Assessment of EMR ML Mining Methods for Measuring Association between Metal Mixture and Mortality for Hypertension.

IF 3.1 Q2 PERIPHERAL VASCULAR DISEASE

High Blood Pressure & Cardiovascular Prevention Pub Date : 2024-09-01 Epub Date: 2024-08-12 DOI:10.1007/s40292-024-00666-w

Site Xu, Mu Sun

{"title":"Assessment of EMR ML Mining Methods for Measuring Association between Metal Mixture and Mortality for Hypertension.","authors":"Site Xu, Mu Sun","doi":"10.1007/s40292-024-00666-w","DOIUrl":null,"url":null,"abstract":"Introduction: There are limited data available regarding the connection between heavy metal exposure and mortality among hypertension patients.Aim: We intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that monitors mortality based on heavy metal exposure among hypertension patients.Methods: Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2018). We developed 5 ML models for mortality prediction among hypertension patients by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, we chose the optimally performing model after parameter adjustment by genetic algorithm (GA) for prediction. Finally, in order to visualize the model's ability to make decisions, we used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 2347 participants in total.Results: A best-performing eXtreme Gradient Boosting (XGB) with GA for mortality prediction among hypertension patients by 13 heavy metals was selected (AUC 0.959; 95% CI 0.953-0.965; accuracy 96.8%). According to sum of SHAP values, cadmium (0.094), cobalt (2.048), lead (1.12), tungsten (0.129) in urine, and lead (2.026), mercury (1.703) in blood positively influenced the model, while barium (- 0.001), molybdenum (- 2.066), antimony (- 0.398), tin (- 0.498), thallium (- 2.297) in urine, and selenium (- 0.842), manganese (- 1.193) in blood negatively influenced the model.Conclusions: Hypertension patients' mortality associated with heavy metal exposure was predicted by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Cadmium, cobalt, lead, tungsten in urine, and mercury in blood are positively correlated with mortality, while barium, molybdenum, antimony, tin, thallium in urine, and lead, selenium, manganese in blood is negatively correlated with mortality.","PeriodicalId":12890,"journal":{"name":"High Blood Pressure & Cardiovascular Prevention","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11485017/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"High Blood Pressure & Cardiovascular Prevention","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s40292-024-00666-w","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/12 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: There are limited data available regarding the connection between heavy metal exposure and mortality among hypertension patients.

Aim: We intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that monitors mortality based on heavy metal exposure among hypertension patients.

Methods: Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2018). We developed 5 ML models for mortality prediction among hypertension patients by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, we chose the optimally performing model after parameter adjustment by genetic algorithm (GA) for prediction. Finally, in order to visualize the model's ability to make decisions, we used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 2347 participants in total.

Results: A best-performing eXtreme Gradient Boosting (XGB) with GA for mortality prediction among hypertension patients by 13 heavy metals was selected (AUC 0.959; 95% CI 0.953-0.965; accuracy 96.8%). According to sum of SHAP values, cadmium (0.094), cobalt (2.048), lead (1.12), tungsten (0.129) in urine, and lead (2.026), mercury (1.703) in blood positively influenced the model, while barium (- 0.001), molybdenum (- 2.066), antimony (- 0.398), tin (- 0.498), thallium (- 2.297) in urine, and selenium (- 0.842), manganese (- 1.193) in blood negatively influenced the model.

Conclusions: Hypertension patients' mortality associated with heavy metal exposure was predicted by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Cadmium, cobalt, lead, tungsten in urine, and mercury in blood are positively correlated with mortality, while barium, molybdenum, antimony, tin, thallium in urine, and lead, selenium, manganese in blood is negatively correlated with mortality.

查看原文本刊更多论文

评估用于测量金属混合物与高血压死亡率之间关联的 EMR ML 挖掘方法。

简介：关于重金属暴露与高血压患者死亡率之间关系的现有数据非常有限：关于重金属暴露与高血压患者死亡率之间关系的可用数据有限。目的：我们打算建立一个可解释的机器学习（ML）模型，该模型具有高效性和鲁棒性，可根据重金属暴露监测高血压患者的死亡率：我们的数据集来自美国国家健康与营养调查（NHANES，2013-2018 年）。我们根据重金属暴露情况建立了 5 个用于预测高血压患者死亡率的 ML 模型，并根据 10 个判别特征对这些模型进行了测试。此外，我们通过遗传算法（GA）调整参数后选择了性能最优的模型进行预测。最后，为了使模型的决策能力可视化，我们使用了SHAPLE Additive exPlanation（SHAP）和Local Interpretable Model-Agnostic Explanations（LIME）算法来说明模型的特征。研究共包括 2347 名参与者：结果：通过 13 种重金属对高血压患者的死亡率进行预测，选出了性能最佳的梯度提升算法（XGB）（AUC 0.959；95% CI 0.953-0.965；准确率 96.8%）。根据 SHAP 值的总和，尿液中的镉（0.094）、钴（2.048）、铅（1.12）、钨（0.129）和血液中的铅（2.026）、汞（1.703）对模型有积极影响，而钡（- 0.001）、尿中的钼（- 2.066）、锑（- 0.398）、锡（- 0.498）、铊（- 2.297）和血液中的硒（- 0.842）、锰（- 1.193）对模型有负面影响：高血压患者的死亡率与重金属暴露有关，可通过一个高效、稳健、可解释的 GA-XGB 模型（含 SHAP 和 LIME）进行预测。尿液中的镉、钴、铅、钨和血液中的汞与死亡率呈正相关，而尿液中的钡、钼、锑、锡、铊和血液中的铅、硒、锰与死亡率呈负相关。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

High Blood Pressure & Cardiovascular Prevention PERIPHERAL VASCULAR DISEASE-

CiteScore

5.70

自引率

3.30%

发文量

期刊介绍： High Blood Pressure & Cardiovascular Prevention promotes knowledge, update and discussion in the field of hypertension and cardiovascular disease prevention, by providing a regular programme of independent review articles covering key aspects of the management of hypertension and cardiovascular diseases. The journal includes: Invited ''State of the Art'' reviews. Expert commentaries on guidelines, major trials, technical advances.Presentation of new intervention trials design.''Pros and Cons'' or round tables on controversial issues.Statements on guidelines from hypertension and cardiovascular scientific societies.Socio-economic issues.Cost/benefit in prevention of cardiovascular diseases.Monitoring of healthcare systems.News and views from the Italian Society of Hypertension (including abstracts).All manuscripts are subject to peer review by international experts. Letters to the editor are welcomed and will be considered for publication.