Fine Nowell M, Kalmady Sunil V, Sun Weijie, Greiner Russ, Howlett Jonathan G, White James A, McAlister Finlay A, Ezekowitz Justin A, Kaul Padma
Division of Cardiology, Department of Cardiac Sciences, Libin Cardiovascular Institute, Cumming School of Medicine, University of Calgary, Calgary Alberta.
Canadian Vigour Center, Katz Group Center for Pharmacy and Health Research, University of Alberta, Edmonton Alberta.
PLOS Digit Health. 2024 Oct 25;3(10):e0000636. doi: 10.1371/journal.pdig.0000636. eCollection 2024 Oct.
Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system.
Patients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively.
ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system.
前往急诊科（ED）就诊或因心力衰竭（HF）住院的患者后续出现不良结局的风险增加，然而有效的风险分层仍然具有挑战性。我们利用基于机器学习（ML）的方法，通过一个大型区域行政医疗数据系统，识别急诊就诊或住院后有不良结局风险的HF患者。
纳入2002年至2016年期间在加拿大艾伯塔省前往急诊科就诊或因HF住院的患者。感兴趣的结局为30天和1年与HF相关的急诊就诊、HF再次住院或全因死亡。我们应用了一种特征提取方法，使用来自多个健康数据源的深度特征合成，并将梯度提升算法（CatBoost）与逻辑回归模型的性能进行比较。受试者工作特征曲线下面积（AUC-ROC）用于评估模型性能。我们纳入了50,630例患者，有93,552次HF急诊就诊/住院。在保留验证队列的30天随访中，Catboost模型和逻辑回归模型对于HF急诊就诊、HF再次住院或死亡这一联合终点的AUC-ROC分别为74.16（73.18 - 75.11）和62.25（61.25 - 63.18）。在1年随访中，相应的值分别为76.80（76.1 - 77.47）和69.52（68.77 - 70.26）。在30天和1年随访时，仅全因死亡终点的CatBoost模型和逻辑回归模型的AUC-ROC值分别为83.21（81.83 - 84.41）和69.53（67.98 - 71.18），以及85.73（85.14 - 86.29）和69.40（68.57 - 70.26）。
使用来自大型区域行政医疗系统的数据，基于ML的深度特征合成建模在急诊就诊或住院后30天和1年随访时为HF患者提供了更好的风险分层。
