基于体检数据的糖尿病智能诊断算法

Intelligent Diagnosis Algorithm of Diabetes Based on Physical Examination Data

目前,医师对疾病的诊断主要依靠对患者的血液分析、超声和CT等相关辅助检查数据,医疗任务繁重。为了减轻医师的工作负担,使其能够更充分地利用患者的各项检查数据,从而对患者的潜在疾病进行相对全面的诊断,减少漏诊,该研究采用随机森林算法和神经网络算法两种智能诊断算法对患者部分辅助检查数据和身体指标进行分析,用于糖尿病的诊断中,首先介绍了两种智能诊断算法在疾病诊断中的工作原理,并针对印第安人糖尿病数据集对算法模型进行了训练,将数据集随机分成训练集和测试集,训练集被用来训练智能诊断算法的分类模型,测试集则被用来测试模型分类的有效性,结果发现,在样本量有限的前提下,基于智能诊断算法的诊断正确率可达85%,且会随着样本量的增加而提高。基于智能诊断算法的糖尿病诊断方法具有一定的通用性,在未来大数据时代,获取患者体检数据和诊断数据相对便捷,通过该方法对疾病进行诊断将为医疗领域带来极大的便利。

Nowadays,doctors'diagnosis of patients'diseases mainly depends on the auxiliary detection data such as blood analysis,ultrasound and CT and their medical tasks are heavy.In order to reduce the workload of doctors and make them make full use of the patient's various detection data to diagnose potential diseases more comprehensively and reduce the rate of missed diagnosis,in this study,two intelligent algorithms,random forest and neural network,were used to analyze parts of auxiliary detection data and body indexes of patients for diabetes diagnosis.At first,the working principle of the two intelligent algorithms in disease diagnosis were introduced,and then the algorithm model were trained based on the Indian diabetes data set.The data set was randomly divided into a training sample set and a testing sample set.The training sample set was used to train the classification model of the algorithm,and the test sample set was used to test the effectiveness of the model classification.It can be seen that in the case of limited sample size,the correct rate of diagnosis based on intelligent algorithm can reach 85%,and it would improve with the increase of sample size.The diabetes diagnosis method based on intelligent algorithm introduced in this study has certain generality.In the era of big data in the future,it is relatively convenient to obtain the physical examination data and diagnosis data of patients.It will bring great convenience to the medical field to diagnose diseases by this method.