AIM: To establish an intelligent diagnostic model of keratoconus for small-diameter corneas by data mining and analysis of patients' clinical data.METHODS: Diagnostic study. A total of 830 patients(830 eyes)were collected, including 338 male(338 eyes)and 492 female(492 eyes), with an average age of 14-36(23.19±5.71)years. Among them, 731 patients(731 eyes)had undergone corneal refractive surgery at Chongqing Nanping Aier Eye Hospital from January 2020 to March 2022, and 99 patients had a diagnosed keratoconus from January 2015 to March 2022. Corneal diameter ≤11.1 mm was measured by Pentacam in all patients. Two cornea specialists classified patients' data into normal corneas, suspect keratoconus, and keratoconus groups based on the Belin/Ambrósio enhanced ectasia display(BAD)system in Pentacam. The data of 665 patients were randomly selected as the training set and the other 165 patients as the validation set by computer random sampling method. Seven parametric corneal features were extracted by convolutional neural networks(CNN), and the models were built by Residual Network(ResNet), Vision Transformer(ViT), and CNN+Transformer, respectively. The diagnostic accuracy of models was verified by cross-entropy loss and cross-validation method. In addition, sensitivity and specificity were evaluated using receiver operating characteristic curve.RESULTS: The accuracy of ResNet, ViT, and CNN+Transfermer for the diagnosis of normal cornea and suspect keratoconus was 85.57%, 86.11%, and 86.54% respectively, and the area under the receiver operating characteristic curve(AUC)was 0.823, 0.830 and 0.842 respectively. The accuracy of models for the diagnosis of suspect keratoconus and keratoconus was 97.22%, 95.83%, and 98.61%, respectively, and the AUC was 0.951, 0.939, and 0.988 respectively.CONCLUSION: For corneas ≤11.1 mm in diameter, the data model established by CNN+Transformer has a high accuracy rate for classifying keratoconus, which provides real and effective guidance for early screening.

This study established a rapid UPLC-TQ-MS/MS method for determination of eight active ingredients in Lilium lancifolium. The contents range of regaloside E, F, C and B are as follows: 0.604 0×10⁻¹-18.62×10⁻¹, 0.680 0×10⁻²-44.75×10⁻², 0.700 0×10⁻³-29.65×10⁻¹, 0.170 0×10⁻¹-4.724 mg•g⁻¹; the contents of chlorogenic acid, caffeic acid, protocatechualdehyde and ferulic acid, within the range of 6.827×10⁻³-16.07×10⁻³, 0.011 1×10⁻³-79.71×10⁻³, 0.593 7×10⁻³-2.962×10⁻³, 2.606×10⁻²-45.89×10⁻² mg•g⁻¹, respectively. According to PCA (principal components analysis) plotting, 35 batches can be divided into two categories, namely Anhui Huoshan and Hunan Longshan. The main different elements between these two categories are caffeic acid and ferulic acid according to the VIP (variable importance in the projection) points figure. Based on comprehensive principal component values, there are eight batches of L. lancifolium from Huoshan among the comprehensive ranking of ten. The UPLC-TQ-MS method for simultaneous analysis of eight active ingredients is accurate, efficient and convenient. This result can provide scientific basis for quality control of L. lancifolium.