AIM:To predict best-corrected visual acuity(BCVA)by machine learning in patients with ocular trauma who were treated for at least 6mo.METHODS:The internal dataset consisted of 850 patients with 1589 eyes and an averag...AIM:To predict best-corrected visual acuity(BCVA)by machine learning in patients with ocular trauma who were treated for at least 6mo.METHODS:The internal dataset consisted of 850 patients with 1589 eyes and an average age of 44.29y.The initial visual acuity was 0.99 log MAR.The test dataset consisted of 60 patients with 100 eyes collected while the model was optimized.Four different machine-learning algorithms(Extreme Gradient Boosting,support vector regression,Bayesian ridge,and random forest regressor)were used to predict BCVA,and four algorithms(Extreme Gradient Boosting,support vector machine,logistic regression,and random forest classifier)were used to classify BCVA in patients with ocular trauma after treatment for 6mo or longer.Clinical features were obtained from outpatient records,and ocular parameters were extracted from optical coherence tomography images and fundus photographs.These features were put into different machine-learning models,and the obtained predicted values were compared with the actual BCVA values.The best-performing model and the best variable selected were further evaluated in the test dataset.RESULTS:There was a significant correlation between the predicted and actual values[all Pearson correlation coefficient(PCC)>0.6].Considering only the data from the traumatic group(group A)into account,the lowest mean absolute error(MAE)and root mean square error(RMSE)were 0.30 and 0.40 log MAR,respectively.In the traumatic and healthy groups(group B),the lowest MAE and RMSE were 0.20 and 0.33 log MAR,respectively.The sensitivity was always higher than the specificity in group A,in contrast to the results in group B.The classification accuracy and precision were above 0.80 in both groups.The MAE,RMSE,and PCC of the test dataset were 0.20,0.29,and 0.96,respectively.The sensitivity,precision,specificity,and accuracy of the test dataset were 0.83,0.92,0.95,and 0.90,respectively.CONCLUSION:Predicting BCVA using machine-learning models in patients with treated ocular trauma is accurate and helpful in the identification of visual dysfunction.展开更多
AIM: To complete the data of ocular trauma in central China, as a well-known tertiary referral center for ocular trauma, we documented the epidemiological characteristics and visual outcomes of patients hospitalized f...AIM: To complete the data of ocular trauma in central China, as a well-known tertiary referral center for ocular trauma, we documented the epidemiological characteristics and visual outcomes of patients hospitalized for ocular trauma in this region.METHODS: A retrospective study of patients hospitalized for ocular trauma in central China from 2006 to 2011 was performed.· RESULTS: This study included 5964 eyes of 5799 patients. The average age was 35.5 ±21.8y with a male-to-female ratio of 2.8:1. The most common age was 45-59 y age group. Most patients were farmers and workers(51.9%). The most common injuries were firework related(24.5%), road traffic related(24.2%), and work related(15.0%). Among the most common causative agents were firecrackers(24.5%), followed by metal/knife/scissors(21.4%). Most injuries occurred in January(14.2%),February(27.0%), and August(10.0%). There were 8.5%patients with ocular injuries combined with other injuries.The incidence of open ocular injuries(4585 eyes, 76.9%)was higher than closed ocular injuries(939 eyes, 15.7%).The incidences of chemical and thermal ocular injuries were 1.2% and 0.6%. Ocular trauma score(OTS)predicted final visual acuity at non light perception(NLP), 20/200-20/50 and 20/40 with a sensitivity of 100%,and light perception(LP) /hand motion(HM) and 1/200-19/200 with a specificity of 100%.· CONCLUSION: This study provides recent epidemiological data of patients hospitalized for ocular trauma in central China. Some factors influencing the visual outcome include time interval between injury and visit to the clinic, wound location, open or closed globe injury, initial visual acuity, and OTS.展开更多
基金Supported by National Key R&D Program of China(No.2022YFC3302001)the Human Injury and Disability Degree Classification(No.SF20181312)the National Natural Science Foundation of China(No.62071285)。
文摘AIM:To predict best-corrected visual acuity(BCVA)by machine learning in patients with ocular trauma who were treated for at least 6mo.METHODS:The internal dataset consisted of 850 patients with 1589 eyes and an average age of 44.29y.The initial visual acuity was 0.99 log MAR.The test dataset consisted of 60 patients with 100 eyes collected while the model was optimized.Four different machine-learning algorithms(Extreme Gradient Boosting,support vector regression,Bayesian ridge,and random forest regressor)were used to predict BCVA,and four algorithms(Extreme Gradient Boosting,support vector machine,logistic regression,and random forest classifier)were used to classify BCVA in patients with ocular trauma after treatment for 6mo or longer.Clinical features were obtained from outpatient records,and ocular parameters were extracted from optical coherence tomography images and fundus photographs.These features were put into different machine-learning models,and the obtained predicted values were compared with the actual BCVA values.The best-performing model and the best variable selected were further evaluated in the test dataset.RESULTS:There was a significant correlation between the predicted and actual values[all Pearson correlation coefficient(PCC)>0.6].Considering only the data from the traumatic group(group A)into account,the lowest mean absolute error(MAE)and root mean square error(RMSE)were 0.30 and 0.40 log MAR,respectively.In the traumatic and healthy groups(group B),the lowest MAE and RMSE were 0.20 and 0.33 log MAR,respectively.The sensitivity was always higher than the specificity in group A,in contrast to the results in group B.The classification accuracy and precision were above 0.80 in both groups.The MAE,RMSE,and PCC of the test dataset were 0.20,0.29,and 0.96,respectively.The sensitivity,precision,specificity,and accuracy of the test dataset were 0.83,0.92,0.95,and 0.90,respectively.CONCLUSION:Predicting BCVA using machine-learning models in patients with treated ocular trauma is accurate and helpful in the identification of visual dysfunction.
基金Supported by National Key Basic Research Program of China(973 Program)(No.2013CB967001)National Natural Science Foundation of China(31271400)+3 种基金Medical Science and Technology Research Project of Henan Province,China(No.201203021)2014 Annual Science and Technology Key Project of Education Department of Henan Province(No.14A320085)the Team Construction and Innovative Research of the First Affiliated Hospital of Zhengzhou University of 2011Youth Innovation Foundation of the First Affiliated Hospital of Zhengzhou University of 2011
文摘AIM: To complete the data of ocular trauma in central China, as a well-known tertiary referral center for ocular trauma, we documented the epidemiological characteristics and visual outcomes of patients hospitalized for ocular trauma in this region.METHODS: A retrospective study of patients hospitalized for ocular trauma in central China from 2006 to 2011 was performed.· RESULTS: This study included 5964 eyes of 5799 patients. The average age was 35.5 ±21.8y with a male-to-female ratio of 2.8:1. The most common age was 45-59 y age group. Most patients were farmers and workers(51.9%). The most common injuries were firework related(24.5%), road traffic related(24.2%), and work related(15.0%). Among the most common causative agents were firecrackers(24.5%), followed by metal/knife/scissors(21.4%). Most injuries occurred in January(14.2%),February(27.0%), and August(10.0%). There were 8.5%patients with ocular injuries combined with other injuries.The incidence of open ocular injuries(4585 eyes, 76.9%)was higher than closed ocular injuries(939 eyes, 15.7%).The incidences of chemical and thermal ocular injuries were 1.2% and 0.6%. Ocular trauma score(OTS)predicted final visual acuity at non light perception(NLP), 20/200-20/50 and 20/40 with a sensitivity of 100%,and light perception(LP) /hand motion(HM) and 1/200-19/200 with a specificity of 100%.· CONCLUSION: This study provides recent epidemiological data of patients hospitalized for ocular trauma in central China. Some factors influencing the visual outcome include time interval between injury and visit to the clinic, wound location, open or closed globe injury, initial visual acuity, and OTS.
