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

2021 ◽  
Vol 14 (12) ◽  
pp. 1941-1949
Author(s):  
Seungkwon Choi ◽  
◽  
Sungwho Park ◽  
Iksoo Byon ◽  
Hee-Young Choi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Visual Acuity ◽  
Prediction Models ◽  
External Validation ◽  
Vitreous Hemorrhage ◽  
Final Visual Acuity ◽  
Open Globe Injury ◽  
Corneal Injury ◽  
Open Globe ◽  
Feature Importance

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.

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

2021 ◽  
Vol 11 (2) ◽  
pp. 297-300
Author(s):  
Nazia Imam ◽  
Mobashir Sarfraz Ali ◽  
Bibhuti Prassan Sinha ◽  
Gyan Bhaskar ◽  
Rakhi Kusumesh
Keyword(s):  
Visual Acuity ◽  
Clinical Features ◽  
Medical Records ◽  
Tertiary Care ◽  
Final Visual Acuity ◽  
Ocular Injury ◽  
Age Group ◽  
Mechanism Of Injury ◽  
Open Globe Injury ◽  
Open Globe

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.

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

2021 ◽  
Vol 14 (8) ◽  
pp. 1237-1240
Author(s):  
Maryam Zamani ◽  
◽  
Akbar Fotouhi ◽  
Morteza Naderan ◽  
Mohammad Soleimani ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Ocular Trauma ◽  
Final Visual Acuity ◽  
Open Globe Injury ◽  
Geriatric Population ◽  
Cross Sectional ◽  
Female Ratio ◽  
Globe Rupture ◽  
Open Globe ◽  
Open Globe Injuries

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.

scholarly journals Open-globe-injury: A single center Spanish retrospective 5-year cohort study

2020 ◽  
pp. 112067212096203
Author(s):  
Elena Guzmán-Almagro ◽  
Guillermo Fernandez-Sanz ◽  
Diana Herrero-Escudero ◽  
Inés Contreras ◽  
Julio González Martín-Moro
Keyword(s):  
Visual Acuity ◽  
Penetrating Trauma ◽  
Good Prognosis ◽  
Interquartile Range ◽  
Final Visual Acuity ◽  
Open Globe Injury ◽  
Visual Outcomes ◽  
Work Related ◽  
Open Globe ◽  
Senior Women

Purpose: To review and analyze the epidemiological profile, clinical characteristics and visual outcomes in patients attended for traumatic open globe injury (OGI) at our hospital over a 5-year period. Design: Retrospective chart review study. Methods: Retrospective analysis of all patients attended at Fundación Jiménez Díaz University Hospital for OGI between 2011 and 2015. Data from 104 patients including demographics, ocular examination, medical and surgical treatment, visual outcomes, and complications were analyzed. Results: Most patients were male (79.8%) and the median age at the time of injury was 41 years (interquartile range 31.5–58 years). Work-related accidents represent more than half of the cases and their main mechanism was penetrating trauma or foreign body. This type of accident had good prognosis (median final visual acuity in decimal scale 0.8; interquartile range 0.4–1). Falls were the second most common cause of OGI, predominantly affecting senior women (50%), with a high incidence of ocular rupture (50%) and associating a poor visual prognosis (median final visual acuity 0.01; interquartile range 0–0.5). There was a strong correlation (0.75; p < 0.001) between ocular trauma score (OTS) and final best corrected visual acuity. Conclusions: Two different patterns of OGI were identified in our sample. Work-related trauma in young males was the most common form of OGI and was associated with good prognosis. However, falls in senior women were associated with poor prognosis.

Surgical management and outcomes of pediatric open globe injuries requiring vitrectomy

2021 ◽  
pp. 112067212110006
Author(s):  
Xin Liu ◽  
Lufei Wang ◽  
Fengjuan Yang ◽  
Jia’nan Xie ◽  
Jinsong Zhao ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Surgical Management ◽  
Pediatric Patients ◽  
Vitreous Hemorrhage ◽  
Visual Outcome ◽  
Poor Visual Outcome ◽  
Early Vitrectomy ◽  
Open Globe ◽  
Time From Injury ◽  
Ocular Sign

Purpose: To describe surgical management and establish visual outcomes of open globe injury (OGI) in pediatric patients requiring vitrectomy. Methods: Forty-eight eyes of 48 pediatric patients underwent vitrectomy for OGI with secondary vitreoretinal complications in the eye center of Jilin University were included. Characteristics of patients, details of ocular examination and operation, presenting and final visual acuity were recorded. Results: Presenting visual acuity less than 20/400 was found in 44 eyes (91.7%), which included no light perception (NLP) in four eyes. At last visit, there was no eyes with visual acuity of NLP, and 19 eyes (39.6%) had a vision recovery to 20/400 or better. Mechanisms of injury, intraocular contents prolapse, presence of hyphema, intraocular foreign body, vitreous hemorrhage, retinal detachment, and total time from injury to PPV > 2 weeks were significant predictors of visual prognosis. Logistic regression analysis showed that hyphema was a significant predictive factor for poor visual outcome. Conclusion: Visual acuity was improved in most of the patients with OGI in this study. Hyphema is an important presenting ocular sign in estimating the post-vitrectomy visual outcome for OGI in children. Proper timing of vitrectomy is suggested, and in this study patients may benefit more with early vitrectomy as less proliferative vitreoretinopathy (PVR) was found together with a better visual acuity.

Abstract 196: Development and Validation of Machine Learning-based Race-specific Models to Predict 10-year Risk of Heart Failure: A Multi-cohort Analysis

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Matthew W Segar ◽  
Byron Jaeger ◽  
Kershaw V Patel ◽  
Vijay Nambi ◽  
Chiadi E Ndumele ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Heart Failure ◽  
Risk Prediction ◽  
Prediction Models ◽  
External Validation ◽  
Superior Performance ◽  
Risk Models ◽  
Black And White ◽  
White Adults

Introduction: Heart failure (HF) risk and the underlying biological risk factors vary by race. Machine learning (ML) may improve race-specific HF risk prediction but this has not been fully evaluated. Methods: The study included participants from 4 cohorts (ARIC, DHS, JHS, and MESA) aged > 40 years, free of baseline HF, and with adjudicated HF event follow-up. Black adults from JHS and white adults from ARIC were used to derive race-specific ML models to predict 10-year HF risk. The ML models were externally validated in subgroups of black and white adults from ARIC (excluding JHS participants) and pooled MESA/DHS cohorts and compared to prior established HF risk scores developed in ARIC and MESA. Harrell’s C-index and Greenwood-Nam-D’Agostino chi-square were used to assess discrimination and calibration, respectively. Results: In the derivation cohorts, 288 of 4141 (7.0%) black and 391 of 8242 (4.7%) white adults developed HF over 10 years. The ML models had excellent discrimination in both black and white participants (C-indices = 0.88 and 0.89). In the external validation cohorts for black participants from ARIC (excluding JHS, N = 1072) and MESA/DHS pooled cohorts (N = 2821), 131 (12.2%) and 115 (4.1%) developed HF. The ML model had adequate calibration and demonstrated superior discrimination compared to established HF risk models (Fig A). A consistent pattern was also observed in the external validation cohorts of white participants from the MESA/DHS pooled cohorts (N=3236; 100 [3.1%] HF events) (Fig A). The most important predictors of HF in both races were NP levels. Cardiac biomarkers and glycemic parameters were most important among blacks while LV hypertrophy and prevalent CVD and traditional CV risk factors were the strongest predictors among whites (Fig B). Conclusions: Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance when compared to traditional risk prediction models.

scholarly journals Party Poppers and Balloons: Fun and Games or Lives and Limbs?

2020 ◽  
Vol 36 (2) ◽  
Author(s):  
Fiza Shaheen ◽  
Rehan Naqaish ◽  
Muhammad Amer Awan
Keyword(s):  
Ocular Trauma ◽  
Vitreous Hemorrhage ◽  
Open Globe Injury ◽  
Lens Extraction ◽  
Safety Awareness ◽  
Full Thickness Macular Hole ◽  
Open Globe ◽  
Awareness Programs ◽  
Pars Plana ◽  
Popular Party

Abstract We report two cases of ocular trauma caused by recently popular party poppers and LED balloons, commonly used in parties nowadays. One case depicted a closed globe injury as a result of a party popper spray over the eye. The pressure of the spray resulted in a blunt trauma causing full thickness macular hole which was later treated with Pars Plana Vitrectomy (PPV) surgery. The second case is an example of an open globe injury caused by the bursting of LED balloon over the eye of a young child resulting in corneal perforation, traumatic cataract, vitreous hemorrhage with an intraocular foreign body (IOFB). It was successfully treated with corneal suturing, lens extraction, PPV surgery and removal of IOFB followed by a secondary lens implantation. Both of the sustained injuries were completely avoidable hence emphasizing the requirement of eye safety awareness programs and diligence in the use of these gadgets in everyday lives.

scholarly journals Machine learning-based clinical outcome prediction in surgery for acromegaly

Endocrine ◽  
2021 ◽  
Author(s):  
Olivier Zanier ◽  
Matteo Zoli ◽  
Victor E. Staartjes ◽  
Federica Guaraldi ◽  
Sofia Asioli ◽  
...  
Keyword(s):  
Machine Learning ◽  
Transsphenoidal Surgery ◽  
Prediction Models ◽  
External Validation ◽  
Clinical Prediction ◽  
Clinical Prediction Models ◽  
Total Resection ◽  
Prior Surgery ◽  
Using Data ◽  
Csf Leaks

Abstract Purpose Biochemical remission (BR), gross total resection (GTR), and intraoperative cerebrospinal fluid (CSF) leaks are important metrics in transsphenoidal surgery for acromegaly, and prediction of their likelihood using machine learning would be clinically advantageous. We aim to develop and externally validate clinical prediction models for outcomes after transsphenoidal surgery for acromegaly. Methods Using data from two registries, we develop and externally validate machine learning models for GTR, BR, and CSF leaks after endoscopic transsphenoidal surgery in acromegalic patients. For the model development a registry from Bologna, Italy was used. External validation was then performed using data from Zurich, Switzerland. Gender, age, prior surgery, as well as Hardy and Knosp classification were used as input features. Discrimination and calibration metrics were assessed. Results The derivation cohort consisted of 307 patients (43.3% male; mean [SD] age, 47.2 [12.7] years). GTR was achieved in 226 (73.6%) and BR in 245 (79.8%) patients. In the external validation cohort with 46 patients, 31 (75.6%) achieved GTR and 31 (77.5%) achieved BR. Area under the curve (AUC) at external validation was 0.75 (95% confidence interval: 0.59–0.88) for GTR, 0.63 (0.40–0.82) for BR, as well as 0.77 (0.62–0.91) for intraoperative CSF leaks. While prior surgery was the most important variable for prediction of GTR, age, and Hardy grading contributed most to the predictions of BR and CSF leaks, respectively. Conclusions Gross total resection, biochemical remission, and CSF leaks remain hard to predict, but machine learning offers potential in helping to tailor surgical therapy. We demonstrate the feasibility of developing and externally validating clinical prediction models for these outcomes after surgery for acromegaly and lay the groundwork for development of a multicenter model with more robust generalization.

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

2021 ◽  
Author(s):  
Haochi Ho ◽  
Jane Foo ◽  
Yi-Chiao Li ◽  
Samantha Bobba ◽  
Christopher Go ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Prognostic Factors ◽  
Retinal Detachment ◽  
Case Series ◽  
Final Visual Acuity ◽  
Ocular Injury ◽  
Visual Outcomes ◽  
Globe Rupture ◽  
Open Globe ◽  
Open Globe Injuries

Abstract 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.

Sign in / Sign up

Export Citation Format

Share Document