Development and validation of a nomogram model for predicting the high-risk symptom multi-trajectories in patients with heart failure.

Abstract

Aim: To identify the high-risk symptom multi-trajectories of patients with heart failure (HF) during the first six months after discharge, and construct a nomogram model to predict them.

Methods and results: This study was conducted across four tertiary hospitals from September 2023 to January 2025. Symptom evaluations was conducted before discharge, and at 2 weeks, 1 month, 3 months, and 6 months after discharge. A total of 259 HF patients completed the six-month follow-up. Of these, 18.9% exhibited severe-variable changes in symptom trajectories, which were significantly associated with unplanned readmission, indicating high-risk symptom multi-trajectories. LASSO regression identified four variables: anxiety, depression, resilience, and social support. The resulting nomogram, a visual tool used to predict the probability of high-risk symptom multi-trajectories, achieved an area under the curve of 0.921, a sensitivity of 85.7%, and a specificity of 83.3%. The calibration curve exhibited a high level of consistency. Decision curve analysis revealed that this nomogram had greater clinical value when the risk threshold was between 5% and 79%.

Conclusion: 18.9% of patients with HF had high-risk symptom multi-trajectories of poor prognosis during the six months after discharge. A nomogram was developed to predict the likelihood of this group. This tool provided valuable guidance for the early intervention of HF symptoms.