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

Abstract 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 enab...

Full description

Saved in:
Bibliographic Details
Main Authors: Naidong Pang, Ying Tian, Hongjie Chi, Xiaohong Fu, Xin Li, Shuyu Wang, Feifei Pan, Dongying Wang, Lin Xu, Jingyi Luo, Aijun Liu, XingPeng Liu
Format: Article
Language:English
Published: BMC 2025-05-01
Series:Cardio-Oncology
Subjects:
Online Access:https://doi.org/10.1186/s40959-025-00342-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154836517978112
author Naidong Pang
Ying Tian
Hongjie Chi
Xiaohong Fu
Xin Li
Shuyu Wang
Feifei Pan
Dongying Wang
Lin Xu
Jingyi Luo
Aijun Liu
XingPeng Liu
author_facet Naidong Pang
Ying Tian
Hongjie Chi
Xiaohong Fu
Xin Li
Shuyu Wang
Feifei Pan
Dongying Wang
Lin Xu
Jingyi Luo
Aijun Liu
XingPeng Liu
author_sort Naidong Pang
collection DOAJ
description Abstract 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. Graphical Abstract
format Article
id doaj-art-ed4abb7a365e47ea8343fbdd80355a93
institution OA Journals
issn 2057-3804
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series Cardio-Oncology
spelling doaj-art-ed4abb7a365e47ea8343fbdd80355a932025-08-20T02:25:11ZengBMCCardio-Oncology2057-38042025-05-0111111710.1186/s40959-025-00342-5Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter studyNaidong Pang0Ying Tian1Hongjie Chi2Xiaohong Fu3Xin Li4Shuyu Wang5Feifei Pan6Dongying Wang7Lin Xu8Jingyi Luo9Aijun Liu10XingPeng Liu11Department of Cardiology, Heart Center, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Hematology, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Cardiology, Heart Center, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Cardiology, First Hospital of Shanxi Medical UniversityDepartment of Cardiology, Second Hospital of Shanxi Medical UniversityThe Third Clinical Medical College, Shanxi Medical UniversityDepartment of Cardiology, First Hospital of Shanxi Medical UniversityDepartment of Cardiology, Second Hospital of Shanxi Medical UniversityDepartment of Cardiology, Heart Center, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Hematology, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Hematology, Beijing Chaoyang Hospital, Capital Medical UniversityDepartment of Cardiology, Heart Center, Beijing Chaoyang Hospital, Capital Medical UniversityAbstract 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. Graphical Abstracthttps://doi.org/10.1186/s40959-025-00342-5Light chain amyloidosisCardiac deathSudden cardiac deathMachine learningPrediction modelNomogram
spellingShingle Naidong Pang
Ying Tian
Hongjie Chi
Xiaohong Fu
Xin Li
Shuyu Wang
Feifei Pan
Dongying Wang
Lin Xu
Jingyi Luo
Aijun Liu
XingPeng Liu
Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
Cardio-Oncology
Light chain amyloidosis
Cardiac death
Sudden cardiac death
Machine learning
Prediction model
Nomogram
title Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
title_full Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
title_fullStr Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
title_full_unstemmed Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
title_short Development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis: a multicenter study
title_sort development and validation of an early prediction model for cardiac death risk in patients with light chain amyloidosis a multicenter study
topic Light chain amyloidosis
Cardiac death
Sudden cardiac death
Machine learning
Prediction model
Nomogram
url https://doi.org/10.1186/s40959-025-00342-5
work_keys_str_mv AT naidongpang developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT yingtian developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT hongjiechi developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT xiaohongfu developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT xinli developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT shuyuwang developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT feifeipan developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT dongyingwang developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT linxu developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT jingyiluo developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT aijunliu developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy
AT xingpengliu developmentandvalidationofanearlypredictionmodelforcardiacdeathriskinpatientswithlightchainamyloidosisamulticenterstudy