用于预测心房颤动和癌症患者 1 年缺血性中风和出血事件的机器学习算法的开发和验证。

IF 3.4 3区 医学 Q2 CARDIAC & CARDIOVASCULAR SYSTEMS Cardiovascular Toxicology Pub Date : 2024-04-01 Epub Date: 2024-03-18 DOI:10.1007/s12012-024-09843-8
Bang Truong, Jingyi Zheng, Lori Hornsby, Brent Fox, Chiahung Chou, Jingjing Qian
{"title":"用于预测心房颤动和癌症患者 1 年缺血性中风和出血事件的机器学习算法的开发和验证。","authors":"Bang Truong, Jingyi Zheng, Lori Hornsby, Brent Fox, Chiahung Chou, Jingjing Qian","doi":"10.1007/s12012-024-09843-8","DOIUrl":null,"url":null,"abstract":"<p><p>In this study, we leveraged machine learning (ML) approach to develop and validate new assessment tools for predicting stroke and bleeding among patients with atrial fibrillation (AFib) and cancer. We conducted a retrospective cohort study including patients who were newly diagnosed with AFib with a record of cancer from the 2012-2018 Surveillance, Epidemiology, and End Results (SEER)-Medicare database. The ML algorithms were developed and validated separately for each outcome by fitting elastic net, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and neural network models with tenfold cross-validation (train:test = 7:3). We obtained area under the curve (AUC), sensitivity, specificity, and F2 score as performance metrics. Model calibration was assessed using Brier score. In sensitivity analysis, we resampled data using Synthetic Minority Oversampling Technique (SMOTE). Among 18,388 patients with AFib and cancer, 523 (2.84%) had ischemic stroke and 221 (1.20%) had major bleeding within one year after AFib diagnosis. In prediction of ischemic stroke, RF significantly outperformed other ML models [AUC (0.916, 95% CI 0.887-0.945), sensitivity 0.868, specificity 0.801, F2 score 0.375, Brier score = 0.035]. However, the performance of ML algorithms in prediction of major bleeding was low with highest AUC achieved by RF (0.623, 95% CI 0.554-0.692). RF models performed better than CHA<sub>2</sub>DS<sub>2</sub>-VASc and HAS-BLED scores. SMOTE did not improve the performance of the ML algorithms. Our study demonstrated a promising application of ML in stroke prediction among patients with AFib and cancer. This tool may be leveraged in assisting clinicians to identify patients at high risk of stroke and optimize treatment decisions.</p>","PeriodicalId":9570,"journal":{"name":"Cardiovascular Toxicology","volume":" ","pages":"365-374"},"PeriodicalIF":3.4000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10998799/pdf/","citationCount":"0","resultStr":"{\"title\":\"Development and Validation of Machine Learning Algorithms to Predict 1-Year Ischemic Stroke and Bleeding Events in Patients with Atrial Fibrillation and Cancer.\",\"authors\":\"Bang Truong, Jingyi Zheng, Lori Hornsby, Brent Fox, Chiahung Chou, Jingjing Qian\",\"doi\":\"10.1007/s12012-024-09843-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In this study, we leveraged machine learning (ML) approach to develop and validate new assessment tools for predicting stroke and bleeding among patients with atrial fibrillation (AFib) and cancer. We conducted a retrospective cohort study including patients who were newly diagnosed with AFib with a record of cancer from the 2012-2018 Surveillance, Epidemiology, and End Results (SEER)-Medicare database. The ML algorithms were developed and validated separately for each outcome by fitting elastic net, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and neural network models with tenfold cross-validation (train:test = 7:3). We obtained area under the curve (AUC), sensitivity, specificity, and F2 score as performance metrics. Model calibration was assessed using Brier score. In sensitivity analysis, we resampled data using Synthetic Minority Oversampling Technique (SMOTE). Among 18,388 patients with AFib and cancer, 523 (2.84%) had ischemic stroke and 221 (1.20%) had major bleeding within one year after AFib diagnosis. In prediction of ischemic stroke, RF significantly outperformed other ML models [AUC (0.916, 95% CI 0.887-0.945), sensitivity 0.868, specificity 0.801, F2 score 0.375, Brier score = 0.035]. However, the performance of ML algorithms in prediction of major bleeding was low with highest AUC achieved by RF (0.623, 95% CI 0.554-0.692). RF models performed better than CHA<sub>2</sub>DS<sub>2</sub>-VASc and HAS-BLED scores. SMOTE did not improve the performance of the ML algorithms. Our study demonstrated a promising application of ML in stroke prediction among patients with AFib and cancer. This tool may be leveraged in assisting clinicians to identify patients at high risk of stroke and optimize treatment decisions.</p>\",\"PeriodicalId\":9570,\"journal\":{\"name\":\"Cardiovascular Toxicology\",\"volume\":\" \",\"pages\":\"365-374\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10998799/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cardiovascular Toxicology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s12012-024-09843-8\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/3/18 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cardiovascular Toxicology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12012-024-09843-8","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/18 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

在本研究中,我们利用机器学习(ML)方法开发并验证了预测心房颤动(AFib)合并癌症患者中风和出血的新评估工具。我们进行了一项回顾性队列研究,研究对象包括 2012-2018 年监测、流行病学和最终结果(SEER)--医疗保险数据库中新诊断为心房颤动并有癌症记录的患者。通过拟合弹性网(elastic net)、随机森林(RF)、极梯度提升(XGBoost)、支持向量机(SVM)和神经网络模型并进行十倍交叉验证(train:test = 7:3),针对每种结果分别开发并验证了多重L算法。我们获得了曲线下面积(AUC)、灵敏度、特异性和 F2 分数作为性能指标。模型校准采用 Brier 评分进行评估。在敏感性分析中,我们使用合成少数群体过度取样技术(SMOTE)对数据进行了重新取样。在 18,388 名心房颤动和癌症患者中,有 523 人(2.84%)在确诊心房颤动后一年内发生缺血性中风,221 人(1.20%)发生大出血。在预测缺血性卒中方面,RF 明显优于其他 ML 模型[AUC(0.916,95% CI 0.887-0.945),灵敏度 0.868,特异性 0.801,F2 得分 0.375,Brier 得分 = 0.035]。然而,ML 算法在预测大出血方面的性能较低,其中 RF 的 AUC 最高(0.623,95% CI 0.554-0.692)。RF 模型的表现优于 CHA2DS2-VASc 和 HAS-BLED 评分。SMOTE 没有提高 ML 算法的性能。我们的研究表明,ML 在心房颤动和癌症患者卒中预测中的应用前景广阔。该工具可用于协助临床医生识别中风高危患者并优化治疗决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Development and Validation of Machine Learning Algorithms to Predict 1-Year Ischemic Stroke and Bleeding Events in Patients with Atrial Fibrillation and Cancer.

In this study, we leveraged machine learning (ML) approach to develop and validate new assessment tools for predicting stroke and bleeding among patients with atrial fibrillation (AFib) and cancer. We conducted a retrospective cohort study including patients who were newly diagnosed with AFib with a record of cancer from the 2012-2018 Surveillance, Epidemiology, and End Results (SEER)-Medicare database. The ML algorithms were developed and validated separately for each outcome by fitting elastic net, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and neural network models with tenfold cross-validation (train:test = 7:3). We obtained area under the curve (AUC), sensitivity, specificity, and F2 score as performance metrics. Model calibration was assessed using Brier score. In sensitivity analysis, we resampled data using Synthetic Minority Oversampling Technique (SMOTE). Among 18,388 patients with AFib and cancer, 523 (2.84%) had ischemic stroke and 221 (1.20%) had major bleeding within one year after AFib diagnosis. In prediction of ischemic stroke, RF significantly outperformed other ML models [AUC (0.916, 95% CI 0.887-0.945), sensitivity 0.868, specificity 0.801, F2 score 0.375, Brier score = 0.035]. However, the performance of ML algorithms in prediction of major bleeding was low with highest AUC achieved by RF (0.623, 95% CI 0.554-0.692). RF models performed better than CHA2DS2-VASc and HAS-BLED scores. SMOTE did not improve the performance of the ML algorithms. Our study demonstrated a promising application of ML in stroke prediction among patients with AFib and cancer. This tool may be leveraged in assisting clinicians to identify patients at high risk of stroke and optimize treatment decisions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Cardiovascular Toxicology
Cardiovascular Toxicology 医学-毒理学
CiteScore
6.60
自引率
3.10%
发文量
61
审稿时长
>12 weeks
期刊介绍: Cardiovascular Toxicology is the only journal dedicated to publishing contemporary issues, timely reviews, and experimental and clinical data on toxicological aspects of cardiovascular disease. CT publishes papers that will elucidate the effects, molecular mechanisms, and signaling pathways of environmental toxicants on the cardiovascular system. Also covered are the detrimental effects of new cardiovascular drugs, and cardiovascular effects of non-cardiovascular drugs, anti-cancer chemotherapy, and gene therapy. In addition, Cardiovascular Toxicology reports safety and toxicological data on new cardiovascular and non-cardiovascular drugs.
期刊最新文献
Correction: Novel Insights into Causal Effects of Serum Lipids and Apolipoproteins on Cardiovascular Morpho-Functional Phenotypes. Unveiling the Mechanism of Protective Effects of Tanshinone as a New Fighter Against Cardiovascular Diseases: A Systematic Review. Protective Effect of Berberine Nanoparticles Against Cardiotoxic Effects of Arsenic Trioxide. Fasting: A Complex, Double-Edged Blade in the Battle Against Doxorubicin-Induced Cardiotoxicity. Advances in Factors Affecting ALDH2 Activity and its Mechanisms.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1