通过可解释的人工智能对血液学指标的分析,用于诊断急性心力衰竭:一项回顾性研究
Rustem Yilmaz1, Fatma Hilal Yagin2, Cemil Colak2
1Department of Cardiology, Samsun Training and Research Hospital, Samsun University Faculty of Medicine, Samsun, Türkiye.
Frontiers in medicine
|April 18, 2024
概括
这项研究使用可解释的人工智能 (XAI) 和机器学习来使用血液学指标诊断急性心力衰竭 (AHF). 确定的主要预测因素包括血小板分布宽度 (PDW),年龄,红细胞分布宽度标准偏差 (RDW-SD) 和血小板计数.
科学领域:
- 医疗信息学 医疗信息学
- 人工智能在医学中的应用
- 血液学 血液学 血液学
背景情况:
- 急性心力衰竭 (AHF) 是一种严重的疾病,需要及时诊断和治疗,通常在急诊室进行.
- 目前对AHF的实验室测试缺乏足够的速度和准确性,强调需要改进诊断工具.
- 血液学指标具有潜力,但需要复杂的分析才能有效诊断AHF.
研究的目的:
- 应用可解释的人工智能 (XAI) 原则来分析血液学指标来诊断AHF.
- 开发和验证一个机器学习模型,以快速准确地检测AHF.
主要方法:
- 来自425名AHF患者和430名健康对照者的人口和血液学数据的回顾性分析.
- 使用最小绝对收缩和选择运算符 (LASSO) 进行特征选择和极端梯度提升 (XGBoost) 进行模型开发.
- 使用十倍交叉验证评估模型性能,计算AUC,F1得分,Brier得分,PPV和NPV等指标. 雇员SHAP用于风险因素分析.
主要成果:
- 在AHF患者和健康个体之间观察到各种血液学参数 (WBC,单细胞,中性粒细胞,NLR,RDW-SD,RDW-CV,PDW,红细胞,血红蛋白,基细胞,淋巴细胞,MPV,血小板,血红素,MCH,PCT) 的显著差异 (p <0.05).
- 在XGBoost-LASSO模型中,AUC达到87.9%,F1得分为87.4%.
- 确定AHF诊断的关键预测因素是血小板分布宽度 (PDW),年龄,红细胞分布宽度标准偏差 (RDW-SD) 和血小板计数 (PLT).
结论:
- 可解释的人工智能与机器学习相结合,有效地使用血液学数据诊断急性心力衰竭.
- 晚年,低血小板计数,高RDW-SD和升高的PDW是诊断AHF的关键血液学参数.
- 这种方法为临床环境中更快,更准确的AHF诊断提供了一个有希望的途径.
更多相关视频
05:35Author Spotlight: Developing a Point-of-Care Hemoglobin Estimation Method for Anemia Management
Published on: January 19, 2024
791
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
1.2K
相关概念视频
01:30Acute Coronary Syndrome III: Diagnostic Studies
Diagnosing acute coronary syndrome or ACS begins with a thorough patient history. Notable symptoms include central, crushing chest pain radiating to the left arm, neck, jaw, or back, along with shortness of breath, sweating (diaphoresis), nausea, vomiting, dizziness, and palpitations.It is crucial to note any history of cardiac illnesses and assess risk factors, including age, gender, smoking, hypertension, diabetes, hyperlipidemia, and a sedentary lifestyle.During physical examination, vital...
01:30Heart Failure IV: Classification and Diagnostic Evaluation
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...