Establishment of a prediction tool for ocular trauma patients with machine learning algorithm

AIM: To predict final visual acuity and analyze significant factors influencing open globe injury prognosis. METHODS: Prediction models were built using a supervised classification algorithm from Microsoft Azure Machine Learning Studio. The best algorithm was selected to analyze the predicted final visual acuity. We retrospectively reviewed the data of 171 patients with open globe injury who visited the Pusan National University Hospital between January 2010 and July 2020. We then applied cross-validation, the permutation feature importance method, and the synthetic minority over-sampling technique to enhance tool performance. RESULTS: The two-class boosted decision tree model showed the best predictive performance. The accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve were 0.925, 0.962, 0.833, 0.893, and 0.971, respectively. To increase the efficiency and efficacy of the prognostic tool, the top 14 features were finally selected using the permutation feature importance method: (listed in the order of importance) retinal detachment, location of laceration, initial visual acuity, iris damage, surgeon, past history, size of the scleral laceration, vitreous hemorrhage, trauma characteristics, age, corneal injury, primary diagnosis, wound location, and lid laceration. CONCLUSION: Here we devise a highly accurate model to predict the final visual acuity of patients with open globe injury. This tool is useful and easily accessible to doctors and patients, reducing the socioeconomic burden. With further multicenter verification using larger datasets and external validation, we expect this model to become useful worldwide.

Vitrectomized versus non-vitrectomized eyes in diabetic macular edema response to ranibizumab—retinal layers thickness as prognostic biomarkers

To evaluate the role of the vitreous in the management of diabetic macular edema with ranibizumab intravitreal injections in a pro re nata regimen. Prospective study of 50 consecutive eyes with diabetic macular edema treated with ranibizumab and 12 months of follow-up. Primary endpoint: to assess differences between non-vitrectomized and vitrectomized eyes in the number injections needed to control the edema. Secondary endpoints: comparison of groups regarding best corrected visual acuity, central foveal thickness and thickness of seven retinal layers. 46 eyes from 38 patients, 10 vitrectomized and 36 non-vitrectomized, completed the follow-up. At month 12, the two groups achieved an equivalent anatomical outcome and needed a similar number of ranibizumab intravitreal injections. In vitrectomized eyes final visual acuity was worse when baseline retinal nerve fiber layers in the central foveal subfield were thicker, showing a strong correlation (r = − 0.942, p < 0.001). A similar, albeit moderate correlation was observed in non-vitrectomized eyes (r = − 0.504, p = 0.002). A decrease of retinal nerve fiber layers inner ring thickness was correlated with a better final visual acuity only in vitrectomized eyes (r = 0.734, p = 0.016). The effect of diabetic macular edema seems to be worse in vitrectomized eyes, with a thinner inner retina reservoir.Clinicaltrials.govNCT04387604.

Open globe injuries in geriatric population in Iran: characteristics and outcomes

AIM: To investigate the patterns and outcomes of open globe injuries in the elderly population in Iran. METHODS: In this retrospective cross-sectional chart review, medical records of 248 patients (aged 60y and more) with the diagnosis of open globe injury from 2006 to 2016 were reviewed. Demographic features, type, and mechanism of open globe injury, ocular trauma score (OTS), visual acuity before and after treatment, the zone of injuries, and the associated injuries found at the presentation or thereafter were documented. RESULTS: A total of 248 eyes of 248 patients were included. The mean age was 69.2±5.8y (range: 60-90y). Male/ female ratio was about 3:1 (187 vs 61). The three most common causes of injury were falling (25.2%), sharp objects (18.9%), and tree branches (13.9%). Penetrating injury accounted for most of the geriatric ocular trauma (50.4%), followed by globe rupture (40.3%), intraocular foreign body (IOFB; 7.3%), and perforating injury (2.0%). The median raw OTS for the population was 60.5 and the most common OTS class was 3. The injuries tend to affect zone I more than zone II and zone III. The only predictor of final visual acuity was the class of OTS (P<0.001). CONCLUSION: Geriatric open globe injury should be valued specifically. The most common type of open globe injury in Iran is penetrating injuries but falling remain the main cause. The OTS class must be considered as an important predictor of final visual acuity.

Bungee cord related ocular trauma: An avoidable cause of ocular morbidity

To study the mechanism and clinical features of ocular injury and its outcome associated with bungee cord related eye trauma. A retrospective review of medical records was performed at our tertiary care centre to identify patients presented with bungee cord related eye injury between March 2016 to February 2017. Data collected from medical records were age, sex, mechanism of injury, clinical features, therapeutic intervention, presenting visual acuity, final visual acuity and length of follow up. Total of thirteen patients with bungee cord related trauma were identified. Ten (77%) patients presented with closed globe injury and 3(23%) presented with open globe injury. All patients were male with mean age group of 30.15±7.38 years. Presenting visual acuity ranges from 6/12 to NPL. Only seven (54%) of patients were having final visual acuity of better than or equal to 6/18 in injured eye. Three patients (23.1%) with open globe injury had final visual acuity of counting fingers or worse. Main mechanism of injury being combination of blunt and high speed projectile injury due to slippage of metal or plastic hook while the cord is stretched. Trauma with bungee cord is usually affecting working age group male with injury resulting in loss of workable vision to loss of eye hence there is need of appropriate intervention like use of printed warning on package and modification of hook design to decrease the incidence of bungee cord related trauma.

Outcomes Following Pars Plana Vitrectomy for Severe Ocular Trauma

Purpose: To investigate outcomes and presenting characteristics for subjects undergoing pars plana vitrectomy for ocular trauma. Methods: Retrospective study of 113 patients who underwent pars plana vitrectomy for severe ocular trauma at [name deleted to maintain the integrity of the review process] between 1999 and 2018. Data were collected on age, gender, initial and final visual acuity (LogMAR), mode of injury, type of injury, number of surgeries performed, follow-up duration, type of tamponade, presence of phthisis, and retinal detachment. The Birmingham Eye Trauma Terminology System (BETTS) was employed. Results: We identified assault and contusion injuries to be the most common mode and type of ocular injury in our cohort. Furthermore, through follow-up we noted a varied number of operations required by patients presenting with ocular trauma and a statistically significant improvement in visual acuity from 1.73 (±0.86) LogMAR to 1.17 (±1.03; p <0.01) LogMAR. A statistically significant difference in final visual acuity was also noted between BETTS classified type of injury groups (p < 0.01). Notably, only 7.3% and 8.2% of patients developed phthisis or a persisting retinal detachment, respectively, during follow-up. Conclusion: Our study demonstrates that ocular trauma requiring pars plana vitrectomy can require a varied number of operations with a guarded visual prognosis. However, a small percentage will proceed to develop phthisis following intervention.

Long-term silicone oil tamponade in eyes with complicated retinal detachment

Purpose: To report the visual and anatomic outcomes of eyes with exceedingly long-term silicone oil tamponade. Methods: A retrospective chart review of 43 eyes of 41 patients with silicone oil tamponade for 5 years or more. Rates of retinal reattachment, visual acuity, and complications are presented. Further analysis was performed to identify if silicone oil complications are more common in eyes with lower vision. For this, cases were divided into group A-visual acuity of 20/400 or better and group B-visual acuity of less than 20/400. Results: Mean silicone oil duration was 12.6 ± 6.3 years. The etiology at presentation included: recurrent RRD (60.46%), RRD secondary to trauma (25.58%), and TRD (13.95%). Ninety-three percent of eyes underwent at least one ocular surgery before the vitrectomy with silicone oil tamponade. The retinal attachment rate was 55.8%. Mean visual acuity at presentation was 2.03 ± 0.6 logMAR, and at the final follow-up, 1.85 ± 0.78 logMAR ( p = 0.166). Emulsification developed in 33.3% of cases, glaucoma in 28.6%, band keratopathy in 21.4%, and corneal decompensation in 16.7%. In 26.2% of eyes, the final visual acuity was 20/400 or better (group A). In 73.8% of eyes, final visual acuity was worse than 20/400 (group B). The rates of silicone oil emulsification and glaucoma were not statistically significant between groups. Conclusions: Long-term silicone oil tamponade is a possible option in eyes with complicated retinal detachment following multiple intravitreal procedures, although the complication rates are relatively high. In 26.2% of eyes, visual acuity of 20/400 or better can be preserved for many years.

Prognostic factors and epidemiology of adult open globe injuries from Western Sydney: a twelve-year review

Background To identify prognostic factors determining final visual outcome following open globe injuries. Methods Retrospective case series of patients presenting to Westmead Hospital, Sydney, Australia with open globe injuries from 1st January 2005 to 31st December 2017. Data collected included demographic information, ocular injury details, management and initial and final visual acuities. Results A total of 104 cases were identified. Predictors of poor final visual outcomes included poor presenting visual acuity (p < 0.001), globe rupture (p < 0.001), retinal detachment (p < 0.001), Zone III wounds (p < 0.001), hyphema (p = 0.003), lens expulsion (p = 0.003) and vitreous hemorrhage (p < 0.001). Multivariate analysis demonstrated presenting visual acuity (p < 0.001), globe rupture (p = 0.013) and retinal detachment (p = 0.011) as being statistically significant for predicting poor visual outcomes. The presence of lid laceration (p = 0.197) and uveal prolapse (p = 0.667) were not significantly associated with the final visual acuity. Conclusions Poor presenting visual acuity, globe rupture and retinal detachment are the most important prognostic factors determining final visual acuity following open globe injury.

Factors determining the compliance of patients receiving anti-VEGF therapy for macular diseases with long-term follow-up in real-life practice

Purpose: to identify statistically significant factors that determine adherence to long-term follow-up on the part of patients receiving anti-VEGF therapy for macular diseases.Material and methods. A retrospective analysis was performed on 247 patients (153 women, 94 men) aged 24 to 92 years treated with anti-VEGF for “wet” age-related macular degeneration (n = 164), diabetic macular edema (n = 18), macular edema due to retinal vein occlusion (n = 35) and myopic choroidal neovascularization (n = 30). Demographic data and treatment results were statistically analyzed with the STATISTICA 13.3 program (normal conditions for variables, non-parametric and parametric criteria were determined).Results. Follow-up duration was shown to depend on gender (women are more committed to long-term treatment, p < 0.05), diagnosis (the longest follow-up related to myopic choroidal neovascularization patients), initial and final visual acuity. The comparison of subgroups of patients with the longest (over 30 months, n = 56) and shortest (till 12 months, n = 92) follow-up showed that prolonged monitoring corresponds to higher values of the initial (p < 0.01) and final (p < 0.05) visual acuity, as well as a lower average number of injections over the entire follow-up (p < 0.001) and a younger age of patients (p = 0.02).Conclusion. The follow-up duration depends on gender and age, the intensity of treatment, as well as on the initial and final visual acuity at a significance level of ˂ 0.05. Also, the follow-up duration depends on the particular diagnosis. An indicator clearly reflecting the severity of the burden of treatment is proposed: the coefficient of therapy intensity which is inversely related to the patient’s adherence to therapy.

Prognostic Factors and Epidemiology of Open Globe Injuries from Western Sydney: A Twelve-Year Review

BackgroundTo identify prognostic factors determining final visual outcome following open globe injuries.MethodsRetrospective case series of patients presenting to Westmead Hospital, Sydney, Australia with open globe injuries from 1st January 2005 to 31st December 2017. Data collected included demographic information, ocular injury details, management and initial and final visual acuities.ResultsA total of 104 cases were identified. Predictors of poor final visual outcomes included poor presenting visual acuity (p < 0.001), globe rupture (p < 0.001), retinal detachment (p < 0.001), Zone III wounds (p < 0.001), hyphema (p=0.003), lens expulsion (p = 0.003) and vitreous hemorrhage (p < 0.001). Multivariate analysis demonstrated presenting visual acuity (p < 0.001), globe rupture (p = 0.013) and retinal detachment (p = 0.011) as being statistically significant for predicting poor visual outcomes. The presence of lid laceration (p = 0.197) and uveal prolapse (p = 0.667) were not significantly associated with the final visual acuity. ConclusionsPoor presenting visual acuity, globe rupture and retinal detachment are the most important prognostic factors determining final visual acuity following open globe injury.