Patent US10426551

Personalized refractive surgery recommendations for eye patients
[+] Show Details

US10426551

1. A computer system, the computer system comprising: one or more hardware processors; (8) (2)

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 provide a refractive surgery recommendation for a patient, including the following: access pre-operative eye characteristic data for the patient's eyes, the pre-operative eye characteristic data taken from pre-operative diagnostic procedures performed on the patient;

access demographic data for the patient;

input the pre-operative eye characteristic data and demographic data into a predictive model in the system memory, the predictive model formulated from other patient data for a plurality of other patients that previously had refractive surgery, the other patient data including, for each other patient included in the plurality of other patients, one or more of: pre-operative eye characteristic data and demographic data, a refractive surgery type, and one or more post-operative uncorrected visual acuity (UCVA) values, each of the one or more post-operative uncorrected visual acuity (UCVA) values measured at a different post-operative time after refractive surgery, the predictive model transforming the pre-operative eye characteristic data and the demographic data of the patient's eye through linear regression to: predict one or more post-operative uncorrected visual acuity (UCVA) maps for the patient, each of the one or more post-operative uncorrected visual acuity (UCVA) maps inferred for a corresponding refractive surgery type based on the patient's pre-operative eye characteristic data and demographic data in view of the other patient data, each uncorrected visual acuity (UCVA) map predicting post-operative uncorrected visual acuity (UCVA) values for the patient at one or more post-operative time periods for the corresponding refractive surgery type; and

recommend the selected refractive surgery type as the refractive surgery recommendation for the patient.

2. The computer system of claim 1, wherein the one or more hardware processors executing the instructions stored in the system memory to access pre-operative 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: uncorrected visual acuity (UCVA), uncorrected near vision, corrected near vision, best-corrected visual acuity (BCVA) with corrective lenses, sphere, cylinder, axis, spherical equivalent, slit-lamp exam results, intraocular pressure, Steep-K, Flat-K, Axis@Flat-K, and corneal thickness. (0)

3. The computer system of claim 1, wherein the one or more hardware processors executing the instructions stored in the system memory to access pre-operative 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 topological map of the patient's eyes. (0)

4. The computer system of claim 1, wherein the one or more hardware processors executing the instructions stored in the system memory to recommend the selected refractive surgery type as the refractive surgery recommendation for the patient comprises the one or more hardware processors executing the instructions stored in the system memory to recommend a refractive surgery type selected from among: Plano-scan-LASIK, Aspheric-LASIK, Tissue-saving-LASIK, or Wavefront-Guided-LASIK. (0)

5. The computer system of claim 1, wherein the other patient data further includes surgery parameters for each other patient included in the plurality of other, the surgery parameters used for a refractive surgery of the refractive surgery type performed on the other patient. (0)

6. The computer system of claim 1, further comprising the one or more hardware processors executing the instructions stored in the system memory to transform surgery parameters for a subset of the plurality of other patients through linear regression to predict surgery parameters for the patient, the surgery parameters predicted from surgery parameters used in other refractive surgeries of the selected refractive surgery type. (1) (0)

8. The computer system of claim 1, wherein the one or more hardware processors executing the instructions stored in the system memory to transform the pre-operative eye characteristic data, demographic data, and other patient data through linear regression comprises the one or more hardware processors executing the instructions stored in the system memory to transform the pre-operative eye characteristic data, demographic data, and other patient data through one of: gradient tree basting regression, online gradient descent based regression, neural network based regression, or Poisson regression. (0)

9. The computer system of claim 1, further comprising the one or more hardware processors executing the instructions stored in the system memory to perform one or more of: (1) (2)

replace a missing value for a feature in the other patient data with an average value for the feature, the average value for the feature averaged from other values for the feature contained in the other patient data; and

replace a missing value for a feature in the other patient data with a most frequently used value for the feature contained in the other patient data.

10. The computer system of claim 9, wherein the predictive model being formulated from other patient data comprises the predictive model being formulated based on one or more categorical features contained in the other patient data, each categorical feature having an enumerated plurality of specified possible values. (1) (0)

12. The computer system of claim 1, wherein the one or more hardware processors executing the instructions stored in the system memory to recommend the selected refractive surgery type as the refractive surgery recommendation for the patient comprise the one or more hardware processors executing the instructions stored in the system memory to recommend a post-operative uncorrected visual acuity (UCVA) map for the patient, the post-operative uncorrected visual acuity (UCVA) map predicting uncorrected visual acuity (UCVA) for the patient for one or more post-operative time periods after refractive surgery of the selected refractive surgery type. (0)

13. A method for use at a computer system, the method for providing a refractive surgery recommendation for a patient, the method comprising the following: accessing pre-operative eye characteristic data for the patient's eyes, the pre-operative eye characteristic data taken from pre-operative diagnostic procedures performed on the patient; (4) (3)

accessing demographic data for the patient;

inputting the pre-operative eye characteristic data and demographic data into a predictive model, the predictive model formulated from other patient data for a plurality of other patients that previously had refractive surgery, the other patient data including, for each other patient included in the plurality of other patients, one or more of: pre-operative eye characteristic data, demographic data, a refractive surgery type, and one or more post-operative uncorrected visual acuity (UCVA) values, each of the one or more post-operative uncorrected visual acuity (UCVA) values measured at a different post-operative time after refractive surgery, the predictive model transforming the pre-operative eye characteristic data and the demographic data of the patient's eye through linear regression, including: predicting one or more post-operative uncorrected visual acuity (UCVA) maps for the patient, each of the one or more post-operative uncorrected visual acuity (UCVA) maps inferred for a corresponding refractive surgery type based on the patient's pre-operative eye characteristic data and demographic data in view of the other patient data, each uncorrected visual acuity (UCVA) map predicting post-operative uncorrected visual acuity (UCVA) values for the patient at one or more post-operative time periods for the corresponding refractive surgery type; and

matching the patient to a selected refractive surgery type based on predicted post-operative uncorrected visual acuity (UCVA) values in the one or more uncorrected visual acuity (UCVA) maps for the patient; and

recommending the selected refractive surgery type as the refractive surgery recommendation for the patient.

14. The method of claim 13, wherein accessing pre-operative eye characteristic data for the patient's eyes comprises accessing one or more of: uncorrected visual acuity (UCVA), uncorrected near vision, corrected near vision, best corrected visual acuity (BCVA) with corrective lenses, sphere, cylinder, axis, spherical equivalent, slit-lamp exam results, intraocular pressure, Steep-K, Flat-K, Axis@Flat-K, and corneal thickness. (0)

15. The method of claim 13, further comprising transforming surgery parameters for a subset of the plurality of other patients through linear regression to predict surgery parameters for the patient, the surgery parameters predicted from surgery parameters used in other refractive surgeries of the selected refractive surgery type. (1) (0)

17. The method of claim 13, wherein the predictive model being formulated from other patient data comprises the predictive model being formulated based on one or more categorical features contained in the other patient data, each categorical feature having an enumerated plurality of specified possible values. (1) (0)

19. The method of claim 13, wherein recommending the selected refractive surgery type comprises recommending a post-operative uncorrected visual acuity (UCVA) map for the patient, the post-operative uncorrected visual acuity (UCVA) map predicting uncorrected visual acuity (UCVA) for the patient for one or more post-operative time periods after refractive surgery of the selected refractive surgery type. (0)

20. A non-transitory computer-readable storage medium for use at a computer system, the non-transitory computer-readable storage medium comprising computer-executable instructions that, when executed at a processor, cause the computer system to perform a method for providing a refractive surgery recommendation for a patient, the method comprising: (0) (3)

accessing pre-operative eye characteristic data for the patient's eyes, the pre-operative eye characteristic data taken from pre-operative diagnostic procedures performed on the patient;

accessing demographic data for the patient;

inputting the pre-operative eye characteristic data and demographic data into a predictive model, the predictive model formulated from other patient data for a plurality of other patients that previously had refractive surgery, the other patient data including, for each other patient included in the plurality of other patients, one or more of: pre-operative eye characteristic data, demographic data, a refractive surgery type, and one or more post-operative uncorrected visual acuity (UCVA) values, each of the one or more post-operative uncorrected visual acuity (UCVA) values measured at a different post-operative time after refractive surgery, the predictive model transforming the pre-operative eye characteristic data and the demographic data of the patient's eye through linear regression to: predict one or more post-operative uncorrected visual acuity (UCVA) maps for the patient, each of the one or more post-operative uncorrected visual acuity (UCVA) maps inferred for a corresponding refractive surgery type based on the patient's pre-operative eye characteristic data and demographic data in view of the other patient data, each uncorrected visual acuity (UCVA) map predicting post-operative uncorrected visual acuity (UCVA) values for the patient at one or more post-operative time periods for the corresponding refractive surgery type; and

match the patient to a selected refractive surgery type based on predicted post-operative uncorrected visual acuity (UCVA) values in the one or more uncorrected visual acuity (UCVA) maps for the patient; and recommend the selected refractive surgery type as the refractive surgery recommendation for the patient.

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Patent US10426551

Personalized refractive surgery recommendations for eye patients

Patent Matrix® Search