P-027: Development of an artificial intelligence diagnostic model based on routine laboratory results and echocardiography for the early diagnosis of light chain amyloidosis

Abstract

Background In order to enhance the detection rate of light chain amyloidosis(AL) and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed. Methods Through cooperation with 18 hospitals in the Chinese Registration Network for Light-chain Amyloidosis (CRENLA), a nationwide survey was conducted from 2009 to 2020, and 1064 patients with systemic AL amyloidosis were registered and followed. The routine biochemical examination records and echocardiography from 824 patients were collected. Meanwhile 1000 records of non-AL (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases) were also collected. The data set was split into training and test subsets with the ratio of 4:1. An early assistant diagnostic model of MM was established by Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Deep Neural Networks (DNN), and Random Forest (RF). Out team calculated the precision and recall of the system. The performance of the diagnostic model was evaluated by using the receiver operating characteristic (ROC) curve. Results By designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (91.7%), recall (95.2%) and F1 score (0.93) for the AL group. The maximized area under the ROC (AUROC) was calculated. Conclusion The model established by artificial intelligence derived from routine laboratory and echocardiography results can accurately diagnose AL, which can boost the rate of early diagnosis. In order to enhance the detection rate of light chain amyloidosis(AL) and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed. Through cooperation with 18 hospitals in the Chinese Registration Network for Light-chain Amyloidosis (CRENLA), a nationwide survey was conducted from 2009 to 2020, and 1064 patients with systemic AL amyloidosis were registered and followed. The routine biochemical examination records and echocardiography from 824 patients were collected. Meanwhile 1000 records of non-AL (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases) were also collected. The data set was split into training and test subsets with the ratio of 4:1. An early assistant diagnostic model of MM was established by Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Deep Neural Networks (DNN), and Random Forest (RF). Out team calculated the precision and recall of the system. The performance of the diagnostic model was evaluated by using the receiver operating characteristic (ROC) curve. By designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (91.7%), recall (95.2%) and F1 score (0.93) for the AL group. The maximized area under the ROC (AUROC) was calculated. The model established by artificial intelligence derived from routine laboratory and echocardiography results can accurately diagnose AL, which can boost the rate of early diagnosis.