eye condition for a patient over time can be used to assist the eye practitioner in tailoring a treatment plan and/or tailoring a subsequent examination schedule for the patient.

First claim

What is claimed:

1. A computer system, the computer system comprising:
one or more hardware processors;
system memory coupled to the one or more hardware processors, the system memory storing instructions that are executable by the one or more hardware processors;
the one or more hardware processors executing the instructions stored in the system memory to predict a sphere for a patient's eyes, including the following:
access eye characteristic data for the patient's eyes, the eye characteristic data acquired during an eye examination performed on the patient, the eye characteristic data including one or more measured sphere values for the sphere of the patient's eyes;
access demographic data for the patient;
input the eye characteristic data, including the one or more measured sphere values for the sphere of the patient's eyes, and the demographic data into a predictive model in the system memory, the predictive model formulated from other patient data acquired during other eye examinations for a plurality of other patients, the other patient data including, for each other patient included in the plurality of other patients, one or more measured sphere values for the sphere of the other patient's eyes, other eye characteristic data for the other patient's eyes, and demographic data for the other patient, the predictive model transforming the eye characteristic data for the patient, the demographic data for the patient, and the other patient data through linear regression to:
forecast sphere values for the sphere of the patient's eyes at a plurality of different post examination time periods, the forecast sphere values inferred from the eye characteristic data for the patient, including the one or more measured sphere values for the sphere of the patient's eyes, and the demographic data for the patient in view of the other patient data; and
formulate a time series chart of sphere for the patient's eyes from the forecast sphere values, the time series chart forecasting likely sphere values for the sphere of the patient's eyes over a plurality of different time periods in the future; and

output the formulated time series chart as a prediction of changes to the sphere of the patient's eyes as the patient ages.

2. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to access the eye characteristic data for the patient's eyes comprises the one or more hardware processors executing the instructions stored in the system memory to access one or more of: cylinder, axis, uncorrected visual acuity (UCVA), and best-corrected visual acuity (BCVA) for the patient.

3. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to access the eye characteristic data for the patient's eyes comprises the one or more hardware processors executing the instructions stored in the system memory to access results from a topological map of the patient's eyes.

4. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to return the formulated time series chart comprises the one or more hardware processors executing the instructions stored in the system memory to return a time series chart indicating predicted sphere for the patient's eyes at six months, one year, and two years after the eye examination.

5. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to access the eye characteristic data for the patient's eyes comprises the one or more hardware processors executing the instructions stored in the system memory to access the eye characteristic data for a pediatric patient.

6. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to transform the eye characteristic data for the patient, the demographic data for the patient, and the other patient data through linear regression comprises the one or more hardware processors executing the instructions stored in the system memory to transform the eye characteristic data for the patient, the demographic data for the patient, and the other patient data through one of: gradient tree boosting regression, online gradient descent based regression, neural network based regression, or Poisson regression.

7. The computer system of claim 1 , wherein the one or more hardware processors executing the instructions stored in the system memory to forecast sphere values for the sphere of the patient's eyes at the plurality of different post examination time periods comprises the one or more hardware processors executing the instructions stored in the system memory to forecast the sphere of the patient's eyes at the plurality of different post examination time periods based on sphere values for the sphere of one or more other patients, from among the plurality of other patients, having a specified similarity of demographic data to the demographic data of the patient.

8. The computer system of claim 1 , further comprising the one or more hardware processors executing the instructions stored in the system memory to tailor an eye care plan for the patient based on the formulated time series chart.

9. A computer system, the computer system comprising:
one or more hardware processors;
system memory coupled to the one or more hardware processors, the system memory storing instructions that are executable by the one or more hardware processors;
the one or more hardware processors executing the instructions stored in the system memory to predict a sphere for a patient's eyes, including the following:
access eye characteristic data for the patient's eyes, the eye characteristic data acquired during a plurality of different eye examinations performed on the patient, each eye examination included in the plurality of different eye examinations performed at a different time and separated from a next subsequent eye exam included in the plurality of different eye examinations by a time gap, for each of the plurality of different eye examinations, the eye characteristic data including one or more measured sphere values for the sphere of the patient's eyes;
access demographic data for the patient;
input the eye characteristic data, time gaps, and the demographic data into a predictive model, the eye characteristic data including, for each of the plurality of different eye examinations, the one or more measured sphere values for the sphere of the patient's eyes, the predictive model formulated from other patient data acquired during other eye examinations for a plurality of other patients, the other patient data including, for each other patient included in the plurality of other patients, one or more measured sphere values for the sphere of the other patient's eyes, other eye characteristic data for the other patient's eyes, and demographic data for the other patient, the predictive model transforming the eye characteristic data for the patient, the time gaps, and the demographic data for the patient through linear regression to:
forecast sphere values for the sphere of the patient's eyes at a plurality of different post examination time periods, the forecast sphere values inferred from the one or more measured sphere values for the sphere of the patient's eyes acquired during different eye examinations for the patient and from the demographic data for the patient in view of the time gaps separating each of the plurality of different eye examinations; and
formulate a time series chart of sphere for the patient's eyes from the forecast sphere values, the time series chart

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Gupta Manish
• Gupta Prashant
• Mustafi Joy

Classifications

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B5/7275

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title

• G16H50/50

  for simulation or modelling of medical disorders · CPC title

• A61B3/028

  for testing visual acuity; for determination of refraction, e.g. phoropters · CPC title

• A61B3/0025 Primary

  characterised by electronic signal processing, e.g. eye models · CPC title