Comparison of LASSO and random forest models for predicting the risk of premature coronary artery disease.

PURPOSE: With the change of lifestyle, the occurrence of coronary artery disease presents a younger trend, increasing the medical and economic burden on the family and society. To reduce the burden caused by this disease, this study applied LASSO Logistic Regression and Random Forest to establish a risk prediction model for premature coronary artery disease(PCAD) separately and compared the predictive performance of the two models. METHODS: The data are obtained from 1004 patients with coronary artery disease admitted to a third-class hospital in Liaoning Province from September 2019 to December 2021. The data from 797 patients were ultimately evaluated. The dataset of 797 patients was randomly divided into the training set (569 persons) and the validation set (228 persons) scale by 7:3. The risk prediction model was established and compared by LASSO Logistic and Random Forest. RESULT: The two models in this study showed that hyperuricemia, chronic renal disease, carotid artery atherosclerosis were important predictors of premature coronary artery disease. A result of the AUC between the two models showed statistical difference (Z = 3.47, P < 0.05). CONCLUSIONS: Random Forest has better prediction performance for PCAD and is suitable for clinical practice. It can provide an objective reference for the early screening and diagnosis of premature coronary artery disease, guide clinical decision-making and promote disease prevention.

Three-dimensional fluorinated covalent organic frameworks coated capillary for the separation of fluoroquinolones by capillary electrochromatography.

In this work, a three-dimensional fluorinated covalent organic frameworks (3D FCOFs) JUC-515 was synthesized from tetra(4-aminophenyl)methane (TAM) and 2,3,5,6-tetrafluoroterephthalol (TFA) by an ionic liquid method. JUC-515 was introduced into the capillary column and bonded to the inner wall of the capillary column by chemical bonding. Through a variety of characterization results, JUC-515 was successfully synthesized and introduced into the capillary column. The effects of buffer solution concentration, organic additive content and pH of the buffer solution on the separation of fluoroquinolones (FQs) were investigated in detail. The JUC-515-coated capillary column showed good resolution (>1.5) and reproducibility. The relative standard deviations (RSDs) of the retention time for intraday, interday, column-to-column and interbatch precision were less than 0.88%, 2.45%, 2.74% and 3.32%, respectively. The RSDs of the peak area for intraday, interday, column-to-column and interbatch precision were less than 3.79%, 4.31%, 3.33% and 5.62%, respectively. The JUC-515-coated capillary column could be used no less than 150 times. The results showed that the JUC-515-coated capillary column had good separation performance. In addition, by separating fluorinated ß-phenylalanine analogs, ß-phenylalanine and trifluoromethyl ß-phenylalanine analogs, the separation mechanism based on fluorine interactions was discussed. In conclusion, JUC-515 had good potential as a stationary phase for capillary electrochromatography.