scholarly journals Gradient Boosting Decision Tree Algorithm for the Prediction of Postoperative Intraocular Lens Position in Cataract Surgery

2020 ◽  
Author(s):  
Tingyang Li ◽  
Kevin Yang ◽  
Joshua Stein ◽  
Nambi Nallasamy
Keyword(s):  
Decision Tree ◽  
Cataract Surgery ◽  
Intraocular Lens ◽  
Anterior Chamber Depth ◽  
Absolute Error ◽  
Gradient Boosting ◽  
Tree Model ◽  
Lens Position ◽  
Iol Power ◽  
Testing Set

Purpose: To develop a method for predicting postoperative anterior chamber depth (ACD) in cataract surgery patients based on preoperative biometry, demographics, and intraocular lens (IOL) power. Methods: Patients who underwent cataract surgery and had both preoperative and postoperative biometry measurements were included. Patient demographics and IOL power were collected from the Sight Outcomes Research Collaborative (SOURCE) database. A gradient boosting decision tree model was developed to predict the postoperative ACD. The mean absolute error (MAE) and median absolute error (MedAE) were used as evaluation metrics. The performance of the proposed method was compared to five existing formulas. Results: 847 patients were assigned randomly in a 4:1 ratio to a training/validation set (678 patients) and a testing set (169 patients). Using preoperative biometry and patient sex as predictors, the presented method achieved an MAE of 0.106 (SD: 0.098) on the testing set, and a MedAE of 0.082. MAE was significantly lower than that of the five existing methods (p < 0.01). When keratometry was excluded, our method attained an MAE of 0.123 (SD: 0.109), and a MedAE of 0.093. When IOL power was used as an additional predictor, our method achieved an MAE of 0.105 (SD: 0.091) and a MedAE of 0.080. Conclusions: The presented machine learning method achieved accuracy surpassing that of previously reported methods in the prediction of postoperative ACD. Translational Relevance: Increasing accuracy of postoperative ACD prediction with the presented algorithm has the potential to improve refractive outcomes in cataract surgery.

scholarly journals Improving the prediction of effective lens position for intraocular lens power calculations

2020 ◽  
Vol 17 (2) ◽  
pp. 233-242
Author(s):  
Juanita Noeline Chui ◽  
Keith Ong
Keyword(s):  
Cataract Surgery ◽  
Intraocular Lens ◽  
Sagittal Plane ◽  
Anterior Chamber Depth ◽  
Posterior Chamber ◽  
Power Calculation ◽  
Iol Power Calculation ◽  
Lens Position ◽  
Iol Power ◽  
Corneal Apex

Purpose: Achieving the desired post-operative refraction in cataract surgery requires accurate calculations for intraocular lens (IOL) power. Latest-generation formulae use anterior-chamber depth (ACD)—the distance from the corneal apex to the anterior surface of the lens—as one of the parameters to predict the post-operative IOL position within the eye, termed the effective lens position (ELP). Significant discrepancies between predicted and actual ELP result in refractive surprise. This study aims to improve the predictability of ELP. We hypothesise that predictions based on the distance from the corneal apex to the mid-sagittal plane of the cataractous lens would more accurately reflect the position of the principal plane of the non-angulated IOL within the capsular bag. Accordingly, we propose that predictions derived from ACD + ½LT (length thickness) would be superior to those from ACD alone. Design: Retrospective cohort study, comparing ELP predictions derived from ACD to aproposed prediction parameter. Method: This retrospective study includes data from 162 consecutive cataract surgery cases, with posterior-chamber IOL (AlconSN60WF) implantation. Pre- and postoperative biometric measurements were made using the IOLMaster700 (ZEISS, Jena, Germany). The accuracy and reliability of ELP predictions derived from ACD and ACD + ½LT were compared using software-aided analyses. Results: An overall reduction in average ELP prediction error (PEELP) was achieved using the proposed parameter (root-mean-square-error [RMSE] = 0.50 mm), compared to ACD (RMSE = 1.57 mm). The mean percentage PEELP, comparing between eyes of different axial lengths, was 9.88% ± 3.48% and −34.9% ± 4.79% for predictions derived from ACD + ½LT and ACD, respectively. A 44.10% ± 5.22% mean of differences was observed (p < 0.001). Conclusion: ACD + ½LT predicts ELP with greater accuracy and reliability than ACD alone; its use in IOL power calculation formulae may improve refractive outcomes.

scholarly journals Relationship between Medium-Term Changes in Intraocular Lens Position and Refraction after Cataract Surgery with Two Different Models of Monofocal Lenses

2021 ◽  
Vol 10 (17) ◽  
pp. 3856
Author(s):  
Hideki Fukumitsu ◽  
Vicent J. Camps ◽  
Sara Miraflores ◽  
David P. Piñero
Keyword(s):  
Cataract Surgery ◽  
Intraocular Lens ◽  
Statistical Significance ◽  
Anterior Chamber Depth ◽  
Strong Correlations ◽  
Lens Position ◽  
Single Piece ◽  
Iol Power ◽  
The Difference ◽  
Group 2

The aim of this prospective descriptive study was to characterize the variations of the clinical effective lens position (ELP) (considering paraxial optics and postoperative data) and the intraocular lens (IOL) position, using “eye” data gathered from a 6-month follow-up of patients who underwent uneventful cataract surgery. Patients were implanted with two different monofocal IOLs: AcrySof IQ SN60WF (Alcon) (Group 1, 247 eyes) and Akreos MI60L (Bausch & Lomb) (Group 2, 104 eyes). No significant differences were found between groups concerning spherical equivalent (SE), axial length, and clinical ELP changes, from 1 to 6 months after surgery (p ≥ 0.516). A more positive change in postoperative anterior chamber depth was found in Group 2, but the difference did not reach statistical significance (p = 0.065). No significant moderate to strong correlations were found between the changes in clinical ELP and preoperative data. The correlation between the changes in SE and clinical ELP over time was strong and statistically significant (groups 1 and 2: r = 0.957 and r = 0.993, p < 0.001). In conclusion, changes in refraction from 1 to 6 months after cataract surgery, with single-piece monofocal IOLs, are not clinically relevant, which correlates with the presence of good positional stability. These changes cannot be predicted preoperatively and considered in IOL power calculations.

scholarly journals AI-powered effective lens position prediction improves the accuracy of existing lens formulas

2021 ◽  
pp. bjophthalmol-2020-318321
Author(s):  
Tingyang Li ◽  
Joshua Stein ◽  
Nambi Nallasamy
Keyword(s):  
Anterior Chamber Depth ◽  
Absolute Error ◽  
University Of Michigan ◽  
Lens Position ◽  
Testing Dataset ◽  
Iol Power ◽  
Position Prediction ◽  
The Mean ◽  
Postoperative Anterior Chamber Depth ◽  
Testing Set

AimsTo assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves the refraction prediction performance of existing intraocular lens (IOL) calculation formulas.MethodsA dataset of 4806 patients with cataract was gathered at the Kellogg Eye Center, University of Michigan, and split into a training set (80% of patients, 5761 eyes) and a testing set (20% of patients, 961 eyes). A previously developed ML-based method was used to predict the postoperative ACD based on preoperative biometry. This ML-based postoperative ACD was integrated into new effective lens position (ELP) predictions using regression models to rescale the ML output for each of four existing formulas (Haigis, Hoffer Q, Holladay and SRK/T). The performance of the formulas with ML-modified ELP was compared using a testing dataset. Performance was measured by the mean absolute error (MAE) in refraction prediction.ResultsWhen the ELP was replaced with a linear combination of the original ELP and the ML-predicted ELP, the MAEs±SD (in Diopters) in the testing set were: 0.356±0.329 for Haigis, 0.352±0.319 for Hoffer Q, 0.371±0.336 for Holladay, and 0.361±0.331 for SRK/T which were significantly lower (p<0.05) than those of the original formulas: 0.373±0.328 for Haigis, 0.408±0.337 for Hoffer Q, 0.384±0.341 for Holladay and 0.394±0.351 for SRK/T.ConclusionUsing a more accurately predicted postoperative ACD significantly improves the prediction accuracy of four existing IOL power formulas.

scholarly journals AI-Powered Effective Lens Position Prediction Improves the Accuracy of Existing Lens Formulas

2020 ◽  
Author(s):  
Tingyang Li ◽  
Joshua D. Stein ◽  
Nambi Nallasamy
Keyword(s):  
Anterior Chamber Depth ◽  
Absolute Error ◽  
University Of Michigan ◽  
Lens Position ◽  
Testing Dataset ◽  
Iol Power ◽  
Position Prediction ◽  
The Mean ◽  
Postoperative Anterior Chamber Depth ◽  
Testing Set

ABSTRACTAimsTo assess whether incorporating a machine learning (ML) method for accurate prediction of postoperative anterior chamber depth (ACD) improves the refraction prediction performance of existing intraocular lens (IOL) calculation formulas.MethodsA dataset of 4806 cataract patients were gathered at the Kellogg Eye Center, University of Michigan, and split into a training set (80% of patients, 5761 eyes) and a testing set (20% of patients, 961 eyes). A previously developed ML-based method was used to predict the postoperative ACD based on preoperative biometry. This ML-based postoperative ACD was integrated into new effective lens position (ELP) predictions using regression models to rescale the ML output for each of four existing formulas (Haigis, Hoffer Q, Holladay, and SRK/T). The performance of the formulas with ML-modified ELP was compared using a testing dataset. Performance was measured by the mean absolute error (MAE) in refraction prediction.ResultsWhen the ELP was replaced with a linear combination of the original ELP and the ML-predicted ELP, the MAEs ± SD (in Diopters) in the testing set were: 0.356 ± 0.329 for Haigis, 0.352 ± 0.319 for Hoffer Q, 0.371 ± 0.336 for Holladay, and 0.361 ± 0.331 for SRK/T which were significantly lower than those of the original formulas: 0.373 ± 0.328 for Haigis, 0.408 ± 0.337 for Hoffer Q, 0.384 ± 0.341 for Holladay, and 0.394 ± 0.351 for SRK/T.ConclusionUsing a more accurately predicted postoperative ACD significantly improves the prediction accuracy of four existing IOL power formulas.

scholarly journals Relationship between Crystalline Lens Thickness and Shape and the Identification of Anterior Ocular Segment Parameters for Predicting the Intraocular Lens Position after Cataract Surgery

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Tsukasa Satou ◽  
Kimiya Shimizu ◽  
Shuntaro Tsunehiro ◽  
Akihito Igarashi ◽  
Sayaka Kato ◽  
...  
Keyword(s):  
Cataract Surgery ◽  
Intraocular Lens ◽  
Prediction Error ◽  
Anterior Segment ◽  
Anterior Chamber Depth ◽  
Crystalline Lens ◽  
Lens Thickness ◽  
Lens Position ◽  
The Difference ◽  
Segment Data

Purpose. This study was performed to investigate the relationships among crystalline lens shape, actual intraocular lens (IOL) position, and crystalline lens thickness (LT), as measured by anterior segment optical coherence tomography (AS-OCT), and to determine anterior ocular segment parameters that predict postoperative IOL position. Methods. Seventy-nine eyes of 79 patients who underwent uneventful cataract surgery were enrolled. For crystalline lens preoperative anterior segment data, the LT, and anterior, equatorial, and posterior surface depths (ASD, ESD, and PSD, respectively) of crystalline lenses were quantitatively determined. For postoperative anterior segment data, the actual IOL position was quantified. Moreover, the following correlations were analyzed: LT with the ASD, ESD, PSD, and IOL position; IOL position with the ASD, ESD, and PSD; and refractive prediction error with the difference between the predicted postoperative anterior chamber depth (ACD) of the SRK/T formula and the IOL position, ASD, ESD, and PSD (each depth minus the predicted postoperative ACD of the SRK/T formula). Results. The LT was significantly correlated with the ASD (r = -0.65) and PSD (r = 0.41), whereas it was not correlated with the ESD or IOL position. The IOL position was significantly correlated with the ASD (r = 0.67), ESD (r = 0.72), and PSD (r = 0.74). The refractive prediction error was significantly correlated with the difference between the predicted postoperative ACD of the SRK/T formula and the IOL position (r = 0.65), ASD (r = 0.46), ESD (r = 0.54), and PSD (r = 0.58). Conclusions. The ESD and PSD obtained using AS-OCT were highly correlated with the IOL position and significantly correlated with the refractive prediction error. These findings suggest that the ESD and PSD may enhance the accuracy of actual IOL position prediction.

scholarly journals Comparison of the Kane formula with existing formulas for intraocular lens power selection

2019 ◽  
Vol 4 (1) ◽  
pp. e000251 ◽  
Author(s):  
Benjamin J Connell ◽  
Jack X Kane
Keyword(s):  
Intraocular Lens ◽  
Axial Length ◽  
Prediction Error ◽  
Anterior Chamber Depth ◽  
Absolute Error ◽  
Case Review ◽  
Refractive Outcome ◽  
Retrospective Case ◽  
Length Range ◽  
Iol Power

ObjectiveTo compare the accuracy of a new intraocular lens (IOL) power formula (Kane formula) with existing formulas using IOLMaster, predominantly model 3, biometry (measures variables axial length, keratometry and anterior chamber depth) and optimised lens constants. To compare the accuracy of three new or updated IOL power formulas (Kane, Hill-RBF V.2.0 and Holladay 2 with new axial length adjustment) compared with existing formulas (Olsen, Barrett Universal 2, Haigis, Holladay 1, Hoffer Q, SRK/T).Methods and analysisA single surgeon retrospective case review was performed from patients having uneventful cataract surgery with Acrysof IQ SN60WF IOL implantation over 11 years in a Melbourne private practice. Using optimised lens constants, the predicted refractive outcome for each formula was calculated for each patient. This was compared with the actual refractive outcome to give the prediction error. Eyes were separated into subgroups based on axial length as follows: short (≤22.0 mm), medium (>22.0 to <26.0 mm) and long (≥26.0 mm).ResultsThe study included 846 patients. Over the entire axial length range, the Kane formula had the lowest mean absolute prediction error (p<0.001, all formulas). The mean postoperative difference from intended outcome for the Kane formula was −0.14+0.27×1 (95% LCL −1.52+0.93×43; 95% UCL +0.54+1.03×149). The formula demonstrated the lowest absolute error in the medium axial length range (p<0.001). In the short and long axial length groups, no formula demonstrated a significantly lower absolute mean prediction error.ConclusionUsing three variables (AL, K, ACD), the Kane formula was a more accurate predictor of actual postoperative refraction than the other formulae under investigation. There were not enough eyes of short or long axial length to adequately power statistical comparisons within axial length subgroups.

scholarly journals Evaluating newer generation intraocular lens calculation formulas in manual versus femtosecond laser-assisted cataract surgery

2021 ◽  
Vol 14 (8) ◽  
pp. 1174-1178
Author(s):  
Harrish Nithianandan ◽  
◽  
Eric S. Tam ◽  
Hannah Chiu ◽  
Rajiv Maini ◽  
...  
Keyword(s):  
Femtosecond Laser ◽  
Cataract Surgery ◽  
Radial Basis Function ◽  
Intraocular Lens ◽  
Refractive Error ◽  
Basis Function ◽  
Case Series ◽  
Absolute Error ◽  
Iol Power ◽  
Intraocular Lens Calculation

AIM: To determine the refractive accuracy of the Haigis, Barrett Universal II (Barrett), and Hill-radial basis function 2.0 (Hill-RBF) intraocular lens (IOL) power calculations formulas in eyes undergoing manual cataract surgery (MCS) and refractive femtosecond laser-assisted cataract surgery (ReLACS). METHODS: This was a REB-approved, retrospective interventional comparative case series of 158 eyes of 158 patients who had preoperative biometry completed using the IOL Master 700 and underwent implantation of a Tecnis IOL following uncomplicated cataract surgery using either MCS or ReLACS. Target spherical equivalence (SE) was predicted using the Haigis, Barrett, and Hill-RBF formulas. An older generation formula (Hoffer Q) was included in the analysis. Mean refractive error (ME) was calculated one month postoperatively. The lens factors of all formulas were retrospectively optimized to set the ME to 0 for each formula across all eyes. The median absolute errors (MedAE) and the proportion of eyes achieving an absolute error (AE) within 0.5 diopters (D) were compared between the two formulas among MCS and ReLACS eyes, respectively. RESULTS: Of the 158 eyes studied, 64 eyes underwent MCS and 94 eyes underwent ReLACS. Among MCS eyes, the MedAE did not differ between the formulas (P=0.59), however among ReLACS eyes, Barrett and Hill-RBF were more accurate (P=0.001). Barrett and Hill-RBF were both more likely to yield AE<0.5 D among both groups (P<0.001). CONCLUSION: The Barrett and Hill-RBF formula lead to greater refractive accuracy and likelihood of refractive success when compare to Haigis in eyes undergoing ReLACS.

Sign in / Sign up

Export Citation Format

Share Document