An interpretable machine learning (ML) framework is introduced to enhance the diagnosis of Mild Cognitive Impairment (MCI) and Alzheimer's disease (AD) by ensuring robustness of the ML models' interpretations. The dataset used comprises volumetric measurements from brain MRI and genetic data from healthy individuals and patients with MCI/AD, obtained through the Alzheimer's Disease Neuroimaging Initiative. The existing class imbalance is addressed by an ensemble learning approach, while various attribution-based and counterfactual-based interpretability methods are leveraged towards producing diverse explanations related to the pathophysiology of MCI/AD. A unification method combining SHAP with counterfactual explanations assesses the interpretability techniques' robustness. The best performing model yielded 87.5% balanced accuracy and 90.8% F1-score. The attribution-based interpretability methods highlighted significant volumetric and genetic features related to MCI/AD risk. The unification method provided useful insights regarding those features' necessity and sufficiency, further showcasing their significance in MCI/AD diagnosis.

翻译：本文提出了一种可解释机器学习框架，旨在通过确保机器学习模型解释的鲁棒性来提升轻度认知障碍与阿尔茨海默病的诊断效能。所使用的数据集包含来自阿尔茨海默病神经影像学计划的脑部磁共振成像体积测量数据及健康个体与MCI/AD患者的遗传数据。针对现存的类别不平衡问题，本研究采用集成学习方法进行处理，同时综合利用多种基于归因和反事实的可解释性方法，以生成与MCI/AD病理生理机制相关的多样化解释。通过将SHAP与反事实解释相结合的统一评估方法，对各类可解释性技术的鲁棒性进行了系统检验。性能最优模型的平衡准确率达到87.5%，F1分数为90.8%。基于归因的可解释性方法凸显了与MCI/AD风险相关的重要体积特征与遗传特征。统一评估方法为这些特征的必要性与充分性提供了有价值的见解，进一步揭示了它们在MCI/AD诊断中的重要意义。