基于机器学习的出血性脑卒中临床智能诊疗预测模型的建立

Clinical Intelligent Diagnosis and Treatment Model of Hemorrhagic Stroke Based on Machine learning

针对出血性脑卒中起病急、进展快且通常会导致脑组织机械性损伤和一系列复杂的生理病理反应等问题建立了一种基于机器学习的智能诊疗预测模型,使用人工智能技术对大量影像数据进行处理分析,随机抽取数据样本将模型应用于出血性脑卒中的临床诊疗预测中。与传统回归方法相比,机器学习方法在均方误差、平均绝对误差、平均绝对百分比误差上分别有62.08%、65.89%和47.33%的提升,证明机器学习智能诊疗预测模型可提高出血性脑卒中患者的预测准确率。

A machine learning based intelligent diagnosis and treatment model is proposed to address the urgent onset and rapid progression of hemorrhagic stroke,which often leads to mechanical damage to brain tissue and a series of complex physiological and pathological reactions.Firstly,artificial intelligence technology is used to process and analyze a large amount of image data.The model is applied to the clinical diagnosis and treatment of hemorrhagic stroke with randomly selected data.Compared with traditional methods,there are 62.08%,65.89%and 47.33%improvements in mean square error,mean absolute error and mean absolute percentage error,respectively.This model improves the accuracy of the prediction of hemorrhagic stroke patients.