Early Detection of Heart Failure With Reduced Ejection Fraction Using Perioperative Data Among Noncardiac Surgical Patients: A Machine-Learning Approach

Abstract

Background: Heart failure with reduced ejection fraction (HFrEF) is a condition imposing significant health care burden. Given its syndromic nature and often insidious onset, the diagnosis may not be made until clinical manifestations prompt further evaluation. Detecting HFrEF in precursor stages could allow for early initiation of treatments to modify disease progression. Granular data collected during the perioperative period may represent an underutilized method for improving the diagnosis of HFrEF. We hypothesized that patients ultimately diagnosed with HFrEF following surgery can be identified via machine-learning approaches using pre- and intraoperative data.

Methods: Perioperative data were reviewed from adult patients undergoing general anesthesia for major surgical procedures at an academic quaternary care center between 2010 and 2016. Patients with known HFrEF, heart failure with preserved ejection fraction, preoperative critical illness, or undergoing cardiac, cardiology, or electrophysiologic procedures were excluded. Patients were classified as healthy controls or undiagnosed HFrEF. Undiagnosed HFrEF was defined as lacking a HFrEF diagnosis preoperatively but establishing a diagnosis within 730 days postoperatively. Undiagnosed HFrEF patients were adjudicated by expert clinician review, excluding cases for which HFrEF was secondary to a perioperative triggering event, or any event not associated with HFrEF natural disease progression. Machine-learning models, including L1 regularized logistic regression, random forest, and extreme gradient boosting were developed to detect undiagnosed HFrEF, using perioperative data including 628 preoperative and 1195 intraoperative features. Training/validation and test datasets were used with parameter tuning. Test set model performance was evaluated using area under the receiver operating characteristic curve (AUROC), positive predictive value, and other standard metrics.

Results: Among 67,697 cases analyzed, 279 (0.41%) patients had undiagnosed HFrEF. The AUROC for the logistic regression model was 0.869 (95% confidence interval, 0.829-0.911), 0.872 (0.836-0.909) for the random forest model, and 0.873 (0.833-0.913) for the extreme gradient boosting model. The corresponding positive predictive values were 1.69% (1.06%-2.32%), 1.42% (0.85%-1.98%), and 1.78% (1.15%-2.40%), respectively.

Conclusions: Machine-learning models leveraging perioperative data can detect undiagnosed HFrEF with good performance. However, the low prevalence of the disease results in a low positive predictive value, and for clinically meaningful sensitivity thresholds to be actionable, confirmatory testing with high specificity (eg, echocardiography or cardiac biomarkers) would be required following model detection. Future studies are necessary to externally validate algorithm performance at additional centers and explore the feasibility of embedding algorithms into the perioperative electronic health record for clinician use in real time.

Figure 1:

Study inclusions/exclusions, heart failure phenotypes, and machine learning methods (algorithm training, tuning, and testing). ASA = American Society of Anesthesiologists, F/S = feature selection, preop = preoperative, intraop = intraoperative, HFrEF = heart failure with reduced ejection fraction, HFpEF = heart failure with preserved ejection fraction * Minor procedures defined as cases with Anesthesia Current Procedural Terminology code base unit value ≤3 ** Additional details provided in Supplemental Digital Content 3

Figure 2:

Summary overview - preoperative features, intraoperative segmentation, and intraoperative features used for feature selection and machine learning model development.

Figure 3 -

Feature importance of top 50 (of 207) selected features in the tuned L1 regularized logistic regression model for detection of undiagnosed HFrEF on the test set. In the case of logistic regression, feature importance is calculated as the regression coefficients. Blue bars indicate positive coefficients (positively associated with undiagnosed HFrEF), red bars indicate negative coefficients (negatively associated with undiagnosed HFrEF). Black font indicates preoperative features; red font indicates intraoperative features. ACE = angiotensin converting enzyme; EGFR = estimated glomerular filtration rate; HbA1c = hemoglobin A1C; HFrEF = heart failure with reduced ejection fraction; LVEF = left ventricular ejection fraction MAP = mean arterial pressure