Abstract
Purpose: Our work introduces a highly accurate, safe, and sufficiently explicable machine-learning (artificial intelligence) model of intraocular lens power (IOL) translating into better post-surgical outcomes for patients with cataracts. We also demonstrate its improved predictive accuracy over previous formulas. Methods: We collected retrospective eye measurement data on 5,331 eyes from 3,276 patients across multiple centers who received a lens implantation during cataract surgery. The dependent measure is the post-operative manifest spherical equivalent error from intended and the independent variables are the patient- and eye-specific characteristics. This dataset was split so that one subset was for formula construction and the other for validating our new formula. Data excluded fellow eyes, so as not to confound the prediction with bilateral eyes. Results: Our formula is three times more precise than reported studies with a median absolute IOL error of 0.204 diopters (D). When converted to absolute predictive refraction errors on the cornea, the median error is 0.137 D which is close to the IOL manufacturer tolerance. These estimates are validated out-of-sample and thus are expected to reflect the future performance of our prediction formula, especially since our data were collected from a wide variety of patients, clinics, and manufacturers. Conclusion: The increased precision of IOL power calculations has the potential to optimize patient positive refractive outcomes. Our model also provides uncertainty plots that can be used in tandem with the clinician’s expertise and previous formula output, further enhancing the safety. Translational relavance: Our new machine learning process has the potential to significantly improve patient IOL refractive outcomes safely.
Highlights
Pre-operative intraocular lens (IOL) power predictions are essential to patient refractive outcomes on implanted lenses in cataract surgery and ophthalmologists have been interested in accurate predictions for a long time
These estimates are validated out-of-sample and are expected to reflect the future performance of our prediction formula, especially since our data were collected from a wide variety of patients, clinics, and manufacturers
Our model provides uncertainty plots that can be used in tandem with the clinician’s expertise and previous formula output, further enhancing the safety
Summary
Pre-operative intraocular lens (IOL) power predictions are essential to patient refractive outcomes on implanted lenses in cataract surgery and ophthalmologists have been interested in accurate predictions for a long time. Before the introduction of mathematical prediction formulas, IOL power was inferred from patient history using educated guesses This changed in 1981 with the first known formula, the SRK equation, IOL power A – 2.5L – 0.9K, where L is the axial length in mm, K is the average keratometry in diopters, and A is a constant dependent on properties of the manufactured lens being implanted. Hill et al designed a radial basis function neural net that extracts features and relationships from a large dataset to predict the optimal emmetropic IOL power ( forward termed “RBF 1.0 calculator”). This computational process is available on the ASCRS website and commercially at RBFcalculator.com. For the state of the art, standard deviation of prediction error in refraction is between 0.361 and 0.433 (Cooke and Cooke, 2016)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
