Predicting visual acuity with machine learning in treated ocular trauma patients

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.

Catalytic effects of NH4+ on hydrogen evolution and manganese electrodeposition on stainless steel

The effects of(NH4)2SO4 concentration(c((NH4)2SO4))on hydrogen evolution and Mn electrodeposition on stainless steel(SS)in different potential ranges were investigated by linear sweep voltammetry(LSV),electrochemical impedance spectroscopy(EIS),potentiostatic polarization,chronoamperometry,scanning electron microscope(SEM)and X-ray diffraction(XRD)techniques.The results show that the NH4^+discharge reaction(NDR)intensifies the overall hydrogen evolution kinetics,and the NDR is catalyzed by increasing c((NH4)2SO4)and over-potential.The electro-crystallization of Mn on SS follows a three-dimensional progressive nucleation and diffusion-limited growth mechanism.Increasing the over-potential could accelerate the nucleation rate and also cause the decline of the nucleation density.The absorbed Mn^2+preferably discharges at low over-potential.Increasing c((NH4)2SO4)at medium over-potential could improve the current efficiency and produce more block-like grains.The nucleation process is suppressed by increasing c((NH4)2SO4)at high over-potential,at which the formation of columnar grains with higher hydrogen contents becomes prevailing.

Comparison of corrosion and oxygen evolution behaviors between cast and rolled Pb–Ag–Nd anodes

The corrosion and oxygen evolution behaviors of cast and rolled Pb–Ag–Nd anodes were investigated by metalloscopy, environmental scanning electron microscopy, X-ray diffraction analysis, and various electrochemical measurements. The rolled anode exhibits fewer interdendritic boundaries and a dispersed distribution of Pb–Ag eutectic mixtures and Nd-rich phases in its cross-section. This feature inhibits rapid interdendritic corrosion into the metallic substrate along the interdendritic boundary network. In addition, the anodic layer formed on the rolled anode is more stable toward the electrolyte than that formed on the cast anode, reducing the corrosion of the metallic substrate during current interruption. Hence, the rolled anode has a higher corrosion resistance than the cast anode. However, the rolled anode exhibits a slightly higher anodic potential than the cast anode after 72 h of galvanostatic polarization, consistent with the larger charge transfer resistance. This larger charge transfer resistance may result from the oxygen-evolution reactive sites being blocked by the adsorption of more intermediates and oxygen species at the anodic layer/electrolyte interfaces of the rolled anode than at the interfaces of cast anode.

An association study of HFEgene mutation with idiopathic male infertility in the Chinese Han population

Mutations in the haemochromatosis gene （HFE） influence iron status in the general population of Northern Europe, and excess iron is associated with the impairment of spermatogenesis. The aim of this study is to investigate the association between three mutations （C282Y, H63D and S65C） in the HFEgene with idiopathic male infertility in the Chinese Han population. Two groups of Chinese men were recruited： 444 infertile men （including 169 with idiopathic azoospermia） and 423 controls with proven fertility. The HFEgene was detected using polymerase chain reaction-restriction fragment length polymorphism （PCR-RFLP） technique. The experimental results demonstrated that no C282Y or $65C mutations were detected. Idiopathic male infertility was not significantly associated with heterozygous H63D mutation （odds ratio=O.801, 95% confidence interval=0.452-1.421, X2=0.577, P=0.448）. The H63D mutation frequency did not correlate significantly with the serum luteinizing hormone （LH）, follicle-stimulating hormone （FSH） and testosterone （T） levels in infertile men （P=0.896, P=0.404 and P=O.05, respectively）. Our data suggest that the HFEH63D mutation is not associated with idiopathic male reproductive dysfunction.

Superparamagnetic CoFe2O4@Au with High Specific Absorption Rate and Intrinsic Loss Power for Magnetic Fluid Hyperthermia Applications

CoFe2O4 nanoparticles(NPs)and surface modified with gold(Au)have been synthesized by a thermal decomposition method.The obtained NPs and formation of CoFe2O4@Au core–shell(CS)were confirmed by characterizing their structural and optical properties using X-ray powder diffraction(XRD)patterns,Fourier transform infrared spectroscopy,Raman spectroscopy,UV–Visible and photoluminescence studies.Morphological and compositional studies were carried out using high-resolution transmission electron microscopy and energy-dispersive X-ray spectroscopy,while the magnetic properties were determined using alternating gradient magnetometer and Mossbauer to define the magneto-structural effects of shell formation on the core NPs.Induction heating properties of CoFe2O4 and CoFe2O4@Au CS magnetic nanoparticles(MNPs)have been investigated and correlated with magneto-structural properties.Specific absorption rate and intrinsic loss power were calculated for these MNPs within the human tolerable range of frequency and amplitude,suggesting their potential in magnetic fluid hyperthermia therapy for possible cancer treatment.