Improving clinical refractive results of cataract surgery by machine learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Sramka M
PROVIDER: S-EPMC6611496 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Improving clinical refractive results of cataract surgery by machine learning.
Sramka Martin M Slovak Martin M Tuckova Jana J Stodulka Pavel P
PeerJ 20190702
<h4>Aim</h4>To evaluate the potential of the Support Vector Machine Regression model (SVM-RM) and Multilayer Neural Network Ensemble model (MLNN-EM) to improve the intraocular lens (IOL) power calculation for clinical workflow.<h4>Background</h4>Current IOL power calculation methods are limited in their accuracy with the possibility of decreased accuracy especially in eyes with an unusual ocular dimension. In case of an improperly calculated power of the IOL in cataract or refractive lens replac ...[more]
Similar Datasets
Project description:The statistical characteristics of biometry and refractive error in a large sample of cataractous Cuban patients are presented, comparing between sexes and age groups. All patients were studied at the Cuban Institute of Ophthalmology "Ramón Pando Ferrer," La Habana. The sample consists of 28252 eyes of 25068 patients, subjected to cataract surgery during the time period between 2006 and 2019. Their biometry was obtained using IOL Master devices; also, visual acuity, refraction, and corneal power were registered. After surgery, the visual acuity and refraction were measured. The refractive prediction error was determined. For patients with both eyes registered, anisometropia was also calculated. Age and sex were used to segment the data. The preoperative biometric parameters show highly significant differences between sexes, with male eyes being longer and with a deeper anterior chamber but with a thinner lens. Also, keratometry shows highly significant differences, with female eyes being steeper than male. Before surgery, both sexes have myopic eyes as average, with males being more myopic than females (p < 0.001). After surgery, the average spherical equivalent is -0.36 D and female eyes are more myopic than males (p < 0.001). Visual acuity with and without distance correction has a significant increase after surgery. These results are of importance not only for Cuba but also for other countries with a large Cuban population and/or similar ethnic composition, such as the USA (particularly the south of Florida), Spain, and many countries in Latin America.
| S-EPMC8099509 | biostudies-literature
Project description:Recently, it has become more important to screen candidates that undergo corneal refractive surgery to prevent complications. Until now, there is still no definitive screening method to confront the possibility of a misdiagnosis. We evaluate the possibilities of machine learning as a clinical decision support to determine the suitability to corneal refractive surgery. A machine learning architecture was built with the aim of identifying candidates combining the large multi-instrument data from patients and clinical decisions of highly experienced experts. Five heterogeneous algorithms were used to predict candidates for surgery. Subsequently, an ensemble classifier was developed to improve the performance. Training (10,561 subjects) and internal validation (2640 subjects) were conducted using subjects who had visited between 2016 and 2017. External validation (5279 subjects) was performed using subjects who had visited in 2018. The best model, i.e., the ensemble classifier, had a high prediction performance with the area under the receiver operating characteristic curves of 0.983 (95% CI, 0.977-0.987) and 0.972 (95% CI, 0.967-0.976) when tested in the internal and external validation set, respectively. The machine learning models were statistically superior to classic methods including the percentage of tissue ablated and the Randleman ectatic score. Our model was able to correctly reclassify a patient with postoperative ectasia as an ectasia-risk group. Machine learning algorithms using a wide range of preoperative information achieved a comparable performance to screen candidates for corneal refractive surgery. An automated machine learning analysis of preoperative data can provide a safe and reliable clinical decision for refractive surgery.
| S-EPMC6586803 | biostudies-literature
Project description:AimTo evaluate refractive outcomes of cataract surgery with intraocular lens (IOL) implantation in operated eyes of primary congenital glaucoma (PCG).DesignA retrospective case-control study.MethodsPatients of PCG who developed cataract following trabeculectomy with trabeculotomy were recruited. Preoperative biometry was recorded and refractive outcomes of the patients in terms of spherical equivalent (SE) and prediction error were noted at 3 and at 12 months following surgery. The refractive outcomes were compared with non-glaucomatous eyes of children in similar age group who underwent lens aspiration with IOL implantation (controls).ResultsThe median age of the children with PCG (n = 31) at the time of cataract surgery was 60 months, similar to controls (n = 29); 48 months (p = 0.3). The SE in PCG eyes at 12 months was comparable to controls (p = 0.18). The prediction error (postoperative SE - predicted SE) at 3 months (p = 0.018) and at 12 months (p = 0.03) among PCG eyes was higher and more myopic compared with controls. The range of prediction error at 12 months in PCG eyes was - 8.6 to + 5.8 D (median - 2.0 D), whereas in controls it was - 4.2 to + 6.3 D (median + 0.5 D). For each mmHg intraocular pressure (IOP) increase there was 0.42 mm increase in axial length among PCG eyes and a 0.24 mm increase among controls (p < 0.001).ConclusionsAfter IOL implantation there was a greater prediction error and a greater myopic shift among PCG eyes. Eyes of children with PCG are more prone to refractive surprises as their axial length changes are more sensitive to IOP fluctuation.
| S-EPMC6461842 | biostudies-literature
Project description:Suboptimal cataract surgery outcomes remain a challenge in most developing countries. In Ghana, about 2 million people have been reported to be blind due to cataract with about 20% new cases being recorded yearly. The aim of this study was to evaluate postoperative correction of refractive errors after cataract surgery in a selected eye hospital in Ashanti Region, Ghana. This was a retrospective study where medical records of patients (aged 40-100) who reported to an eye hospital in Ghana from 2013-2018 were reviewed. Included in the study were patients aged ≥40 years and patients with complete records. Data on patient demographics, type of surgery, intra-ocular lens (PCIOL) power, availability of biometry, postoperative refraction outcomes, pre- and postoperative visual acuity were analyzed. Data of two hundred and thirteen eyes of 190 patients who met the inclusion criteria were analyzed. Descriptive analysis and Chi-square test were carried out to determine the mean, median, standard deviation and relevant associations. The mean ± SD age was 67.21±12.2 years (51.2% were females). Small Incision Cataract Surgery (99.5%) with 100% IOL implants was the main cataract surgery procedure in this study. Pre-operative biometry was performed for 38.9% of all patients on their first eye surgery and 41.5% for second eye surgeries. About 71% eyes in this study were blind (presenting VA<3/60) before surgery; 40.4% had post-operative VA <3/60. Pre-existing ocular comorbidities discovered post- surgery, attributed to suboptimal visual outcomes. More than half (55.3%) of patients did not undergo postoperative refraction due to loss to follow-up. Year of surgery (p = .017), follow up visits< 2months (p < .0001) and discovered comorbidity post-surgery (p = .035) were the factors significantly associated with postoperative refraction. Myopia and compound myopic astigmatism were the dominant refractive error outcomes. The timing of post-operative refraction had a significant effect on postoperative refraction done. These findings indicate a clinically meaningful significance between completion of postoperative care and postoperative refraction done. Consequently, with settings in most developing countries, where less biometry is done, it is appropriate that post-operative refractive services are encouraged and done earlier to enhance the patients' expectations while increasing cataract surgery patronage.
| S-EPMC8211256 | biostudies-literature
Project description:AbstractCorneal diseases, uncorrected refractive errors, and cataract represent the major causes of blindness globally. The number of refractive surgeries, either cornea- or lens-based, is also on the rise as the demand for perfect vision continues to increase. With the recent advancement and potential promises of artificial intelligence (AI) technologies demonstrated in the realm of ophthalmology, particularly retinal diseases and glaucoma, AI researchers and clinicians are now channeling their focus toward the less explored ophthalmic areas related to the anterior segment of the eye. Conditions that rely on anterior segment imaging modalities, including slit-lamp photography, anterior segment optical coherence tomography, corneal tomography, in vivo confocal microscopy and/or optical biometers, are the most commonly explored areas. These include infectious keratitis, keratoconus, corneal grafts, ocular surface pathologies, preoperative screening before refractive surgery, intraocular lens calculation, and automated refraction, among others. In this review, we aimed to provide a comprehensive update on the utilization of AI in anterior segment diseases, with particular emphasis on the recent advancement in the past few years. In addition, we demystify some of the basic principles and terminologies related to AI, particularly machine learning and deep learning, to help improve the understanding, research and clinical implementation of these AI technologies among the ophthalmologists and vision scientists. As we march toward the era of digital health, guidelines such as CONSORT-AI, SPIRIT-AI, and STARD-AI will play crucial roles in guiding and standardizing the conduct and reporting of AI-related trials, ultimately promoting their potential for clinical translation.
| S-EPMC7611495 | biostudies-literature
Project description:ImportanceApproximately 2 million cataract operations are performed annually in the US, and patterns of cataract surgery delivery are changing to meet the increasing demand. Therefore, a comparative analysis of visual acuity outcomes after immediate sequential bilateral cataract surgery (ISBCS) vs delayed sequential bilateral cataract surgery (DSBCS) is important for informing future best practices.ObjectiveTo compare refractive outcomes of patients who underwent ISBCS, short-interval (1-14 days between operations) DSBCS (DSBCS-14), and long-interval (15-90 days) DSBCS (DSBCS-90) procedures.Design, setting, and participantsThis retrospective cohort study used population-based data from the American Academy of Ophthalmology Intelligent Research in Sight (IRIS) Registry. A total of 1 824 196 IRIS Registry participants with bilateral visual acuity measurements who underwent bilateral cataract surgery were assessed.ExposuresParticipants were divided into 3 groups (DSBCS-90, DSBCS-14, and ISBCS groups) based on the timing of the second eye surgery. Univariable and multivariable linear regression models were used to analyze the refractive outcomes of the first and second surgery eye.Main outcomes and measuresMean postoperative uncorrected visual acuity (UCVA) and best-corrected visual acuity (BCVA) after cataract surgery.ResultsThis study analyzed data from 1 824 196 patients undergoing bilateral cataract surgery (mean [SD] age for those <87 years, 70.03 [7.77]; 684 916 [37.5%] male). Compared with the DSBCS-90 group, after age, self-reported race, insurance status, history of age-related macular degeneration, diabetic retinopathy, and glaucoma were controlled for, the UCVA of the first surgical eye was higher by 0.41 (95% CI, 0.36-0.45; P < .001) letters, and the BCVA was higher by 0.89 (95% CI, 0.86-0.92; P < .001) letters in the DSBCS-14 group, whereas in the ISBCS group, the UCVA was lower by 2.79 (95% CI, -2.95 to -2.63; P < .001) letters and the BCVA by 1.64 (95% CI, -1.74 to -1.53; P < .001) letters. Similarly, compared with the DSBCS-90 group for the second eye, in the DSBCS-14 group, the UCVA was higher by 0.79 (95% CI, 0.74-0.83; P < .001) letters and the BCVA by 0.48 (95% CI, 0.45-0.51; P < .001) letters, whereas in the ISBCS group, the UCVA was lower by -1.67 (95% CI, -1.83 to -1.51; P < .001) letters and the BCVA by -1.88 (95% CI, -1.98 to -1.78; P < .001) letters.Conclusions and relevanceThe results of this cohort study of patients in the IRIS Registry suggest that compared with DSBCS-14 or DSBCS-90, ISBCS is associated with worse visual outcomes, which may or may not be clinically relevant, depending on patients' additional risk factors. Nonrandom surgery group assignment, confounding factors, and large sample size could account for the small but statistically significant differences noted. Further studies are warranted to determine whether these factors should be considered clinically relevant when counseling patients before cataract surgery.
| S-EPMC8251655 | biostudies-literature
Project description:IntroductionIn the context of managing patients' expectations and satisfaction regarding visual acuity after cataract surgery, we aimed to investigate the improvement in visual acuity and patient satisfaction after small-incision lenticule extraction (SMILE) in pseudophakic (trifocal intraocular lens, IOL) patients with residual myopic refraction after cataract surgery.MethodsSeventy-six patients (82 eyes) who underwent cataract surgery with ZEISS AT LISA tri 839MP IOL implantation were included in this retrospective study. The included patients were 56-79 years old, wanted spectacle independence, and had preoperative myopic refraction between - 1.0 and - 2.25 diopters (D) and astigmatism between - 0.75 and - 1.75 D. The treatment status of these patients was defined as trifocal IOL (n = 82). SMILE was performed in patients who were dissatisfied after cataract surgery, and these patients were followed up for 1 year on average. We evaluated visual acuity and satisfaction and further examined laser vision correction and satisfaction levels in patients who were dissatisfied after trifocal IOL implantation.ResultsThe possible reasons for patient dissatisfaction were reading books, using a computer, and driving at night. After SMILE, the residual myopic refractive error (spherical) decreased significantly from - 2.08 ± 0.28 [- 2.25 to - 1.0] preoperatively to - 0.25 ± 0.20 - 0.5 to 0] 1 year postoperatively (p < 0.001). Additionally, the uncorrected distance visual acuity increased from 0.65 ± 0.08 [0.52-0.7] logMAR preoperatively to 0.09 ± 0.02 [0.05-0.1] logMAR at 1 month postoperatively (p < 0.001), 0.09 ± 0.02 [0.05-0.1] logMAR at 6 months postoperatively, and 0.06 ± 0.02 [0.05-0.1] logMAR at 12 months postoperatively (p < 0.001). Patient satisfaction measures after SMILE (reading, night driving, and using a computer) were significantly improved.ConclusionSMILE is a reliable method for treating residual refraction after cataract surgery, as it provides results in the shortest time without complications and increases patient satisfaction.Trial registrationThe protocol was registered on clinicaltrials.gov (NCT04693663).
| S-EPMC9253212 | biostudies-literature
Project description:PurposeTo describe current cataract surgery practice patterns and trends among Korean ophthalmologists.MethodsA survey was conducted among members of the Korean Society of Cataract and Refractive Surgery in October 2020. Of the 998 questionnaires, 262 (26.3%) were received for analysis. Data were analyzed using descriptive statistics and compared with those of previous surveys.ResultsThe largest percentage of respondents (39%) had <5 years of practical experience, and 40% had >11 years of practical experience. The average, median, and mode monthly volumes of cataract surgeries performed by the Korean Society of Cataract and Refractive Surgery members were 31, 20, and 10 cases, respectively. Topical anesthesia was administered by 85% of the respondents. For intraocular lens (IOL) calculations, 96% of the respondents used optical biometry. The proportion of surgeons providing femtosecond laser-assisted cataract surgery increased significantly from 5% in 2018 to 29% in 2020. This increase was accompanied by an increase in the multifocal IOLs. Those who implant multifocal IOL for >10% of their cases increased from 16% (2018) to 29% (2020). Topical nonsteroidal anti-inflammatory drugs were prescribed postoperatively by 76% of the respondents. Most respondents (70%) prescribed these anti-inflammatory drugs for 4 weeks.ConclusionsThis survey provided a comprehensive update on current cataract surgery practice in the Republic of Korea. The results highlighted the increasing use of premium IOLs, femtosecond laser-assisted cataract surgery, optical biometry, and topical anesthesia to better meet the patients' needs.
| S-EPMC8357609 | biostudies-literature
Project description:PurposeCurrently, there are no UK optometric guidelines regarding the pre and postoperative refractive management of patients undergoing cataract surgery. This study used a Delphi method to gain consensus on best practice.MethodsEighteen recommendations targeted areas of concern/variability in advice that were highlighted in an earlier focus group study of refractive management for patients who had received cataract surgery. These covered three topics: preoperative target refraction discussions, postoperative refractive management and driving advice postoperatively. The recommendations were then developed using evidence from optometry and ophthalmology clinical expertise and the research literature. Eighteen recommendations underwent a process of agreement and modification using a Delphi study consisting of a panel of 22 highly experienced optometrists (N = 11, 25 years mean clinical experience) and ophthalmologists (N = 11, 17 years mean clinical experience) who rated and commented upon the importance and feasibility of each recommendation. The responses were considered by the research team and the recommendations modified and/or removed prior to a second Delphi round of responses to a modified series of recommendations. Consensus of opinion was defined as greater than 80% of panellists 'agreed' or 'strongly agreed' on the recommendation for both importance and feasibility.ResultsFourteen of the 18 recommendations reached consensus in the first round. A second round of the Delphi method saw 17 modified recommendations scored and commented upon by 20 clinicians. Fifteen recommendations reached consensus after two rounds of the Delphi method.ConclusionsRecommendations to guide the pre and postoperative refractive management of patients undergoing cataract surgery were agreed between highly experienced optometrists and ophthalmologists using a 2-round Delphi method. Patients would benefit from consistent target refraction discussions, postoperative refractive management and driving advice, and recommendations were of particular benefit to less experienced optometrists.
| S-EPMC10100233 | biostudies-literature
Project description:ImportanceCompetence in cataract surgery is a public health necessity, and videos of cataract surgery are routinely available to educators and trainees but currently are of limited use in training. Machine learning and deep learning techniques can yield tools that efficiently segment videos of cataract surgery into constituent phases for subsequent automated skill assessment and feedback.ObjectiveTo evaluate machine learning and deep learning algorithms for automated phase classification of manually presegmented phases in videos of cataract surgery.Design, setting, and participantsThis was a cross-sectional study using a data set of videos from a convenience sample of 100 cataract procedures performed by faculty and trainee surgeons in an ophthalmology residency program from July 2011 to December 2017. Demographic characteristics for surgeons and patients were not captured. Ten standard labels in the procedure and 14 instruments used during surgery were manually annotated, which served as the ground truth.ExposuresFive algorithms with different input data: (1) a support vector machine input with cross-sectional instrument label data; (2) a recurrent neural network (RNN) input with a time series of instrument labels; (3) a convolutional neural network (CNN) input with cross-sectional image data; (4) a CNN-RNN input with a time series of images; and (5) a CNN-RNN input with time series of images and instrument labels. Each algorithm was evaluated with 5-fold cross-validation.Main outcomes and measuresAccuracy, area under the receiver operating characteristic curve, sensitivity, specificity, and precision.ResultsUnweighted accuracy for the 5 algorithms ranged between 0.915 and 0.959. Area under the receiver operating characteristic curve for the 5 algorithms ranged between 0.712 and 0.773, with small differences among them. The area under the receiver operating characteristic curve for the image-only CNN-RNN (0.752) was significantly greater than that of the CNN with cross-sectional image data (0.712) (difference, -0.040; 95% CI, -0.049 to -0.033) and the CNN-RNN with images and instrument labels (0.737) (difference, 0.016; 95% CI, 0.014 to 0.018). While specificity was uniformly high for all phases with all 5 algorithms (range, 0.877 to 0.999), sensitivity ranged between 0.005 (95% CI, 0.000 to 0.015) for the support vector machine for wound closure (corneal hydration) and 0.974 (95% CI, 0.957 to 0.991) for the RNN for main incision. Precision ranged between 0.283 and 0.963.Conclusions and relevanceTime series modeling of instrument labels and video images using deep learning techniques may yield potentially useful tools for the automated detection of phases in cataract surgery procedures.
| S-EPMC6450320 | biostudies-literature