Dataset Information

Comparison of Formula-Specific Factors and Artificial Intelligence Formulas with Axial Length Adjustments in Bilateral Cataract Patients with Long Axial Length.

ABSTRACT:

Introduction

To evaluate and compare the effectiveness for reducing the prediction error (PE) of the second eye using formula-specific factors, artificial intelligence (AI) formulas (PEARL-DGS and Kane), and the Cooke-modified axial length (CMAL) methods in bilateral cataract patients with long axial length (AL).

Methods

A total of 98 patients with long AL who underwent sequential bilateral cataract surgeries were retrospectively enrolled. The second-eye IOL power was calculated by the formula-specific factors, AI formulas, and CMAL methods when the first eye suffered from refraction surprise. The correction factors of eight formulas were calculated by regression analysis.

Results

There was a significant correlation between bilateral preoperative biometric parameters (P < 0.05) as well as bilateral PE (P < 0.05). The Kane formula displayed the lowest median absolute error (MedAE) and highest proportion of PE within ± 0.50 and ± 1.00 D compared with other formulas for the first eye. For the second-eye refinement, all three methods could reduce the second-eye MedAE. The formula-specific correction factors were 0.250, 0.331, 0.343, 0.394, 0.409, 0.452, 0.503, and 0.520 for Kane, Barrett Universal II (BUII), PEARL-DGS, Holladay 2, Holladay 1, Haigis, Hoffer Q, and SRK/T, respectively. The new AI-based Kane and PEARL-DGS with or without the CMAL methods could improve the refractive outcomes of the second eye in sequential bilateral cataract patients with long AL. The Kane, BUII, and PEARL-DGS with specific correction factors displayed higher accuracy compared with the other two methods (P < 0.05).

Conclusions

The new AI-based Kane and PEARL-DGS with or without the CMAL methods could improve the refractive outcomes of the second eye in sequential bilateral cataract patients with long AL. Notably, the Kane, PEARL-DGS, and BUII with specific correction factors displayed higher accuracy.

SUBMITTER: Li C

PROVIDER: S-EPMC9437155 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Formula-Specific Factors and Artificial Intelligence Formulas with Axial Length Adjustments in Bilateral Cataract Patients with Long Axial Length.

Li Chuang C Wang Mingwei M Feng Rui R Liang Feiyan F Liu Xialin X He Chang C Fan Shuxin S

Ophthalmology and therapy 20220802 5

<h4>Introduction</h4>To evaluate and compare the effectiveness for reducing the prediction error (PE) of the second eye using formula-specific factors, artificial intelligence (AI) formulas (PEARL-DGS and Kane), and the Cooke-modified axial length (CMAL) methods in bilateral cataract patients with long axial length (AL).<h4>Methods</h4>A total of 98 patients with long AL who underwent sequential bilateral cataract surgeries were retrospectively enrolled. The second-eye IOL power was calculated b ...[more]

PMID: 35917084

Similar Datasets

Project description:ImportanceComplications that arise from phacoemulsification procedures can lead to worse visual outcomes. Real-time image processing with artificial intelligence tools can extract data to deliver surgical guidance, potentially enhancing the surgical environment.ObjectiveTo evaluate the ability of a deep neural network to track the pupil, identify the surgical phase, and activate specific computer vision tools to aid the surgeon during phacoemulsification cataract surgery by providing visual feedback in real time.Design, setting, and participantsThis cross-sectional study evaluated deidentified surgical videos of phacoemulsification cataract operations performed by faculty and trainee surgeons in a university-based ophthalmology department between July 1, 2020, and January 1, 2021, in a population-based cohort of patients.ExposuresA region-based convolutional neural network was used to receive frames from the video source and, in real time, locate the pupil and in parallel identify the surgical phase being performed. Computer vision-based algorithms were applied according to the phase identified, providing visual feedback to the surgeon.Main outcomes and measuresOutcomes were area under the receiver operator characteristic curve and area under the precision-recall curve for surgical phase classification and Dice score (harmonic mean of the precision and recall [sensitivity]) for detection of the pupil boundary. Network performance was assessed as video output in frames per second. A usability survey was administered to volunteer cataract surgeons previously unfamiliar with the platform.ResultsThe region-based convolutional neural network model achieved area under the receiver operating characteristic curve values of 0.996 for capsulorhexis, 0.972 for phacoemulsification, 0.997 for cortex removal, and 0.880 for idle phase recognition. The final algorithm reached a Dice score of 90.23% for pupil segmentation and a mean (SD) processing speed of 97 (34) frames per second. Among the 11 cataract surgeons surveyed, 8 (72%) were mostly or extremely likely to use the current platform during surgery for complex cataract.Conclusions and relevanceA computer vision approach using deep neural networks was able to pupil track, identify the surgical phase being executed, and activate surgical guidance tools. These results suggest that an artificial intelligence-based surgical guidance platform has the potential to enhance the surgeon experience in phacoemulsification cataract surgery. This proof-of-concept investigation suggests that a pipeline from a surgical microscope could be integrated with neural networks and computer vision tools to provide surgical guidance in real time.

Project description:AimsTo determine the characteristics of corneal biometrics in eyes from aniso-axial length cataract patients compared with eyes from non-aniso-axial length individuals.MethodsThis is a retrospective case series. Cataract patients with preoperative binocular measurements were recruited. A binocular axial difference of ≥1 mm was considered to indicate aniso-axial length. The anterior segmental biometrics were measured using Pentacam HR (Oculus, Wetzlar, Germany) and IOLMaster 500 (Carl Zeiss Meditec, Jena, Germany). Comparisons of biometrics were made among 4 eye conditions: the longer eyes from aniso-axial length patients, the shorter eyes from aniso-axial length patients, the longer eyes from non-aniso-axial length patients, and the shorter eyes from non-aniso-axial length patients. The aniso-axial length eyes were also stratified into 8 subgroups with axial length (AL) increments of 1 mm, and the biometrics of the subgroups were compared.ResultsThere was smaller anterior corneal astigmatism in the shorter aniso-axial length group than those in the longer aniso-axial length group (1.01 ± 0.70 D vs 1.12 ± 0.76 D, P=0.031). The longer aniso-axial length eyes had greater anterior corneal steep curvature (44.13 ± 1.69 D vs 43.87 ± 1.69 D, P=0.009) and anterior corneal astigmatism (1.12 ± 0.76 D vs 1.02 ± 0.69 D, P=0.023) compared with longer non-aniso-axial length subjects. Other corneal biometrics were similar between the aniso-axial length eyes and the non-aniso-axial length eyes. In the longer aniso-axial length group, the posterior corneal aberrations of eyes in the ≥5 mm subgroups were greater than those in the <5 mm subgroups (0.879 ± 0.183 μm vs 0.768 ± 0.178 μm for total aberrations, P < 0.001; 0.228 ± 0.086 μm vs 0.196 ± 0.043 μm for high-order aberrations, P=0.036; 0.847 ± 0.173 μm vs 0.741 ± 0.179 μm for low-order aberrations, P=0.001).ConclusionEyes of aniso-axial length individuals share generally similar corneal biometrics with normal eyes in cataract population. Anterior corneal astigmatism of the longer eyes from the aniso-axial length cataract patients was higher than that of the longer eyes from the non-aniso-axial length individuals. Total posterior corneal aberrations of the longer aniso-axial length eyes increased when the binocular axial difference was over 5 mm.

Dataset Information

Comparison of Formula-Specific Factors and Artificial Intelligence Formulas with Axial Length Adjustments in Bilateral Cataract Patients with Long Axial Length.

Introduction

Methods

Results

Conclusions

Publications

Comparison of Formula-Specific Factors and Artificial Intelligence Formulas with Axial Length Adjustments in Bilateral Cataract Patients with Long Axial Length.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets