Macular thickness as a predictor of loss of visual sensitivity in ethambutol-induced optic neuropathy

Ethambutol is a common cause of drug-related optic neuropathy.Prediction of the onset of ethambutol-induced optic neuropathy and consequent drug withdrawal may be an effective method to stop visual loss.Previous studies have shown that structural injury to the optic nerve occurred earlier than the damage to visual function.Therefore,we decided to detect structural biomarkers marking visual field loss in early stage ethambutol-induced optic neuropathy.The thickness of peripapillary retinal nerve fiber layer,macular thickness and visual sensitivity loss would be observed in 11 ethambutol-induced optic neuropathy patients（22 eyes） using optical coherence tomography.Twenty-four healthy age-and sex-matched participants（48 eyes） were used as controls.Results demonstrated that the temporal peripapillary retinal nerve fiber layer thickness and average macular thickness were thinner in patients with ethambutol-induced optic neuropathy compared with healthy controls.The average macular thickness was strongly positively correlated with central visual sensitivity loss（r2=0.878,P=0.000）.These findings suggest that optical coherence tomography can be used to efficiently screen patients.Macular thickness loss could be a potential factor for predicting the onset of ethambutol-induced optic neuropathy.

Prediction of effluent concentration in a wastewater treatment plant using machine learning models

Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen（T-N） impact on the effluent water quality. The objective of this study is to establish two machine learning models-artificial neural networks（ANNs） and support vector machines（SVMs）, in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination（R^2）, Nash-Sutcliff efficiency（NSE）, relative efficiency criteria（d rel）. Additionally, Latin-Hypercube one-factor-at-a-time（LH-OAT） and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.