Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma

ObjectiveIn order to enhance the detection rate of multiple myeloma and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed.Methods4,187 routine blood and biochemical examination records were collected from Shengjing Hospital affil...

Full description

Bibliographic Details
Main Authors: Wei Yan, Hua Shi, Tao He, Jian Chen, Chen Wang, Aijun Liao, Wei Yang, Huihan Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-03-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2021.608191/full
id doaj-33ecf62c794a41cfa2b75acf1bd96e23
record_format Article
spelling doaj-33ecf62c794a41cfa2b75acf1bd96e232021-03-29T05:50:38ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-03-011110.3389/fonc.2021.608191608191Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple MyelomaWei Yan0Hua Shi1Tao He2Jian Chen3Chen Wang4Aijun Liao5Wei Yang6Huihan Wang7Haematology Department of Shengjing Hospital, China Medical University, Shenyang, ChinaHaematology Department of Shengjing Hospital, China Medical University, Shenyang, ChinaNeusoft Research Institute, Northeastern University, Shenyang, ChinaNeusoft Research Institute, Northeastern University, Shenyang, ChinaNeusoft Research Institute, Northeastern University, Shenyang, ChinaHaematology Department of Shengjing Hospital, China Medical University, Shenyang, ChinaHaematology Department of Shengjing Hospital, China Medical University, Shenyang, ChinaHaematology Department of Shengjing Hospital, China Medical University, Shenyang, ChinaObjectiveIn order to enhance the detection rate of multiple myeloma and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed.Methods4,187 routine blood and biochemical examination records were collected from Shengjing Hospital affiliated to China Medical University from January 2010 to January 2020, which include 1,741 records of multiple myeloma (MM) and 2,446 records of non-myeloma (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases). The data set was split into training and test subsets with the ratio of 4:1 while connecting hemoglobin, serum creatinine, serum calcium, immunoglobulin (A, G and M), albumin, total protein, and the ratio of albumin to globulin data. 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.ResultsBy designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (92.9%), recall (90.0%) and F1 score (0.915) for the myeloma group. The maximized area under the ROC (AUROC) was calculated, and the results of GBDT (AUC: 0.975; 95% confidence interval (CI): 0.963–0.986) outperformed that of SVM, DNN and RF.ConclusionThe model established by artificial intelligence derived from routine laboratory results can accurately diagnose MM, which can boost the rate of early diagnosis.https://www.frontiersin.org/articles/10.3389/fonc.2021.608191/fullmultiple myelomaartificial intelligenceearly diagnosisgradient boosting decision treemachine learning
collection DOAJ
language English
format Article
sources DOAJ
author Wei Yan
Hua Shi
Tao He
Jian Chen
Chen Wang
Aijun Liao
Wei Yang
Huihan Wang
spellingShingle Wei Yan
Hua Shi
Tao He
Jian Chen
Chen Wang
Aijun Liao
Wei Yang
Huihan Wang
Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
Frontiers in Oncology
multiple myeloma
artificial intelligence
early diagnosis
gradient boosting decision tree
machine learning
author_facet Wei Yan
Hua Shi
Tao He
Jian Chen
Chen Wang
Aijun Liao
Wei Yang
Huihan Wang
author_sort Wei Yan
title Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
title_short Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
title_full Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
title_fullStr Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
title_full_unstemmed Employment of Artificial Intelligence Based on Routine Laboratory Results for the Early Diagnosis of Multiple Myeloma
title_sort employment of artificial intelligence based on routine laboratory results for the early diagnosis of multiple myeloma
publisher Frontiers Media S.A.
series Frontiers in Oncology
issn 2234-943X
publishDate 2021-03-01
description ObjectiveIn order to enhance the detection rate of multiple myeloma and execute an early and more precise disease management, an artificial intelligence assistant diagnosis system is developed.Methods4,187 routine blood and biochemical examination records were collected from Shengjing Hospital affiliated to China Medical University from January 2010 to January 2020, which include 1,741 records of multiple myeloma (MM) and 2,446 records of non-myeloma (infectious diseases, rheumatic immune system diseases, hepatic diseases and renal diseases). The data set was split into training and test subsets with the ratio of 4:1 while connecting hemoglobin, serum creatinine, serum calcium, immunoglobulin (A, G and M), albumin, total protein, and the ratio of albumin to globulin data. 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.ResultsBy designing the features properly, the typical machine learning algorithms SVM, DNN, RF and GBDT all performed well. GBDT had the highest precision (92.9%), recall (90.0%) and F1 score (0.915) for the myeloma group. The maximized area under the ROC (AUROC) was calculated, and the results of GBDT (AUC: 0.975; 95% confidence interval (CI): 0.963–0.986) outperformed that of SVM, DNN and RF.ConclusionThe model established by artificial intelligence derived from routine laboratory results can accurately diagnose MM, which can boost the rate of early diagnosis.
topic multiple myeloma
artificial intelligence
early diagnosis
gradient boosting decision tree
machine learning
url https://www.frontiersin.org/articles/10.3389/fonc.2021.608191/full
work_keys_str_mv AT weiyan employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT huashi employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT taohe employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT jianchen employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT chenwang employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT aijunliao employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT weiyang employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
AT huihanwang employmentofartificialintelligencebasedonroutinelaboratoryresultsfortheearlydiagnosisofmultiplemyeloma
_version_ 1724199051790909440