Objective:To use machine learning to predict the efficacy of accelerated corneal collagen cross-linking (A-CXL) surgery, identify prognostic factors, and construct models to predict postoperative disease progression.Methods:A single-center retrospective study was conducted.A total of 82 keratoconus patients (112 eyes) who underwent A-CXL surgery at the West China Hospital of Sichuan University between March and December 2021 were enrolled.Preoperative and follow-up examinations included anterior segment evaluation by slit-lamp microscopy, corneal topography using Pentacam, and corneal biomechanical indices using Corvis ST.Disease progression was defined as an increase in maximum keratometry (Kmax) of ≥1 D from the preoperative level at the last follow-up.Various machine learning algorithms were employed to analyze corneal topography, biomechanical parameters and corneal densitometry values to identify prognostic factors and construct models for predicting postoperative disease progression.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of West China Hospital, Sichuan University (No.2023496).Written informed consent was obtained from each subject.Results:During follow-up, 15.1% (17/112) of the eyes showed progression after A-CXL.The preoperative astigmatism and stress-strain index (SSI) in the progression group were (-5.41±2.72)D and 1.41±0.78, respectively, which were significantly higher than (-3.30±2.54)D and 0.95±0.98 in the non-progression group ( t=2.80, 2.03; both P<0.05).Cox regression analysis identified preoperative astigmatism (hazard ratio [HR]=1.20), SSI (HR=1.10), and anterior corneal densitometry of 2-6 mm (CDA6) (HR=2.10) as significant risk factors for post-A-CXL progression.Among various machine learning models developed and validated, the area under the curve (AUC) values for logistic regression, multilayer perceptron (MLP) model, and random forest (RF) exceeded 0.700.For F1-score, the AUC values for logistic regression, MLP, and RF were 0.870, 0.880, and 0.880, respectively.The network structure of the visualized MLP was a single-layer, 24-neurons neural network with 80% accuracy in predicting whether progression occurred after A-CXL.The clinical nomogram developed in conjunction with astigmatism, SSI, and CDA6 predicted the cumulative probability of progression at 0.5, 1, and 2 years postoperatively based on the sum of the specified values for each variable, and based on the optimal cutoff value, keratoconus corneas could be classified into high-, intermediate-, and low-risk groups, respectively.The time-dependent subject operating characteristic curves of the nomogram showed AUCs of 0.734, 0.685, and 0.935 at 0.5, 1, and 2 years postoperatively, respectively, all of which performed well in predicting progression. Conclusions:Preoperative astigmatism, SSI, and CDA6 are significant risk factors for post-A-CXL progression in keratoconus.The MLP model can accurately predict postoperative disease progression, and the clinical nomogram combining preoperative astigmatism, SSI, and CDA6 can effectively differentiate between low-, medium-, and high-risk postoperative progression outcomes.

Objective:To use machine learning to predict the efficacy of accelerated corneal collagen cross-linking (A-CXL) surgery, identify prognostic factors, and construct models to predict postoperative disease progression.Methods:A single-center retrospective study was conducted.A total of 82 keratoconus patients (112 eyes) who underwent A-CXL surgery at the West China Hospital of Sichuan University between March and December 2021 were enrolled.Preoperative and follow-up examinations included anterior segment evaluation by slit-lamp microscopy, corneal topography using Pentacam, and corneal biomechanical indices using Corvis ST.Disease progression was defined as an increase in maximum keratometry (Kmax) of ≥1 D from the preoperative level at the last follow-up.Various machine learning algorithms were employed to analyze corneal topography, biomechanical parameters and corneal densitometry values to identify prognostic factors and construct models for predicting postoperative disease progression.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of West China Hospital, Sichuan University (No.2023496).Written informed consent was obtained from each subject.Results:During follow-up, 15.1% (17/112) of the eyes showed progression after A-CXL.The preoperative astigmatism and stress-strain index (SSI) in the progression group were (-5.41±2.72)D and 1.41±0.78, respectively, which were significantly higher than (-3.30±2.54)D and 0.95±0.98 in the non-progression group ( t=2.80, 2.03; both P<0.05).Cox regression analysis identified preoperative astigmatism (hazard ratio [HR]=1.20), SSI (HR=1.10), and anterior corneal densitometry of 2-6 mm (CDA6) (HR=2.10) as significant risk factors for post-A-CXL progression.Among various machine learning models developed and validated, the area under the curve (AUC) values for logistic regression, multilayer perceptron (MLP) model, and random forest (RF) exceeded 0.700.For F1-score, the AUC values for logistic regression, MLP, and RF were 0.870, 0.880, and 0.880, respectively.The network structure of the visualized MLP was a single-layer, 24-neurons neural network with 80% accuracy in predicting whether progression occurred after A-CXL.The clinical nomogram developed in conjunction with astigmatism, SSI, and CDA6 predicted the cumulative probability of progression at 0.5, 1, and 2 years postoperatively based on the sum of the specified values for each variable, and based on the optimal cutoff value, keratoconus corneas could be classified into high-, intermediate-, and low-risk groups, respectively.The time-dependent subject operating characteristic curves of the nomogram showed AUCs of 0.734, 0.685, and 0.935 at 0.5, 1, and 2 years postoperatively, respectively, all of which performed well in predicting progression. Conclusions:Preoperative astigmatism, SSI, and CDA6 are significant risk factors for post-A-CXL progression in keratoconus.The MLP model can accurately predict postoperative disease progression, and the clinical nomogram combining preoperative astigmatism, SSI, and CDA6 can effectively differentiate between low-, medium-, and high-risk postoperative progression outcomes.

Background Affected by concentration, composition, and population tolerance of air pollutants, the relationship between air pollutants and population health has regional differences. There is still a research gap in Guiyang. Objective To explore the short-term effects of air pollutant concentrations in low-pollution areas on the outpatient volume of respiratory diseases. Methods Spearman correlation analysis was used to evaluate the correlation between air pollutants, meteorological factors, and respiratory outpatient volume from January 1, 2013 to December 31, 2020 in Guiyang City. A single pollutant distribution lag nonlinear model and a multi-pollutant interaction model were established based on Poisson distribution. A three-dimensional diagram was drawn to display the relationship between air pollutants and respiratory outpatient volume. Quantitative analysis was conducted on the attribution risk and lag effect of air pollutant concentration on outpatient volume of respiratory diseases in Guiyang City. Results The results of the single pollutant model showed that fine particulate matter (PM_2.5), nitrogen dioxide (NO₂), carbon monoxide (CO), and sulfur dioxide (SO₂) elevated the outpatient volume of respiratory diseases. The maximum relative risk (RR) and 95%CI values of PM_2.5, NO₂,CO, and SO₂ appeared on Day 2, 0, 5, and 6, respectively, which were 1.019 (1.015, 1.023), 1.146 (1.122, 1.171), 1.129 (1.116, 1.143), and 1.046(1.040, 1.052), respectively. For every quartile concentration increment of PM_2.5, NO₂, CO, or SO₂, the outpatient volume of respiratory diseases increased by 0.943% (0.111%, 1.782%), 4.050% (3.573%, 4.529%), 0.595% (0.317%, 0.874%), or 0.667% (0.235%, 1.100%), respectively. The maximum RR (95%CI) of O₃ was 1.015 (1.007, 1.023) and appeared on Day 0. The results of multi-pollutant model showed that PM_2.5, NO₂, CO, SO₂, and O₃ all elevated the outpatient volume of respiratory diseases. The maximum RR values of PM_2.5, NO₂, CO, SO₂ and O₃ appeared on Day 14, 0, 5, 7 and 0, respectively, which were 1.027 (1.021, 1.034), 1.213 (1.179, 1.248), 1.059 (1.043, 1.074), 1.016 (1.005, 1.026), and 1.024 (1.015, 1.033), respectively. Compared with the single pollutant model, the RR values of PM_2.5, NO₂, and O₃ on the outpatient volume of respiratory diseases in the multi-pollutant model showed an upward trend, while the RR values of CO and SO₂ in the multi-pollutant model showed a downward trend. Conclusion The impact of low concentrations of PM_2.5, NO₂, CO, and SO₂ on human health cannot be ignored.

Objective:To investigate the role of chemokine receptor CX3CR1 in chronic skin inflammation and its regulatory mechanism.Methods:Wild type (WT) C57BL/6 mice and Cx3 cr1 GFP/GFP mice were induced by DNFB to establish acute and chronic allergic contact dermatitis (ACD) model. Ear inflammation and swelling were observed with hematoxylin-eosin (HE) staining. Flow cytometry (FCM) was used to detect the changes in classical Langerhans cell (LC) and monocyte-derived LC (Mo-LC), as well as the expression of major histocompatibility complex Ⅱ (MHCⅡ), inducible nitric oxide synthase (iNOS) and TNF-α. Changes in epidermal LC in UV irradiation-induced dermatitis models were also analyzed. In human chronic skin inflammation, CX3CL1 expression was detected using immunohistochemistry, RT-PCR and Western blot and CD1a, CD14 and CD207 expression was observed with immunofluorescence staining. Results:In the chronic ACD model, Cx3 cr1 GFP/GFP mice showed significantly alleviated ear inflammatory and swelling as compared with WT mice, but no significant difference was found in the acute ACD model. The percentages of Mo-LC were decreased in the chronic ACD model and after three weeks of UV irradiation. Moreover, MHCⅡ, TNF-α and iNOS expressed by Mo-LC were significantly upregulated as compared with those by classical LC. CX3CL1 expression was significantly upregulated and the numbers of CD14 + monocytes and CD1a + langerin - Mo-LC were dramatically increased in human chronic skin inflammation. Conclusions:CX3CR1 might maintain inflammatory response by regulating local remodeling of Mo-LC in chronic skin inflammation.

The advances of industrial biotechnology highly depend on the development of industrial bioprocess researches. In China, we are facing several challenges because of a huge national industrial fermentation capacity. The industrial bioprocess development experienced several main stages. This work mainly reviews the development of the industrial bioprocess in China during the past 30 or 40 years: including the early stage kinetics model study derived from classical chemical engineering, researching method based on control theory, multiple-parameter analysis techniques of on-line measuring instruments and techniques, and multi-scale analysis theory, and also solid state fermentation techniques and fermenters. In addition, the cutting edge of bioprocess engineering was also addressed.
Bioengineering ; history ; Bioreactors ; Biotechnology ; Chemical Engineering ; China ; Fermentation ; History, 20th Century ; History, 21st Century

Filamentous fungi are widely used in industrial fermentation. Particular fungal morphology acts as a critical index for a successful fermentation. To break the bottleneck of morphological analysis, we have developed a reliable method for fungal morphological analysis. By this method, we can prepare hundreds of pellet samples simultaneously and obtain quantitative morphological information at large scale quickly. This method can largely increase the accuracy and reliability of morphological analysis result. Based on that, the studies of Aspergillus niger morphology under different oxygen supply conditions and shear rate conditions were carried out. As a result, the morphological responding patterns of A. niger morphology to these conditions were quantitatively demonstrated, which laid a solid foundation for the further scale-up.
Aspergillus niger ; cytology ; Fermentation ; Industrial Microbiology ; Reproducibility of Results