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.

Comparison of the binding character of triflavin on resting and activated alpha(IIb)beta(3) integrin in human platelets by electron microscopy.

Triflavin, an Arg-Gly-Asp (RGD)-containing disintegrin purified from venom peptide inhibited platelet aggregation by interfering with the interaction of fibrinogen with alpha(IIb)beta(3) integrin. Using an immunostaining technique and electron microscopy, we investigated and compared the distribution of triflavin binding in both resting and activated platelets. Triflavin uniformly and strongly stained the plasma membrane and the open canalicular system (OCS), whereas a lesser extent of staining was seen on alpha-granules in both resting and activated platelets. Furthermore, resting unfixed platelets were incubated with triflavin for 10 min at 4 degrees C, and then rewarmed at 30 degrees C for 0, 10, and 30 min to advance internalization. At 0 min, platelets showed an extensive rim-staining pattern of bound triflavin on the surface membrane, which was then gradually internalized into the cytoplasmic OCS with prolonging of incubation times. However, triflavin bound fewer to alpha-granules than to the OCS within the 0-30-min period of internalization in both resting and activated platelets. Furthermore, triflavin did not influence physiological endocytosis in resting platelets. Comparing the 3D structures of triflavin and another disintegrin, echistatin, we found that the spatial differences between the RGD motif and the C-termini of structures of disintegrins may mediate functional differences of binding activity towards alpha(IIb)beta(3) integrin in resting platelets. These data indicate that (1) triflavin binds effectively to alpha(IIb)beta(3) on the platelet membrane and cytoplasmic OCS, but a relative lesser extent to alpha-granules in both resting and activated platelets; (2) triflavin is internalized in resting platelets independent of cellular activation; and (3) spatial differences between the RGD motif and the C-termini of disintegrins may play an important role in mediating disintegrin binding to alpha(IIb)beta(3) in resting platelets.