RESUMEN
Objective: The appropriate use of statins plays a vital role in reducing the risk of atherosclerotic cardiovascular disease (ASCVD). However, due to changes in diet and lifestyle, there has been a significant increase in the number of individuals with high cholesterol levels. Therefore, it is crucial to ensure the rational use of statins. Adverse reactions associated with statins, including liver enzyme abnormalities and statin-associated muscle symptoms (SAMS), have impacted their widespread utilization. In this study, we aimed to develop a predictive model for statin efficacy and safety based on real-world clinical data using machine learning techniques. Methods: We employed various data preprocessing techniques, such as improved random forest imputation and Borderline SMOTE oversampling, to handle the dataset. Boruta method was utilized for feature selection, and the dataset was divided into training and testing sets in a 7:3 ratio. Five algorithms, including logistic regression, naive Bayes, decision tree, random forest, and gradient boosting decision tree, were used to construct the predictive models. Ten-fold cross-validation and bootstrapping sampling were performed for internal and external validation. Additionally, SHAP (SHapley Additive exPlanations) was employed for feature interpretability. Ultimately, an accessible web-based platform for predicting statin efficacy and safety was established based on the optimal predictive model. Results: The random forest algorithm exhibited the best performance among the five algorithms. The predictive models for LDL-C target attainment (AUC = 0.883, Accuracy = 0.868, Precision = 0.858, Recall = 0.863, F1 = 0.860, AUPRC = 0.906, MCC = 0.761), liver enzyme abnormalities (AUC = 0.964, Accuracy = 0.964, Precision = 0.967, Recall = 0.963, F1 = 0.965, AUPRC = 0.978, MCC = 0.938), and muscle pain/Creatine kinase (CK) abnormalities (AUC = 0.981, Accuracy = 0.980, Precision = 0.987, Recall = 0.975, F1 = 0.981, AUPRC = 0.987, MCC = 0.965) demonstrated favorable performance. The most important features of LDL-C target attainment prediction model was cerebral infarction, TG, PLT and HDL. The most important features of liver enzyme abnormalities model was CRP, CK and number of oral medications. Similarly, AST, ALT, PLT and number of oral medications were found to be important features for muscle pain/CK abnormalities. Based on the best-performing predictive model, a user-friendly web application was designed and implemented. Conclusion: This study presented a machine learning-based predictive model for statin efficacy and safety. The platform developed can assist in guiding statin therapy decisions and optimizing treatment strategies. Further research and application of the model are warranted to improve the utilization of statin therapy.
RESUMEN
Background: "Pneumonia Prevention No.1" belongs to 'traditional Chinese medicine prescription for prevention of viral pneumonia and influenza' was urgently formulated by Notice on Printing the Novel Coronavirus Diagnosis and Treatment Scheme for COVID-19 (Trial Version 3) and Traditional Chinese Medicine Prevention and Treatment Scheme for COVID-19 in Hubei Province (Trial). Because the prescription drug has the bidirectional regulation function of human immune function, moderate improvement of immune function can effectively resist virus invasion, while excessive immune function will produce immune overresponse. Excessive immune response will aggravate the condition of patients with COVID-19, resulting in the death of severe patients. Methods: Twenty medical workers aged 20-60 years old, who had no immune disease, no current disease and healthy physical examination, were selected as participants. The participants took Hubei "Pneumonia Prevention No.1" decoction, one dosage each day, twice a day, for 7 consecutive days. With the before-after control method, blood samples were collected from the median cubital veins before and after medication. Immunoglobulin IgA, IgG and IgM were measured by immunoturbidimetry, and T lymphocyte subsets CD3, CD4, CD8 and CD4/CD8 were measured by flow cytometry. The changes of indexes before and after medication were compared with SPPS 13.0 statistical software. The data were expressed by (mean ± standard deviation). T-test was adopted, and P < 0.05 was considered statistically significant (P < 0.05). Results: The results of this study show that in healthy participants, the immunoglobulin and T lymphocyte subsets did not differ significantly before and after drug administration (P > 0.05). Conclusion: Under normal drug administration circumstances, "Pneumonia Prevention No. 1" had no significant regulating effect on the immune system in a healthy population and did not increase the immune system capacity beyond a reasonable range. It is safe to be used as a prophylactic measure in healthy populations.
RESUMEN
OBJECTIVE: To establish fingerprints for Poecilobdella manillensis from Guangxi province using the high performance capillary electrophoresis (HPCE) method. METHOD: Electrophoresis was performed on a fused silica capillary column (75 microm x 56 cm), with 25 mmol x L(-1) Na2HPO4-120 mmol x L(-1) Tris-16 mmol x L(-1) SDS (adjusted to pH 12.0 with 1 mol x L(-1) NaOH ) as the running buffer. The applied voltage was 17 kV, the temperature was 25 degrees C and the detection wavelength was 254 nm. The sample's hydrodynamic injection was 3.4 kPa x 6s and the duration was 27 min. RESULT: HPCE fingerprint was established with 13 common peaks. The similarity between fingerprints of P. manillensis in 10 batches and control fingerprints was more than 0.98. CONCLUSION: The method is so precise, reproducible and stable that it could be used as a new means for the quality control of P. manillensis.