{"title":"基于机器学习的急性脑梗塞患者风险因素预测模型的开发:一项临床回顾性研究。","authors":"Changqing Yang, Renlin Hu, Shilan Xiong, Zhou Hong, Jiaqi Liu, Zhuqing Mao, Mingzhu Chen","doi":"10.1186/s12883-024-03818-6","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>The aim of this study was to develop machine learning-based models for predicting acute cerebral infarction (ACI) in patients.</p><p><strong>Methods: </strong>We extracted the data of ACI patients and non-ACI patients (as control) from two hospitals. The Lasso algorithm was employed to select the most crucial features associated with ACI. Five machine learning algorithms-based models were trained, which was performed with 10-fold cross-validation. Then, the area under the receiver operating characteristic curve (AUC), accuracy, and F1-score were calculated in the training models. Accordingly, the training models with excellent performance was selected as the final predictive model. The relative importance of variables was analyzed and ranked.</p><p><strong>Results: </strong>A total of 150 patients were diagnosed with ACI (50.00%), with a higher proportion of males (70.67% vs. 44.00%) compared to the non-ACI patients. The logistic regression model exhibited a good performance in predicting ACI in the training set, as evidenced by its highest AUC, accuracy, sensitivity, and F1-score. Furthermore, feature importance analysis showed that blood glucose, gender, smoking history, serum homocysteine, folic acid, and C-reactive protein were the top six crucial variables of the logistic regression.</p><p><strong>Conclusions: </strong>In our work, the ACI risk prediction model developed by the logistic regression exhibited excellent performance. This could contribute to the identification of risk variables for ACI patients and enables clinicians timely and effective interventions.</p>","PeriodicalId":9170,"journal":{"name":"BMC Neurology","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11365171/pdf/","citationCount":"0","resultStr":"{\"title\":\"Development of machine learning-based models for predicting risk factors in acute cerebral infarction patients: a clinical retrospective study.\",\"authors\":\"Changqing Yang, Renlin Hu, Shilan Xiong, Zhou Hong, Jiaqi Liu, Zhuqing Mao, Mingzhu Chen\",\"doi\":\"10.1186/s12883-024-03818-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>The aim of this study was to develop machine learning-based models for predicting acute cerebral infarction (ACI) in patients.</p><p><strong>Methods: </strong>We extracted the data of ACI patients and non-ACI patients (as control) from two hospitals. The Lasso algorithm was employed to select the most crucial features associated with ACI. Five machine learning algorithms-based models were trained, which was performed with 10-fold cross-validation. Then, the area under the receiver operating characteristic curve (AUC), accuracy, and F1-score were calculated in the training models. Accordingly, the training models with excellent performance was selected as the final predictive model. The relative importance of variables was analyzed and ranked.</p><p><strong>Results: </strong>A total of 150 patients were diagnosed with ACI (50.00%), with a higher proportion of males (70.67% vs. 44.00%) compared to the non-ACI patients. The logistic regression model exhibited a good performance in predicting ACI in the training set, as evidenced by its highest AUC, accuracy, sensitivity, and F1-score. Furthermore, feature importance analysis showed that blood glucose, gender, smoking history, serum homocysteine, folic acid, and C-reactive protein were the top six crucial variables of the logistic regression.</p><p><strong>Conclusions: </strong>In our work, the ACI risk prediction model developed by the logistic regression exhibited excellent performance. This could contribute to the identification of risk variables for ACI patients and enables clinicians timely and effective interventions.</p>\",\"PeriodicalId\":9170,\"journal\":{\"name\":\"BMC Neurology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-08-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11365171/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Neurology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12883-024-03818-6\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Neurology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12883-024-03818-6","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
摘要
研究目的本研究旨在开发基于机器学习的急性脑梗塞(ACI)患者预测模型:我们从两家医院提取了急性脑梗塞患者和非急性脑梗塞患者(作为对照)的数据。采用 Lasso 算法选择与 ACI 相关的最关键特征。训练了五个基于机器学习算法的模型,并进行了 10 倍交叉验证。然后,计算了训练模型的接收者操作特征曲线下面积(AUC)、准确率和 F1 分数。因此,性能优异的训练模型被选为最终预测模型。对变量的相对重要性进行了分析和排序:共有 150 名患者被诊断为 ACI(50.00%),与非 ACI 患者相比,男性比例更高(70.67% 对 44.00%)。逻辑回归模型的 AUC 值、准确率、灵敏度和 F1 分数均为最高,表明该模型在预测训练集中的 ACI 方面表现良好。此外,特征重要性分析表明,血糖、性别、吸烟史、血清同型半胱氨酸、叶酸和 C 反应蛋白是逻辑回归的前六个关键变量:在我们的研究中,通过逻辑回归建立的 ACI 风险预测模型表现优异。结论:在我们的研究中,通过逻辑回归建立的 ACI 风险预测模型表现出了卓越的性能,这有助于识别 ACI 患者的风险变量,使临床医生能够及时采取有效的干预措施。
Development of machine learning-based models for predicting risk factors in acute cerebral infarction patients: a clinical retrospective study.
Objectives: The aim of this study was to develop machine learning-based models for predicting acute cerebral infarction (ACI) in patients.
Methods: We extracted the data of ACI patients and non-ACI patients (as control) from two hospitals. The Lasso algorithm was employed to select the most crucial features associated with ACI. Five machine learning algorithms-based models were trained, which was performed with 10-fold cross-validation. Then, the area under the receiver operating characteristic curve (AUC), accuracy, and F1-score were calculated in the training models. Accordingly, the training models with excellent performance was selected as the final predictive model. The relative importance of variables was analyzed and ranked.
Results: A total of 150 patients were diagnosed with ACI (50.00%), with a higher proportion of males (70.67% vs. 44.00%) compared to the non-ACI patients. The logistic regression model exhibited a good performance in predicting ACI in the training set, as evidenced by its highest AUC, accuracy, sensitivity, and F1-score. Furthermore, feature importance analysis showed that blood glucose, gender, smoking history, serum homocysteine, folic acid, and C-reactive protein were the top six crucial variables of the logistic regression.
Conclusions: In our work, the ACI risk prediction model developed by the logistic regression exhibited excellent performance. This could contribute to the identification of risk variables for ACI patients and enables clinicians timely and effective interventions.
期刊介绍:
BMC Neurology is an open access, peer-reviewed journal that considers articles on all aspects of the prevention, diagnosis and management of neurological disorders, as well as related molecular genetics, pathophysiology, and epidemiology.