RESUMO
Objective: Neurological outcome prediction in patients with ischemic stroke is very critical in treatment strategy and post-stroke management. Machine learning techniques with high accuracy are increasingly being developed in the medical field. We studied the application of machine learning models to predict long-term neurological outcomes in patients with after intravenous thrombolysis. Methods: A retrospective cohort study was performed to review all stroke patients with intravenous thrombolysis. Patients with modified Rankin Score (mRs) less than two at three months post-thrombolysis were considered as good outcome. The clinical features between stroke patients with good and with poor outcomes were compared using three different machine learning models (Random Forest, Support Vector Machine and Logistic Regression) to identify which performed best. Two datasets from the other stroke center were included accordingly for external verification and performed with explainable AI models. Results: Of the 488 patients enrolled in this study, and 374 (76.6%) patients had favorable outcomes. Patients with higher mRs at 3 months had increased systolic pressure, blood glucose, cholesterol (TC), and 7-day National Institute of Health Stroke Scale (NIHSS) score compared to those with lower mRs. The predictability and the areas under the curves (AUC) for the random forest model was relatively higher than support vector machine and LR models. These findings were further validated in the external dataset and similar results were obtained. The explainable AI model identified the risk factors as well. Conclusion: Explainable AI model is able to identify NIHSS_Day7 is independently efficient in predicting neurological outcomes in patients with ischemic stroke after intravenous thrombolysis.
RESUMO
Objective To study the effects of extracted active components of Chaenomeles Speciosa (EACCS) on non-alcoholic fatty liver disease (NAFLD) in mice; To discuss the possible molecular mechanism. Methods Forty male KM mice were randomized into four groups, namely normal group, model group, low-dose (50 mg/kg) EACCS group and high-dose (100 mg/kg) EACCS group. Except that the normal group was daily given routine diet, the other groups were given high-fat–high-fructose diet (HFFD). The mice were put to death 4 weeks later. Body weight, liver weight and serum TG were measured. HE and oil red O staining were used to observe liver tissue morphology. RT-PCR and Western blot were used to detect the expression of lipid metabolism related genes. Results Compared with the normal group, the liver size, liver index (P<0.01) and epididymal fat index (P<0.05) increased significantly;The ALT and GLU in serum increased (P<0.05), TG increased (P<0.05), and pathological findings showed significant steatosis; RT-PCR and Western blot showed that the expression levels of SIRT1 and FoxO1 mRNA decreased and the level of SERBP-1c increased in the model group. Compared with the model group, the hepatic lipid accumulation of EACCS groups was obviously improved, and the serum ALT, GLU, and TG levels significantly decreased, the expression levels of hepatic SIRT1 and FoxO1 mRNA increased. Conclusion EACCS has protective effects on NAFLD mice induced by HFFD, and its mechanism may be related to the activation of SIRT1-FoxO1 signaling pathway in the liver tissues.
