Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias
PeerJ · 2024
DOI: 10.7717/peerj.18391 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ, 2024. Verfasst von Bihua Yao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory Medicine Center, Department of Clinical Laboratory, The First People's Hospital of Jiashan affiliated to Jiaxing University, Jiashan, Zhej…. Hauptthemen laut MEDLINE: Paraproteinemias, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Scientific Research Fund of Zhejiang Provincial Education Department, China, Zhejiang Province State Administration of Traditional Chinese Medicine, China, Zhejiang Province Medical and Health Science and Technology Project, China.
Abstract (Originalsprache)
Background
Plasma cell dyscrasias encompass a diverse set of disorders, where early and precise diagnosis is essential for optimizing patient outcomes. Despite advancements, current diagnostic methodologies remain underutilized in applying artificial intelligence (AI) to routine laboratory data. This study seeks to construct an AI-driven model leveraging standard laboratory parameters to enhance diagnostic accuracy and classification efficiency in plasma cell dyscrasias.
Methods
Data from 1,188 participants (609 with plasma cell dyscrasias and 579 controls) collected between 2018 and 2023 were analyzed. Initial variable selection employed Kruskal-Wallis and Wilcoxon tests, followed by dimensionality reduction and variable prioritization using the Shapley Additive Explanations (SHAP) approach. Nine pivotal variables were identified, including hemoglobin (HGB), serum creatinine, and β 2 -microglobulin. Utilizing these, four machine learning models (gradient boosting decision tree (GBDT), support vector machine (SVM), deep neural network (DNN), and decision tree (DT) were developed and evaluated, with performance metrics such as accuracy, recall, and area under the curve (AUC) assessed through 5-fold cross-validation. A subtype classification model was also developed, analyzing data from 380 cases to classify disorders such as multiple myeloma (MM) and monoclonal gammopathy of undetermined significance (MGUS).
Results
1. Variable selection: The SHAP method pinpointed nine critical variables, including hemoglobin (HGB), serum creatinine, erythrocyte sedimentation rate (ESR), and β 2 -microglobulin. 2. Diagnostic model performance: The GBDT model exhibited superior diagnostic performance for plasma cell dyscrasias, achieving 93.5% accuracy, 98.1% recall, and an AUC of 0.987. External validation reinforced its robustness, with 100% accuracy and an F1 score of 98.5%. 3. Subtype Classification: The DNN model excelled in classifying multiple myeloma, MGUS, and light-chain myeloma, demonstrating sensitivity and specificity above 90% across all subtypes.
Conclusions
AI models based on routine laboratory results significantly enhance the precision of diagnosing and classifying plasma cell dyscrasias, presenting a promising avenue for early detection and individualized treatment strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Laboratory Medicine Center, Department of Clinical Laboratory, The First People's Hospital of Jiashan affiliated to Jiaxing University, Jiashan, Zhejiang, China.
- Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China.
- Social and Behavioral Sciences, University of Amsterdam, Netherlands, Netherlands.
- Shanghai Jiaotong University, Shanghai, China.
- Department of Laboratory Medicine, Zhejiang Provincial People's Hospital, Hangzhou, Zhejiang, China.
- School of Science, Zhejiang University of Science and Technology, Hangzhou, Zhejiang, China.
Förderung
- Scientific Research Fund of Zhejiang Provincial Education Department, China
- Zhejiang Province State Administration of Traditional Chinese Medicine, China
- Zhejiang Province Medical and Health Science and Technology Project, China
- Jiashan Bureau of Science and Technology, China
Zitieren
APA
Yao, B., Liu, Y., Wu, Y., Mao, S., Zhang, H., Jiang, L., Fei, C., Wang, S., Tong, J., & Wu, J. (2024). Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias. PeerJ. https://doi.org/10.7717/peerj.18391
Vancouver
Yao B, Liu Y, Wu Y, Mao S, Zhang H, Jiang L, et al. Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias. PeerJ. 2024. doi:10.7717/peerj.18391
BibTeX
@article{Yao2024,
author = {Yao, Bihua and Liu, Yicheng and Wu, Yuwei and Mao, Siyu and Zhang, Hangbiao and Jiang, Lei and Fei, Cheng and Wang, Shuang and Tong, Jijun and Wu, Jianguo},
title = {Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias},
journal = {PeerJ},
year = {2024},
doi = {10.7717/peerj.18391}
}
EUVIMED