摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报告的主题。根据NewsRx记者在太原的新闻报道，研究表明：“阻塞性睡眠呼吸暂停低通气综合征(OSAHS)是一种常见的全身多发或肝损害疾病，我们的目的是利用机器学习(ML)建立独立的多导睡眠图(PSG)模型，分析危险因素并预测SAHS。”新闻记者引用山西医科大学第一医院的研究，“回顾性收集2018-07/2023年7月山西医科大学第一附属医院健康管理中心2064例鼾症患者的临床资料。”将24个特征变量按7:3的比例随机分为训练组和验证组,通过分析这些特征的重要性,得出LDL-C、Cr、颈总动脉斑块、A1c和BMI是OSAHS发病的主要因素。进一步建立随机森林模型和MLP模型，通过交叉验证调整模型超参数确定最终的预测模型，比较了模型的准确度、精度、召回率、F1分和AUC指标，得出MLP模型的准确度为85.80%，精度为0.89，Reca LL为0.75，F1分为0.82，是最优模型。用ML法建立了OSAHS模型的风险预测模型，证明MLP模型在5种ML模型中表现最好。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Taiyuan, Peopl e's Republic of China, by NewsRx journalists, research stated, "Obstructive slee p apnea hypopnea syndrome (OSAHS) is a common disease that can cause multiple or gan damage in the whole body. Our aim was to use machine learning (ML) to build an independent polysomnography (PSG) model to analyze risk factors and predict O SAHS." The news reporters obtained a quote from the research from the First Hospital of Shanxi Medical University, "Clinical data of 2064 snoring patients who underwen t physical examination in the Health Management Center of the First Affiliated H ospital of Shanxi Medical University from July 2018 to July 2023 were retrospect ively collected, involving 24 characteristic variables. Then they were randomly divided into training group and verification group according to the ratio of 7:3 . By analyzing the importance of these features, it was concluded that LDL-C, Cr , common carotid artery plaque, A1c and BMI made major contributions to OSAHS. M oreover, five kinds of machine learning algorithm models such as logistic regres sion, support vector machine, Boosting, Random Forest and MLP were further estab lished, and cross validation was used to adjust the model hyperparameters to det ermine the final prediction model. We compared the accuracy, Precision, Recall r ate, F1-score and AUC indexes of the model, and finally obtained that MLP was th e optimal model with an accuracy of 85.80%, Precision of 0.89, Reca ll of 0.75, F1-score of 0.82, and AUC of 0.938. We established the risk predicti on model of OSAHS using ML method, and proved that the MLP model performed best among the five ML models."
NETL
NSTL