Cataract, intraocular lens, and refractive surgery in 1987 with a forecast to 1995

Choice of refractive surgery types for myopia assisted by machine learning based on doctors' surgical selection data

In recent years, corneal refractive surgery has been widely used in clinics as an effective means to restore vision and improve the quality of life. When choosing myopia-refractive surgery, it is necessary to comprehensively consider the differences in equipment and technology as well as the specificity of individual patients, which heavily depend on the experience of ophthalmologists. In our study, we took advantage of machine learning to learn about the experience of ophthalmologists in decision-making and assist them in the choice of corneal refractive surgery in a new case. Our study was based on the clinical data of 7,081 patients who underwent corneal refractive surgery between 2000 and 2017 at the Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. Due to the long data period, there were data losses and errors in this dataset. First, we cleaned the data and deleted the samples of key data loss. Then, patients were divided into three groups according to the type of surgery, after which we used SMOTE technology to eliminate imbalance between groups. Six statistical machine learning models, including NBM, RF, AdaBoost, XGBoost, BP neural network, and DBN were selected, and a ten-fold cross-validation and grid search were used to determine the optimal hyperparameters for better performance. When tested on the dataset, the multi-class RF model showed the best performance, with agreement with ophthalmologist decisions as high as 0.8775 and Macro F1 as high as 0.8019. Furthermore, the results of the feature importance analysis based on the SHAP technique were consistent with an ophthalmologist's practical experience. Our research will assist ophthalmologists in choosing appropriate types of refractive surgery and will have beneficial clinical effects.

Symptomatic management of postoperative bullous keratopathy with nonpreserved human amniotic membrane

PURPOSE

To report the results of the management of painfully symptomatic postoperative bullous keratopathy (PBK) by performing a nonpreserved human amniotic membrane (NP-AMT) transplantation in nine eyes with poor visual potential.

METHODS

A prospective, comparative, nonrandomized management of symptomatic PBK was done by performing a complete corneal de-epithelialization followed by a NP-AMT transplantation (NP-AMT group) or no NP-AMT transplantation (control group). We evaluated time for re-epithelialization, patient's symptoms, and appearance of new bullae.

RESULTS

In the NP-AMT group, mean follow-up time was 40 weeks. Mean re-epithelialization time was 11.2 days. Symptoms of PBK resolved completely in eight patients (88%), who were asymptomatic and showing very quiet eyes from postoperative day 1, and resolved partially in one patient in whom we observed barely symptomatic bullae at the peripheral NP-AMT border (sixth postoperative week) and an asymptomatic one at the corneal center under the NP-AMT (seventh postoperative week). In the control group, mean follow-up time was 18 weeks; there were recurrences of symptomatic bullae in four of five patients at a mean time of 6.3 days.

CONCLUSIONS

NP-AMT is a good alternative for the management of painful PBK in eyes with poor visual potential; NP-AMT is widely available, the technique is easy to perform, and it has good results from both the symptomatic and esthetic standpoint.

Visual acuity disturbance in subjects over 50 years of age in a population-based cataract survey

Visual acuity is still an essential examination item in cataract epidemiological studies, even though this parameter lacks objective reliability. A population-based epidemiological study was conducted in a rural area of Japan to find out the relationship between visual acuity levels and cataracts, the types of gradings of which were evaluated by an objectively reliable method through lens images, and to serve as a sample for researchers who perform epidemiological studies on cataract but lack the latest methodology. 863 participants above 50 years of age were examined and those previously diagnosed with ocular diseases which affect visual acuity were excluded from the analysis as much as possible. The mean visual acuity (LogMAR) in subjects in their 50s, 60s, 70s and over 80 years of age was 1.1, 1.0, 0.7 and 0.4, respectively. Both the mean and the distribution of visual acuity showed a statistically significant relationship to ageing (p < 0.01, p < 0.01). Both age and cataract grading showed a statistically significant relationship to visual acuity (p < 0.01), but there was no significant interaction effect between these two variables upon visual acuity. Visual acuity worsened remarkably with ageing in the eyes with grade III, whereas that of eyes with grades I and II remained fairly stable at a level of 0.7-1.0, except for those above 80 years of age. A fairly good visual acuity of 1.0, 0.8 and 0.7 remained in the eyes with pure cortical cataract of grades I, II and III, respectively, whereas those with mixed type cataract were 0.9, 0.6 and 0.3, respectively.

Survey of the optical quality of intraocular lens implants

Intraocular lenses (IOLs) from 15 U.S. firms were tested for conformance to the requirements of the American National Standards Institute Z80.7 standard for IOLs. A total of 162 IOLs were tested for resolution, astigmatism, and accuracy of labeled power. Average resolving power was 78% of the diffraction limit, much better than the ANSI minimum requirement which is typically equivalent to 30% of the diffraction limit. This suggests that the ANSI Z80.7 requirement could be significantly tightened with little effect on current production practices. Only one IOL exhibited astigmatism in excess of 0.25 diopter. Differences between measured and labeled power in excess of 0.50 diopter were found in 22 lenses, indicating that accuracy of refractive power may be the most commonly missed optical requirement of the standard.

Resolution testing of intraocular lenses

A basic goal associated with the manufacture of intraocular lenses (IOLs) is that they not be vision limiting. Manufacturers must therefore test IOL resolution against some minimum requirement. Currently, American National Standards Institute voluntary standard Z80.7-1984 addresses IOL optical requirements. One criterion of this standard is a minimum resolving power of 100 line-pairs-per-millimeter. This report presents some results of lens testing that suggest this standard is inadequate because it may not control the performance of a large enough fraction of the optic aperture.