Intraocular Lens Selection Prediction Engine
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing prediction models for selecting intraocular lens (IOL) power in cataract surgery often produce suboptimal results due to variability in patient conditions, leading to inconsistent post-operative vision outcomes.
Innovation Solution
A method using a prediction engine to select the most appropriate IOL power by evaluating multiple prediction model candidates based on pre-operative eye measurements and historical IOL implantation records, thereby optimizing post-operative manifest refraction in spherical equivalent (MRSE).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed prediction model is used to determine IOL power in all circumstances, then the device complexity is reduced, but the manufacturing precision (accuracy of IOL power selection) deteriorates
Solution Approach 1:
The patent implements a dynamic prediction model selection system that adapts to different patient conditions. Instead of using a single fixed model, the system evaluates multiple prediction model candidates and selects the most appropriate one based on the specific patient's pre-operative measurements and characteristics, thereby maintaining high accuracy across diverse circumstances while managing complexity through automated selection
Solution Approach 2:
The system changes the parameter of prediction model selection based on patient-specific parameters. By evaluating multiple prediction model candidates and selecting among them based on patient characteristics and pre-operative measurements, the system adapts the prediction approach to match the specific clinical scenario, improving accuracy without requiring manual intervention
2Manufacturing precision
If multiple prediction model candidates are evaluated and selected based on patient conditions, then the IOL power selection accuracy is improved, but the device complexity increases
Solution Approach 1:
The prediction engine performs self-service by automatically evaluating multiple prediction model candidates and selecting the most appropriate one based on patient conditions. The system autonomously compares different models, assesses their suitability for the specific patient case, and makes the selection without requiring manual intervention, thereby managing the increased complexity through automation
Solution Approach 2:
The system incorporates feedback mechanisms where the prediction engine evaluates the performance of multiple prediction model candidates based on patient-specific parameters and selects the model that best fits the current case. This feedback-driven selection process ensures optimal accuracy while the automated nature of the feedback loop manages the system complexity
Data Source
AI summary
Systems and methods for intraocular lens selection include obtaining one or more pre-operative measurements of an eye; selecting, from a plurality of historical IOL implantation records, a subset of historical IOL implantation records for evaluating a first plurality of prediction model candidates; evaluating the first plurality of prediction model candidates; selecting a first prediction model from the first plurality of prediction model candidates based on the evaluating; calculating, using the selected first prediction model, a plurality of estimated post-operative MRSE values based on a set of IOL powers and the one or more pre-operative measurements of the eye; determining a first IOL power corresponding to a first estimated post-operative MRSE value that matches a predetermined post-operative MRSE value; and providing the determined first IOL power to a user to aid in selection of an IOL for implantation in the eye.