arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.15973cs.LGq-bio.QM
收藏

整合概率树与因果网络以处理临床和流行病学数据

Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Data

Munster Technological University(芒斯特理工大学);University of Cambridge(剑桥大学);Université Caen Normandie(卡昂诺曼底大学);ENSICAEN(卡昂高等工程师学院);CNRS(法国国家科学研究中心);Normandie Univ(诺曼底大学);GREYC UMR6072;Queens University Belfast(贝尔法斯特女王大学)

Sheresh Zahoor, Pietro Liò, Gaël Dias, Mohammed Hasanuzzaman

AI总结:

本研究提出PCF框架,整合因果贝叶斯网络与概率树,在保持与传统ML模型相当预测性能的同时提供因果推理能力,支持干预模拟和可解释性分析,助力基于证据的临床决策。

摘要:

医疗决策不仅需要准确的预测,还需要深入了解各因素如何影响患者结局。尽管传统的机器学习(ML)模型擅长预测结局(如识别高风险患者),但在回答关于干预的假设性问题时存在局限性。本研究引入了Probabilistic Causal Fusion(PCF)框架,该框架整合了因果贝叶斯网络(CBNs)和概率树(PTrees)以超越单纯的预测。PCF利用来自CBNs的因果关系来构建PTrees,从而能够量化因素的影响并模拟假设性干预。PCF在三个真实世界的医疗数据集上进行了验证,即MIMIC-IV、Framingham Heart Study和Diabetes,选择它们是因为其具有临床多样性的变量。它展示了与传统ML模型相当的预测性能,同时提供了额外的因果推理能力。为了增强可解释性,PCF结合了敏感性分析和SHapley Additive exPlanations(SHAP)。敏感性分析量化了因果参数对结局的影响,如住院时长(LOS)、冠心病(CHD)和Diabetes,而SHAP突出了单个特征在预测建模中的重要性。通过将因果推理与预测建模相结合,PCF弥合了临床直觉与数据驱动洞察之间的差距。其揭示可修改因素之间关系并模拟假设场景的能力,为临床医生提供了对因果途径更清晰的理解。这种方法支持更明智的、基于证据的决策,为应对多样化医疗环境中的复杂问题提供了稳健的框架。

英文摘要:

Healthcare decision-making requires not only accurate predictions but also insights into how factors influence patient outcomes. While traditional Machine Learning (ML) models excel at predicting outcomes, such as identifying high risk patients, they are limited in addressing what-if questions about interventions. This study introduces the Probabilistic Causal Fusion (PCF) framework, which integrates Causal Bayesian Networks (CBNs) and Probability Trees (PTrees) to extend beyond predictions. PCF leverages causal relationships from CBNs to structure PTrees, enabling both the quantification of factor impacts and simulation of hypothetical interventions. PCF was validated on three real-world healthcare datasets i.e. MIMIC-IV, Framingham Heart Study, and Diabetes, chosen for their clinically diverse variables. It demonstrated predictive performance comparable to traditional ML models while providing additional causal reasoning capabilities. To enhance interpretability, PCF incorporates sensitivity analysis and SHapley Additive exPlanations (SHAP). Sensitivity analysis quantifies the influence of causal parameters on outcomes such as Length of Stay (LOS), Coronary Heart Disease (CHD), and Diabetes, while SHAP highlights the importance of individual features in predictive modeling. By combining causal reasoning with predictive modeling, PCF bridges the gap between clinical intuition and data-driven insights. Its ability to uncover relationships between modifiable factors and simulate hypothetical scenarios provides clinicians with a clearer understanding of causal pathways. This approach supports more informed, evidence-based decision-making, offering a robust framework for addressing complex questions in diverse healthcare settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑