| CPC A61B 34/10 (2016.02) [A61B 3/0025 (2013.01); A61B 3/10 (2013.01); A61F 2/16 (2013.01); G06F 30/20 (2020.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G16H 20/40 (2018.01); G16H 50/20 (2018.01); A61B 2034/108 (2016.02); A61F 2240/002 (2013.01)] | 20 Claims |
|
1. A method comprising:
obtaining, by one or more computing devices implementing a prediction engine, one or more pre-operative measurements of an eye for assisting a user to perform an intraocular lens (IOL) implantation in the eye;
selecting, by the prediction engine from a plurality of historical IOL implantation records, a subset of historical IOL implantation records for evaluating a first plurality of prediction model candidates based at least on the one or more pre-operative measurements of the eye, wherein each of the first plurality of prediction model candidates estimates a post-operative manifest refraction in spherical equivalent (MRSE) based on a set of pre-operative eye measurements and an IOL power;
evaluating, by the prediction engine, the first plurality of prediction model candidates based on deviations between estimated post-operative MRSEs produced by each of the first plurality of prediction model candidates using eye measurement data in the selected subset of historical IOL implantation records and actual post-operative MRSEs indicated in the selected subset of historical IOL implantation records;
selecting, by the prediction engine, a first prediction model from the first plurality of prediction model candidates based on the evaluating;
calculating, by the prediction engine using the selected first prediction model, a plurality of estimated post-operative MRSE values based on a set of available IOL powers and the one or more pre-operative measurements of the eye;
determining, by the prediction engine from the set of available IOL powers, a first IOL power corresponding to a first estimated post-operative MRSE value from the plurality of estimated post-operative MRSE values that matches a predetermined post-operative MRSE value;
providing, by the prediction engine, the determined first IOL power to the user to aid in selection of an IOL for implantation in the eye;
obtaining, by the prediction engine, post-operative measurements of the eye including an actual post-operative MRSE value of the eye subsequent to the IOL being implanted in the eye; and
retraining, by the prediction engine, the selected first prediction model based on the actual post-operative MRSE value, wherein subsequent to the retraining, the retrained first prediction model is configured to be utilized for calculating another plurality of estimated post-operative MRSE values based on the set of available IOL powers and one or more pre-operative measurements of another eye.
|