Fluid volume status detection model for patients with heart failure based on machine learning methods

Fluid volume abnormalities are a major cause of exacerbations in heart failure patients. However, there is few efficient, rapid, or cost-effective clinical approach for determining volume status, resulting in inadequate or unsatisfactory treatment. The aim was to develop an early fluid volume detection model for heart failure patients utilizing a machine learning stratification.

The training set data collected by Tianjin Chest Hospital on heart failure patients from December 2016 to December 2021, included 2056 samples and 97 medical characteristics. The minimum Redundancy Maximum Relevance(mRMR) feature selection method was utilized to filter features that were strongly related to the patient's fluid volume status. Four machine learning classification models were used to predict patients' fluid volume status, and their effectiveness was measured using the receiver operating characteristic (ROC) area under the curve (AUC), calibration curve, accuracy, precision, recall, F1 score, specificity, and sensitivity. Data from 186 heart failure patients collected between January 2022 and July 2022 were employed as an external validation set to investigate the effects of model training. SHapley Additive exPlanations (SHAP) were used to interpret the ML models.

Thirty features were selected for model development, and the area under the ROC curve AUC (95 % CI) for the four machine learning models in the testing set was 0.75 (0.73-0.77), 0.77 (0.74-0.79), 0.70 (0.67-0.73), and 0.76 (0.73-0.78), and the AUC (95 % CI) in the external validation set was 0.74 (0.71-0.76), 0.70 (0.67-0.73), 0.64 (0.59-0.68), and 0.67 (0.63-0.71). Logistic regression models were globally interpreted using SHAP-based summary plots.

Machine learning methods are effective in detecting fluid volume status in heart failure patients and can assist physicians with assisted diagnosis, thus helping clinicians to tailor precise management.