Multifocal Contact Lens Compatibility Prediction for Presbyopia Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fitting multi-focal contact lenses is challenging for users due to the difficulty in predicting the outcome, leading to multiple visits and high costs, with eye-care professionals reluctant to recommend certain types of lenses.
Innovation Solution
A system using machine learning to predict lens compatibility by receiving biometric and performance metrics, generating a compatibility index, and providing a report to assist eye-care professionals in recommending lenses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional trial-and-error fitting method is used, then contact lens compatibility can be determined through multiple visits, but the process becomes time-consuming and costly with multiple follow-up visits required
Solution Approach 1:
The system performs preliminary action by using machine learning models to predict contact lens compatibility before the actual fitting process. The model analyzes patient characteristics and ECP performance metrics in advance to determine the most suitable contact lens type, eliminating the need for multiple trial visits and follow-ups while maintaining high prediction accuracy.
Solution Approach 2:
The patent replaces the mechanical trial-and-error fitting process with an information-based machine learning prediction system. Instead of physically trying multiple contact lens types and undergoing repeated visits, the system uses algorithms to process patient data and ECP performance information, substituting the physical fitting mechanism with a computational prediction mechanism.
2Ease of operation
If eye-care professionals manually evaluate each patient, then personalized recommendations can be made, but the process becomes complex and time-consuming requiring multiple visits
Solution Approach 1:
The system implements self-service by enabling the machine learning model to automatically perform the evaluation and prediction tasks that previously required manual ECP intervention. The model autonomously processes patient characteristics, analyzes ECP performance metrics, and generates compatibility predictions without requiring complex manual evaluation procedures, thereby simplifying the overall process.
Solution Approach 2:
The machine learning model serves as an intermediary between the ECP and the contact lens selection process. Instead of the ECP directly evaluating each patient through complex manual procedures, the model acts as an intermediate system that processes information, analyzes patterns, and provides compatibility predictions, thereby mediating the complex evaluation process and simplifying it for both ECPs and patients.
3Reliability
If ECPs recommend conservative lens types, then patient safety is maintained, but innovative vision correction solutions like multi-focal contact lenses are underutilized
Solution Approach 1:
The system applies parameter changes by dynamically adjusting recommendation thresholds and compatibility criteria based on individual ECP performance metrics and patient characteristics. The model doesn't use fixed conservative thresholds but adapts the acceptance criteria for innovative lens types based on real-time analysis of ECP success rates and patient outcomes, allowing safe recommendation of diverse lens types when evidence supports it.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring ECP performance metrics and patient outcomes to refine future recommendations. The model uses feedback from actual patient responses and lens performance data to adjust its predictions, enabling ECPs to confidently recommend innovative lens types when the feedback indicates high likelihood of success, thereby balancing safety with versatility.
Data Source
AI summary
Systems and methods for determining a compatibility between a multi-focal contact lens and a patient seeking presbyopia vision correction include receiving, from a first device associated with a first eye-care professional (ECP), a request for selecting a contact lens for a consumer, wherein the request comprises biometric information associated with the consumer; obtaining a performance metric associated with the first ECP; determining, using the machine learning model and based on the performance metric, a customized compatibility index indicating a compatibility between a particular contact lens and the consumer for the first ECP; and presenting a report indicating the compatibility index on the first device. Additional systems, methods, and non-transitory machine-readable mediums are also provided.