Advantages of Applying Artificial Intelligent System to Medical Neurology (Preprint)
BACKGROUND Cerebral stroke is a common cardiovascular disease in neurology. The current imaging detection method and psychological nerve scoring method are characterized by low sensitivity and high subjectivity. Machine learning in artificial intelligence system has high accuracy in the diagnosis and treatment of diseases and is applied in the field of neurology. At present, there are few researches on machine learning and stroke diagnosis. OBJECTIVE The study aimed to explore the predictive value of artificial intelligence system in stroke disease, and to provide reference for the application of artificial intelligence system in the field of medical neurology. METHODS A retrospective analysis was performed on 763 patients with stroke confirmed by the neurology department of XXX Hospital from January 2014 to December 2019 (183 of whom had recurrent stroke). Basic data and data of all subjects were collected. Univariate and multivariate Cox and Logistic regression model algorithm were respectively used to predict stroke risk factors. Receiver Operating Characteristic (ROC) curve was used to detect the accuracy and sensitivity of Cox and Logistic models. According to the Support Vector Machines (SVM) algorithm in machine learning, data were filled and preprocessed by means of mean value method, median method, linear regression method and normalized Expected Maximum (EM). The influencing factors were selected by conservative mean method, and the risk factors for stroke recurrence were predicted by SVM model. Area under the Curve (AUC) of ROC curve was used to analyze and compare the prediction results of the three models. RESULTS Multivariate Cox model and Logistic model analysis showed that family history of stroke, systolic blood pressure, history of heart disease, total cholesterol, disease progression, dietary habits and history of hypertension were the main risk factors for stroke recurrence. The sensitivity and specificity of Cox model were 0.754 and 0.805 respectively. The AUC of Logistic model was 0.889. In the SVM model data filling algorithm, the median AUC was 0.874, which was significantly higher than other algorithms (P<0.05). The top 10 risk factors of stroke patients predicted by SVM model included both clinically established risk factors and some potential risk factors. The prediction results of stroke risk factors showed 0.873SVM>0.861Logistic>0.853Cox. CONCLUSIONS Artificial intelligence system has obvious advantages in the prediction of stroke disease, which provides reference for the application of artificial intelligence system in the field of medical neurology. CLINICALTRIAL