Using machine learning to predict post-operative depth of focus after cataract surgery with implantation of Tecnis Symfony

Abstract

Objective:

To predict post-operative depth of focus (DoF) using machine learning techniques after cataract surgery with Tecnis Symfony implantation and determine associated impact factors.

Methods:

This was a retrospective cohort study among patients receiving Tecnis Symfony implantation, an extended-range-of-vision intraocular lens, during October 2016–January 2020 at Daqing Oilfield General Hospital, China. Four different predictive models were used to predict good post-operative DoF (⩾2.5 D): Extreme Gradient Boost (XGBoost), random forest (RF), LASSO penalized regression, and multivariable logistic regression (MLR). Apriori algorithm was employed to further explore the association between patient attributes and DoF.

Results:

A total of 182 unique cases (143 patients) were included. The XGBoost model produced the best predictive accuracy compared to RF, LASSO, and MLR models. Overall performance of the best fitting XGBoost model was as follows: accuracy = 70.3%, AUC = 80.2%, sensitivity = 65.5%, and specificity = 87.5%. The Apriori algorithm identified six preoparative attributes with substantial effects on good post-operative DoF: low anterior chamber depth (ACD) (1.9 to <2.5 mm), smaller pupil size (1.7 to <2.5 mm), low-to-mid axial length (21 to <23 mm), minimum astigmatism degree (−0.2 to 0 diopter), low IOP (9 to <12 mmHg), and medium lens target refractive error (−0.5 to <−0.25 diopter).

Conclusions:

Machine Learning models were able to predict good post-operative DoF among cataract patients receiving a Tecnis Symfony ocular lens implantation. The accuracy of the model was above 70%. The Apriori algorithm identified six preoperative attributes with a strong association with post-operative DoF.

Keywords

Lens/cataract epidemiology/biostatistics IOLs biometry/axial length secondary IOL implantation

Get full access to this article

View all access options for this article.

References

GBD 2017. Disease and Injury Incidence and Prevalence Collaborators. Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990-2017: a systematic analysis for. the Global Burden of Disease Study 2017. Lancet 2018; 392(10159): 1789–1858.

National Eye Institute (2020) Cataract Tables. https://www.nei.nih.gov/learn-about-eye-health/resources-for-health-educators/eye-health-data-and-statistics/cataract-data-and-statistics/cataract-tables (accessed 9 September 2020).

MacRae

Holladay

Glasser

, et al. Special report: American academy of ophthalmology task force consensus statement for extended depth of focus intraocular lenses. Ophthalmology 2017; 124(1): 139–141.

Cochener

; Concerto Study Group. Clinical outcomes of a new extended range of vision intraocular lens: international multicenter concerto study. J Cataract Refract Surg 2016; 42(9): 1268–1275.

Akella

Juthani

VV.

Extended depth of focus intraocular lenses for presbyopia. Curr Opin Ophthalmol 2018; 29(4): 318–322.

Tabernero

Piers

Benito

, et al. Predicting the optical performance of eyes implanted with IOLs to correct spherical aberration. Invest Ophthalmol Vis Sci 2006; 47(10): 4651–4658.

Huang

, et al. Large-scale regulatory network analysis from microarray data: modified Bayesian network learning and association rule mining. Decis Support Syst 2007; 43(4): 1207–1225.

Karabatak

Ince

MC.

An expert system for detection of breast cancer based on association rules and neural network. Expert Syst Appl 2009; 36(2): 3465–3469.

Shin

Lee

, et al. Diagnostic analysis of patients with essential hypertension using association rule mining. Healthc Inform Res 2010; 16(2): 77–81.

10.

Raju

Patrician

, et al. Exploring factors associated with pressure ulcers: a data mining approach. Int J Nurs Stud 2015; 52: 102–111.

11.

Pereira

Portela

Santos

, et al. Predicting type of delivery by identification of obstetric risk factors through data mining. Procedia Comput Sci 2015; 64: 601–609.

12.

Aljumah

Ahamad

Siddiqui

MK.

Application of data mining: diabetes health care in young and old patients. J King Saud Univ Comput Inf Sci 2013; 25: 127–136.

13.

Coh

Moghimi

Chen

, et al. Lens position parameters as predictors of intraocular pressure reduction after cataract surgery in glaucomatous versus nonglaucomatous eyes. Invest Ophthalmol Vis Sci 2016; 57(6): 2593–2599.

14.

Jeon

The strengths and limitations of the statistical modeling of complex social phenomenon: focusing on SEM, path analysis, or multiple regression models. Int J Soc Behav Educ Econ Bus Ind Eng 2015; 9(5): 1559–1567.

15.

Wang

Chen

, et al. Prediction of type 2 diabetes risk and its effect evaluation based on the XGBoost model. Healthcare 2020; 8: 247.

16.

Ilayaraja

Meyyappan

Mining medical data to identify frequent diseases using Apriori algorithm. In: Pattern recognition, informatics and mobile engineering (PRIME), 2013 international conference, Periyar University, Salem, Tamilnadu, India, 21–22 February 2013, pp. 194–199. New York: IEEE.

17.

Khalili

Sami

SysDetect: a systematic approach to critical state determination for Industrial Intrusion Detection Systems using Apriori algorithm. J Process Control 2015; 32: 154–160.

18.

Cantor

Kattan

MW.

Determining the area under the ROC curve for a binary diagnostic test. Med Decis Making 2000; 20(4): 468–470.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.17 MB