Nomogram Model Establishment for Short-Term Survival Prediction in Hypothyroidism Patients with Heart Failure Based on the MIMIC-IV Database

Abstract

The objective of this study was to develop an efficient nomogram model for predicting short-term survival in hypothyroidism patients with heart failure. Methods: Retrospective data was extracted from the Medical Information Mart for Intensive Care (MIMIC-IV) open-source clinical database. Patients diagnosed with hypothyroidism and heart failure upon admission were randomly assigned to the training and testing sets. Independent prognostic factors were determined through univariate and multivariate Cox regression analysis. The correlation between variables was assessed using the variance inflation factor. A nomogram model was constructed based on the identified prognostic factors, and risk scores were generated. The model's performance was assessed using the C-index, receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Result: A total of 656 hypothyroidism patients with heart failure were included in the study. Age, Sequential Organ Failure Assessment (SOFA) score, blood glucose (Glu), blood urea nitrogen (BUN), creatinine (Cr), respiratory rate (RR), and Charlson Comorbidity Index (CCI) score were identified as independent risk factors for patient mortality and were incorporated into the final model. The C-index for the training and testing sets was 0.763 and 0.721, respectively, indicating good accuracy of the model. Evaluation of the ROC curve, calibration curve, and decision curve further confirmed the model's robust and reliable predictive performance. Conclusion: In conclusion, our study successfully developed a convenient and effective nomogram model for predicting short-term mortality in hypothyroidism patients with heart failure. We identified several independent risk factors, including age, respiratory rate, serum creatinine, blood glucose levels, etc. These findings have implications for developing individualized therapeutic plans, enhancing patient management and follow-up, and ultimately improving disease outcomes.