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.

Objective To explore the clinical features, diagnosis, and treatment of neonatal necrotizing pneumonia. Methods The clinical data of two cases of neonatal necrotizing pneumonia were retrospectively analyzed. The clinical features, diagnosis, and treatment of neonatal necrotizing pneumonia in literatures were summarized. Results Two cases were diagnosed of community-acquired Staphylococcus aureus necrotizing pneumonia and had the onset with fever. The chest X-ray showed exudative change with cystic shadow. The chest CT showed multiple cavity changes. The sputum and blood cultures were positive for Staphylococcus aureus. Both of them were effectively treated by vancomycin. The imaging was improved during the follow-up. Searching the database, 4 related literatures were being found, and there were totally 7 cases of neonatal necrotizing pneumonia including current 2 cases. The main features were as follows: The pathogenic bacteria in all cases include Staphylococcus aureus. One case was combined with pseudomonas aeruginosa. Six cases were community-acquired infections. All of them were non-immune deficiency newborn. Six cases were primary necrotizing pneumonia. Six cases were unilateral lung involvement. Five cases got fever, 5 cases had septicemia, 3 cases had pleural effusion, 2 cases had aerothorax, one case had bronchial chest and 2 cases had extrapulmonary infection. The C-reactive protein was increased in all cases. Three cases need mechanical ventilation. Six cases had a good prognosis. Conclusions The main pathogenic bacterium in neonatal necrotizing pneumonia was Staphylococcus aureus. The diagnosis was mainly depends on the typical imaging and pathogenic examination. The treatment is mainly the use of antibiotic for gram positive cocci.

Background Dry eye is a common disease worldwide.Cyclosporine A(CsA) is provided to be a immunosuppressive agent and is effective on dry eye.But in China,0.05％ CsA is not yet applied in dry eye treatment.Objective This study was to evaluate the efficacy and safety of 0.05％ CsA eye drops in the treatment of dry eye.Methods This was a randomized,double-blind,vehicle-controlled parallel group study.Forty eyes of 40 patients with moderate to severe dry eye were randomly divided into two groups,with the corresponding treatment of 0.05％ CsA eye drops or the vehicle emulsion.The patients in both the groups received non-preserved artificial tear.Symptoms and signs were observed before administration,(7±1),(28±2),(56±3),and (84±3) days and also 14 days after withdrawal.The clinical effective rate was considered as the primary outcome.The subjective assessment of the patients including total symptom scores and ocular surface disease index (OSDI) scores,Schirmer Ⅰ test (S Ⅰ t) with topical anaesthesia,tear film breakup time (BUT),rose Bengal and fluorescein staining scores were evaluated.The safety profile was evaluated by adverse events,visual acuity and ocular tolerance.Results At the end of this trial,the ocular symptoms scores,conjunctival hyperemia,BUT,S Ⅰ t and keratoconjunctiva staining scores of the two groups had statistically significant difference.The total effective rate of 0.05％ CsA treatment group was 75％ (15/20) and vehicle group was 25％ (5/20).There was a statistically significant difference between groups (P =0.000),and the 95％ confidence interval (C1) of the difference value of total effectiveness between the two groups was 30.80％-53.75％.At the end of this trial,there was no statistically significant difference in visual acuity distribution (P =0.890).No obvious discomfort was found in the patients received 0.05％ CsA eye drops.There were no adverse events during the follow-up duration.Conclusions 0.05％ CsA ophthalmic emulsion is an effective and safe treatment for dry eyes.

ObjectiveTo investigate the safety and curative effect of common bile duct primary closure in laparoscopic and choledochoscopic choledocholithotomy.MethodsClinical data of 178 patients with choledocholithiasis diagnosed and treated in Chaozhou Central Hospital between January 2011 and December 2014 were retrospectively studied. Among the 178 patients, 83 were males and 95 were females with the average age of (46±3) years old. The informed consents of all patients were obtained and the local ethical committee approval had been received. All patients underwent laparoscopic and choledochoscopic choledocholithotomy and were divided into the primary closure group and the T-tube drainage group according to the different treatment for the incision of choledocholithotomy. The patients in the primary closure group underwent primary closure of common bile duct and the patients in the T-tube drainage group received T-tube drainage following choledocholithotomy. The operation duration, exhaust time, length of stay, hospitalization expenses and postoperative complication of two groups were observed. The observation indexes of two groups were compared usingt test or Chi-square test.ResultsThe patients in two groups completed choledocholithotomy successfully. The operation duration, exhaust time, length of stay, hospitalization expenses were respectively (119±18) min, (25±7) h, (6±1) d, (12 000±2 000) yuan in the primary closure group, and were respectively (136±20) min, (38±8) h, (10±1) d, (15 000±2 000) yuan in the T-tube drainage group. And significant difference was observed (t=2.38, 5.00, 7.21, 3.87;P<0.05). The incidence of postoprative complication in the primary closure group was 8%(3/37), which was signiifcantly lower than 12%(17/141) in the T-tube drainage geoup (χ2=3.28,P<0.05). In the primary closure group, 3 patients developed bile leakage and 1 developed incision infection. In the T-tube drainage group, 1 patient developed bile leakage, 5 gallbladder fossa hydrops, 11 incision infection and 10 adhesive intestinal obstruction. All patients recovered after symptomatic treatments.ConclusionCommon bile duct primary closure in laparoscopic and choledochoscopic choledocholithotomy is safe, effective and has the advantages of quick recovery, low costs and low complication incidence.