A Risk Score to Diagnose Cardiac Involvement and Provide Prognosis Information in Patients at Risk of Cardiac Light-Chain Amyloidosis

Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study

BACKGROUND

Cardiac involvement is the primary driver of death in systemic light chain (AL) amyloidosis. However, the early prediction of cardiac death risk in AL amyloidosis remains insufficient.

OBJECTIVES

We aimed to develop a novel prediction model and prognostic scoring system that enables early identification of these high-risk individuals.

METHODS

This study enrolled 235 patients with confirmed AL cardiac amyloidosis from three hospitals. Patients from the first hospital were randomly assigned to the training and internal validation sets in an 8:2 ratio, while the external validation set comprised patients from the other two hospitals. Participants were categorized into a cardiac death group and a non-cardiac death group (including survivors and those who died from other causes). Five different machine learning models were used to train model, and model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis.

RESULTS

All five models showed excellent performance on the training and internal validation sets. In external validation, both the Logistic Regression (LR) and Random Forest models achieved an area under the ROC curve of 0.873 and 0.877, respectively, and exhibited superior calibration and decision curve analysis. Considering the comprehensive performance and clinical applicability, the LR model was selected as the final prediction model. The visualization results are ultimately presented in a nomogram. Further analyses were performed on the newly identified predictors.

CONCLUSIONS

This prediction model enables early identification and risk assessment of cardiac death in patients with AL amyloidosis, exhibiting considerable predictive ability.

Predictive Model Based on Texture Analysis of Noncontrast Cardiac Magnetic Resonance Images for the Prognostic Evaluation of Cardiac Amyloidosis

OBJECTIVES

We aimed to develop a predictive model based on textural features of noncontrast cardiac magnetic resonance (CMR) imaging for risk stratification toward adverse events in patients with cardiac amyloidosis (CA).

METHODS

A cohort of 78 patients with CA was grouped into training (n = 54) and validation (n = 24) sets at a ratio of 7:3. A total of 275 textural features were extracted from the CMR images. MaZda and a support vector machine (SVM) were used for feature selection and model construction. An SVM model incorporating radiological and textural features was built to predict endpoint events by evaluating the area under the curve.

RESULTS

In the entire cohort, 52 patients experienced major adverse cardiovascular events and 26 patients did not. By combining 2 radiological features and 8 texture features, extracted from cine and T2-weighted imaging images, the SVM model achieved area under the curves of the receiver operating characteristic and precision-recall curves of 0.930 and 0.962 in the training cohort and that of 0.867 and 0.941 in the validated cohort, respectively. The Kaplan-Meier curve of this SVM model criterion significantly stratified the CA outcomes (log-rank test, P  < 0.0001).

CONCLUSIONS

The SVM model based on radiological and textural features derived from noncontrast CMR images can be a reliable biomarker for adverse events prognostication in patients with CA.

The value of myocardial contraction fraction and long-axis strain to predict late gadolinium enhancement in multiple myeloma patients with secondary cardiac amyloidosis

The aim of this study is to assess the effectiveness of conventional and two additional functional markers derived from standard cardiac magnetic resonance (CMR) images in detecting the occurrence of late gadolinium enhancement (LGE) in patients with secondary cardiac amyloidosis (CA) related to multiple myeloma (MM). This study retrospectively included 32 patients with preserved ejection fraction (EF) who had MM-CA diagnosed consecutively. Conventional left ventricular (LV) function markers and two additional functional markers, namely myocardial contraction fraction (MCF) and LV long-axis strain (LAS), were obtained using commercial cardiac post-processing software. Logistic regression analyses and receiver operating characteristic (ROC) analysis were performed to evaluate the predictive performances. (1) There were no notable distinctions in clinical features between the LGE+ and LGE- groups, with the exception of a reduced systolic blood pressure in the former (105.60 ± 18.85 mmHg vs. 124.50 ± 20.95 mmHg, P = 0.022). (2) Patients with MM-CA presented with intractable heart failure with preserved ejection fraction (HFpEF). The LVEF in the LGE+ group exhibited a greater reduction (54.27%, IQR 51.59-58.39%) in comparison to the LGE- group (P < 0.05). And MM-CA patients with LGE+ had significantly higher LVMI (90.15 ± 23.69 g/m2), lower MCF (47.39%, IQR 34.28-54.90%), and the LV LAS were more severely damaged (- 9.94 ± 3.42%) than patients with LGE- (all P values < 0.05). (3) The study found that MCF exhibited a significant independent association with LGE, as indicated by an odds ratio of 0.89 (P < 0.05). The cut-off value for MCF was determined to be 64.25% with a 95% confidence interval ranging from 0.758 to 0.983. The sensitivity and specificity of this association were calculated to be 95% and 83%, respectively. MCF is a simple reproducible predict marker of LGE in MM-CA patients. It is a potentially CMR-based method that promise to reduce scan times and costs, and boost the accessibility of CMR.

The diagnostic value of multiparameter cardiovascular magnetic resonance for early detection of light-chain amyloidosis from hypertrophic cardiomyopathy patients

Background

Early-stage amyloidosis of the heart is prone to be underdiagnosed or misdiagnosed, increasing the risk of early heart failure and even death of the patient. To ensure timely intervention for cardiac light-chain amyloidosis (AL CA), it is vital to develop an effective tool for early identification of the disease. Recently, multiparameter cardiovascular magnetic resonance (CMR) has been used as a comprehensive tool to assess myocardial tissue characterization. We aimed to investigate the difference in left ventricular (LV) strain, native T1, extracellular volume (ECV), and late gadolinium enhancement (LGE) between AL CA patients, hypertrophic cardiomyopathy patients (HCM), and healthy control subjects (HA). Moreover, we explored the value of multiparameter CMR for differential diagnosis of the early-stage AL CA patients from HCM patients, who shared similar imaging characteristics under LGE imaging.

Methods

A total of 38 AL CA patients, 16 HCM patients, and 17 HA people were prospectively recruited. All subjects underwent LGE imaging, Cine images, and T1 mapping on a 3T scanner. The LV LGE pattern was recorded as none, patchy or global. LV strain, native T1, and ECV were measured semi-automatically using dedicated CMR software. According to clinical and biochemical markers, all patients were classified as Mayo stage I/II and Mayo stage IIIa/IIIb. Univariable and multivariable logistic regression models were utilized to identify independent predictors of early-stage AL CA from HCM patients. Receiver operator characteristic (ROC) curve analysis and Youden’s test were done to determine the accuracy of multiparameter CMR in diagnosing Mayo stage I/II AL CA and establish a cut-off value.

Results

For Mayo stage I/II AL CA patients, the global longitudinal strain (GLS) absolute value (11.9 ± 3.0 vs. 9.5 ± 1.8, P < 0.001) and the global circumferential strain (GCS) absolute value (19.0 ± 3.6 vs. 9.5 ± 1.8, P < 0.001) were significantly higher than in HCM patients. The native T1 (1334.9 ± 49.9 vs. 1318.2 ± 32.4 ms, P < 0.0001) and ECV values (37.8 ± 5.7 vs. 31.3 ± 2.5%, P < 0.0001) were higher than that of HCM patients. In multiparameter CMR models, GCS (2.097, 95% CI: 1.292–3.403, P = 0.003), GLS (1.468, 95% CI: 1.078–1.998, P = 0.015), and ECV (0.727, 95% CI: 0.569–0.929, P = 0.011) were the significant variables for the discrimination of the early-stage AL CA patients from HCM patients. ROC curve analysis and Youden’s test were used on GCS, GLS, ECV, and pairwise parameters for differentiating between Mayo stage I/II AL CA and HCM patients, respectively. The combination of GLS, GCS, and ECV mapping could distinguish Mayo stage I/II AL amyloidosis patients from hypertrophic cardiomyopathy with excellent performance (AUC = 0.969, Youden index = 0.813).

Conclusion

In early-stage AL CA patients with atypical LGE, who had similar imaging features as HCM patients, ECV mapping, GCS, and GLS were correlated with the clinical classification of the patients. The combination of GCS, GLS, and ECV could differentiate early-stage AL CA from HCM patients. Multiparameter CMR has the potential to provide an effective and quantitative tool for the early diagnosis of myocardial amyloidosis.