机器学习在基于常规全血细胞计数（CBC）结果的慢性淋巴细胞白血病诊断和筛查中的应用。

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results.

机构信息

College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Doha, Qatar.

Medical Oncology-Hematology Department, National Centre for Cancer Care and Research (NCCCR), Hamad Medical Corporation (HMC), Doha, Qatar.

出版信息

Stud Health Technol Inform. 2023 Jun 29;305:279-282. doi: 10.3233/SHTI230483.

DOI:10.3233/SHTI230483

PMID:37387017

Abstract

The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

摘要

最近报道的全面流行病学和全球疾病负担表明，慢性淋巴细胞白血病（CLL）占白血病的 25-30%，因此是最常见的白血病亚型。然而，用于 CLL 诊断的人工智能（AI）技术还不够完善。本研究的新颖之处在于研究数据驱动技术，以利用仅在常规全血细胞计数（CBC）中反映出的复杂的 CLL 相关免疫功能障碍。我们使用统计推断、四种特征选择方法和多阶段超参数调整来构建稳健的分类器。基于二次判别分析（QDA）、逻辑回归（LR）和 XGBoost（XGb）的模型的准确率分别为 97.05%、97.63%和 98.62%，CBC 驱动的 AI 方法有望通过更少的资源使用和相关成本实现及时的医疗护理和改善患者预后。