通过神经符号集成实现可解释的诊断预测
Explainable Diagnosis Prediction through Neuro-Symbolic Integration
- McWilliams School of Biomedical Informatics, The University of Texas Health Science Center（德克萨斯大学休斯顿健康科学中心麦克威廉姆斯生物医学信息学院）
- Mayo Clinic（梅奥诊所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出基于 Logical Neural Networks 的神经符号诊断预测模型，利用带可学习阈值的逻辑规则融合医学知识，在糖尿病预测中提升准确率、AUROC 与可解释性。
AI中文摘要：
诊断预测是医疗保健中的一项关键任务，及时且准确地识别医学病症能够显著影响患者结局。传统机器学习和深度学习模型已在该领域取得显著成功，但往往缺乏可解释性，而这正是临床环境中的一项关键要求。在本研究中，我们探索使用神经符号方法，特别是 Logical Neural Networks（LNN，逻辑神经网络），来开发用于诊断预测的可解释模型。本质上，我们设计并实现了基于 LNN 的模型，这些模型通过具有可学习阈值的逻辑规则整合特定领域知识。我们的模型，尤其是 $M_{\ ext{multi-pathway}}$ 和 $M_{\ ext{comprehensive}}$，表现出优于 Logistic Regression、SVM 和 Random Forest 等传统模型的性能；在糖尿病预测案例研究中，实现了更高的准确率（最高达 80.52%）和 AUROC 分数（最高达 0.8457）。LNN 模型中学习到的权重和阈值可直接揭示特征贡献，从而在不损害预测能力的情况下增强可解释性。这些发现凸显了神经符号方法在弥合医疗保健 AI 应用中准确性与可解释性之间差距方面的潜力。通过提供透明且可适应的诊断模型，我们的工作有助于推动精准医学的进步，并支持公平医疗保健解决方案的开发。未来研究将聚焦于把这些方法扩展到更大、更多样化的数据集，以进一步验证其在不同医学病症和人群中的适用性。
英文摘要：
Diagnosis prediction is a critical task in healthcare, where timely and accurate identification of medical conditions can significantly impact patient outcomes. Traditional machine learning and deep learning models have achieved notable success in this domain but often lack interpretability which is a crucial requirement in clinical settings. In this study, we explore the use of neuro-symbolic methods, specifically Logical Neural Networks (LNNs), to develop explainable models for diagnosis prediction. Essentially, we design and implement LNN-based models that integrate domain-specific knowledge through logical rules with learnable thresholds. Our models, particularly $M_{\text{multi-pathway}}$ and $M_{\text{comprehensive}}$, demonstrate superior performance over traditional models such as Logistic Regression, SVM, and Random Forest, achieving higher accuracy (up to 80.52\%) and AUROC scores (up to 0.8457) in the case study of diabetes prediction. The learned weights and thresholds within the LNN models provide direct insights into feature contributions, enhancing interpretability without compromising predictive power. These findings highlight the potential of neuro-symbolic approaches in bridging the gap between accuracy and explainability in healthcare AI applications. By offering transparent and adaptable diagnostic models, our work contributes to the advancement of precision medicine and supports the development of equitable healthcare solutions. Future research will focus on extending these methods to larger and more diverse datasets to further validate their applicability across different medical conditions and populations.
