Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data.
Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data.
复制标题
具有保留的射血分数（HFPEF）的心力衰竭的诊断签名：使用多模式电子健康记录数据的机器学习方法。
DOI：
10.1186/s12872-022-03005-w
复制
发表时间：
2022-12-26
影响因子：
2.1
通讯作者：
中科院分区：
文献类型：
--
作者：
射血分数保留的心力衰竭（HFpEF）被认为非常普遍，但仍未得到充分诊断。基于证据的治疗可以提高生活质量并减少住院治疗。我们试图开发一种数据驱动的诊断模型，以根据电子健康记录 (EHR) 预测不明原因呼吸困难且左心室 EF 保留的患者发生 HFpEF 的可能性。衍生队列由呼吸困难和超声心动图结果的患者组成。使用自动化信息学管道提取结构化和非结构化数据。患者被回顾性诊断为 HFpEF（病例）、非 HF（对照队列 I）或 EF 降低的 HF（HFrEF；对照队列 II）。通过极端梯度提升来评估临床参数和研究区分病例与对照的能力。可能性评分系统是在单独的测试队列中开发和验证的。衍生队列包括 1585 名连续患者：133 例 HFpEF (9%)、194 例非 HF 病例（对照队列 I）和 1258 例 HFrEF 病例（对照队列 II）。得出了两个 HFpEF 诊断特征，包括症状、诊断和调查结果。最终的预测模型是根据这两个模型的平均似然得分生成的。在由 269 名连续患者组成的验证队列中 [66 例 HFpEF 病例 (24.5%)]，检测 HFpEF 的诊断能力 AUROC 为 90% (P<0.001)，平均精度为 74%。该诊断特征能够区分 HFpEF 与非心源性呼吸困难或 HFrEF 与 EHR，并有助于对不明原因呼吸困难患者进行诊断评估。这种方法将能够识别 HFpEF 患者，然后他们可能会受益于新的循证疗法。在线版本包含可在 10.1186/s12872-022-03005-w 获取的补充材料。
Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. Evidence-based treatments are available that increase quality of life and decrease hospitalization. We sought to develop a data-driven diagnostic model to predict from electronic health records (EHR) the likelihood of HFpEF among patients with unexplained dyspnea and preserved left ventricular EF. The derivation cohort comprised patients with dyspnea and echocardiography results. Structured and unstructured data were extracted using an automated informatics pipeline. Patients were retrospectively diagnosed as HFpEF (cases), non-HF (control cohort I), or HF with reduced EF (HFrEF; control cohort II). The ability of clinical parameters and investigations to discriminate cases from controls was evaluated by extreme gradient boosting. A likelihood scoring system was developed and validated in a separate test cohort. The derivation cohort included 1585 consecutive patients: 133 cases of HFpEF (9%), 194 non-HF cases (Control cohort I) and 1258 HFrEF cases (Control cohort II). Two HFpEF diagnostic signatures were derived, comprising symptoms, diagnoses and investigation results. A final prediction model was generated based on the averaged likelihood scores from these two models. In a validation cohort consisting of 269 consecutive patients [with 66 HFpEF cases (24.5%)], the diagnostic power of detecting HFpEF had an AUROC of 90% (P < 0.001) and average precision of 74%. This diagnostic signature enables discrimination of HFpEF from non-cardiac dyspnea or HFrEF from EHR and can assist in the diagnostic evaluation in patients with unexplained dyspnea. This approach will enable identification of HFpEF patients who may then benefit from new evidence-based therapies. The online version contains supplementary material available at 10.1186/s12872-022-03005-w.
登录
查看更多内容
DOI：
10.1007/s00392-018-1245-z
发表时间：
2018-09
期刊：
Clinical research in cardiology : official journal of the German Cardiac Society
影响因子：
--
作者：
Kaspar M;Fette G;Güder G;Seidlmayer L;Ertl M;Dietrich G;Greger H;Puppe F;Störk S
通讯作者：
Störk S
影响因子：
37.8
作者：
Shah SJ;Kitzman DW;Borlaug BA;van Heerebeek L;Zile MR;Kass DA;Paulus WJ
通讯作者：
Paulus WJ
影响因子：
158.5
作者：
Solomon, S. D.;McMurray, J. J. V.;Lefkowitz, M. P.
通讯作者：
Lefkowitz, M. P.
影响因子：
3.8
作者：
Huusko J;Tuominen S;Studer R;Corda S;Proudfoot C;Lassenius M;Ukkonen H
通讯作者：
Ukkonen H
影响因子：
3.8
作者：
Huusko, Jenni;Purmonen, Timo;Ukkonen, Heikki
通讯作者：
Ukkonen, Heikki