{"title":"基于ehr的肾癌风险预测。","authors":"Kyung Hee Lee, Farrokh Alemi, Xia Wang","doi":"10.1097/QMH.0000000000000526","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and objectives: </strong>The U.S. Preventive Services Task Force (USPSTF) does not currently recommend routine screening for kidney cancer, even though approximately 14 390 people are expected to die from this disease in the United States in 2024. Individualized risk-based kidney cancer screening offers the potential to effectively detect cancer at an early stage and avoid unnecessarily screening the rest of the population who are at low risk. This study proposes electronic health records (EHR) risk evaluation for kidney cancer by examining a comprehensive set of medical history including diagnoses, comorbidities, viruses, and rare diseases.</p><p><strong>Methods: </strong>The relevant medical history for predicting kidney cancer occurrence was identified from the analysis of All of Us data in three steps. First, a Systematized Nomenclature of Medicine (SNOMED) code binary indicator variable in EHR was set for the presence of kidney cancer. Second, the relationship between this binary indicator of cancer and all prior health conditions was examined using the Strong Rule for Feature Elimination and Least Absolute Shrinkage and Selection Operator logistic regression methods of variable selection. Third, the accuracy of the model was reported using cross-validated McFadden's R2 and Area under the Receiver Operating Characteristic curve (AROC) values.</p><p><strong>Results: </strong>The analysis identified 133 out of an initial set of 25 683 clinical diagnoses (represented by SNOMED codes) that were predictive of kidney cancer. The model achieved a cross-validated McFadden's R2 of 0.195 and an AROC of 0.799. Most of the identified codes are consistent with the known risk factors for kidney cancer.</p><p><strong>Conclusions: </strong>It is possible to accurately predict the risk of kidney cancer from medical history using this method. Additional studies to establish high-dimensional predictive risk factors are needed to see if EHR personalized risk prediction can lead to cost-effective cancer screening and eventually better clinical outcomes.</p>","PeriodicalId":20986,"journal":{"name":"Quality Management in Health Care","volume":" ","pages":"186-192"},"PeriodicalIF":1.2000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EHR-Based Risk Prediction for Kidney Cancer.\",\"authors\":\"Kyung Hee Lee, Farrokh Alemi, Xia Wang\",\"doi\":\"10.1097/QMH.0000000000000526\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background and objectives: </strong>The U.S. Preventive Services Task Force (USPSTF) does not currently recommend routine screening for kidney cancer, even though approximately 14 390 people are expected to die from this disease in the United States in 2024. Individualized risk-based kidney cancer screening offers the potential to effectively detect cancer at an early stage and avoid unnecessarily screening the rest of the population who are at low risk. This study proposes electronic health records (EHR) risk evaluation for kidney cancer by examining a comprehensive set of medical history including diagnoses, comorbidities, viruses, and rare diseases.</p><p><strong>Methods: </strong>The relevant medical history for predicting kidney cancer occurrence was identified from the analysis of All of Us data in three steps. First, a Systematized Nomenclature of Medicine (SNOMED) code binary indicator variable in EHR was set for the presence of kidney cancer. Second, the relationship between this binary indicator of cancer and all prior health conditions was examined using the Strong Rule for Feature Elimination and Least Absolute Shrinkage and Selection Operator logistic regression methods of variable selection. Third, the accuracy of the model was reported using cross-validated McFadden's R2 and Area under the Receiver Operating Characteristic curve (AROC) values.</p><p><strong>Results: </strong>The analysis identified 133 out of an initial set of 25 683 clinical diagnoses (represented by SNOMED codes) that were predictive of kidney cancer. The model achieved a cross-validated McFadden's R2 of 0.195 and an AROC of 0.799. Most of the identified codes are consistent with the known risk factors for kidney cancer.</p><p><strong>Conclusions: </strong>It is possible to accurately predict the risk of kidney cancer from medical history using this method. Additional studies to establish high-dimensional predictive risk factors are needed to see if EHR personalized risk prediction can lead to cost-effective cancer screening and eventually better clinical outcomes.</p>\",\"PeriodicalId\":20986,\"journal\":{\"name\":\"Quality Management in Health Care\",\"volume\":\" \",\"pages\":\"186-192\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2025-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Quality Management in Health Care\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/QMH.0000000000000526\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/3/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q4\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quality Management in Health Care","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/QMH.0000000000000526","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/21 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0
摘要
背景和目的：美国预防服务工作组（USPSTF）目前不建议对肾癌进行常规筛查，尽管预计到2024年美国将有大约14390人死于肾癌。个体化的基于风险的肾癌筛查提供了在早期有效发现癌症的潜力，并避免了对其他低风险人群进行不必要的筛查。本研究通过检查包括诊断、合并症、病毒和罕见疾病在内的一套全面的病史，提出了肾癌电子健康记录（EHR）风险评估。方法：通过对All of Us数据的分析，分三步确定预测肾癌发生的相关病史。首先，在EHR中设置了一个系统化医学命名法（SNOMED）代码二进制指标变量，用于肾癌的存在。其次，使用特征消除强规则、最小绝对收缩和变量选择算子逻辑回归方法检验了癌症二元指标与所有既往健康状况之间的关系。第三，采用交叉验证的麦克法登R2和受试者工作特征曲线下面积（Area under the Receiver Operating Characteristic curve， AROC）值报告模型的准确性。结果：该分析从最初的25683例临床诊断（由SNOMED代码表示）中确定了133例可预测肾癌。交叉验证的McFadden’s R2为0.195，AROC为0.799。大多数已识别的代码与已知的肾癌危险因素一致。结论：该方法可从病史中准确预测肾癌的发生风险。需要进一步的研究来建立高维预测风险因素，以确定电子病历个性化风险预测是否能够带来具有成本效益的癌症筛查，并最终获得更好的临床结果。
Background and objectives: The U.S. Preventive Services Task Force (USPSTF) does not currently recommend routine screening for kidney cancer, even though approximately 14 390 people are expected to die from this disease in the United States in 2024. Individualized risk-based kidney cancer screening offers the potential to effectively detect cancer at an early stage and avoid unnecessarily screening the rest of the population who are at low risk. This study proposes electronic health records (EHR) risk evaluation for kidney cancer by examining a comprehensive set of medical history including diagnoses, comorbidities, viruses, and rare diseases.
Methods: The relevant medical history for predicting kidney cancer occurrence was identified from the analysis of All of Us data in three steps. First, a Systematized Nomenclature of Medicine (SNOMED) code binary indicator variable in EHR was set for the presence of kidney cancer. Second, the relationship between this binary indicator of cancer and all prior health conditions was examined using the Strong Rule for Feature Elimination and Least Absolute Shrinkage and Selection Operator logistic regression methods of variable selection. Third, the accuracy of the model was reported using cross-validated McFadden's R2 and Area under the Receiver Operating Characteristic curve (AROC) values.
Results: The analysis identified 133 out of an initial set of 25 683 clinical diagnoses (represented by SNOMED codes) that were predictive of kidney cancer. The model achieved a cross-validated McFadden's R2 of 0.195 and an AROC of 0.799. Most of the identified codes are consistent with the known risk factors for kidney cancer.
Conclusions: It is possible to accurately predict the risk of kidney cancer from medical history using this method. Additional studies to establish high-dimensional predictive risk factors are needed to see if EHR personalized risk prediction can lead to cost-effective cancer screening and eventually better clinical outcomes.
期刊介绍：
Quality Management in Health Care (QMHC) is a peer-reviewed journal that provides a forum for our readers to explore the theoretical, technical, and strategic elements of health care quality management. The journal''s primary focus is on organizational structure and processes as these affect the quality of care and patient outcomes. In particular, it:
-Builds knowledge about the application of statistical tools, control charts, benchmarking, and other devices used in the ongoing monitoring and evaluation of care and of patient outcomes;
-Encourages research in and evaluation of the results of various organizational strategies designed to bring about quantifiable improvements in patient outcomes;
-Fosters the application of quality management science to patient care processes and clinical decision-making;
-Fosters cooperation and communication among health care providers, payers and regulators in their efforts to improve the quality of patient outcomes;
-Explores links among the various clinical, technical, administrative, and managerial disciplines involved in patient care, as well as the role and responsibilities of organizational governance in ongoing quality management.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
