In clinical practice, several standardized neuropsychological tests have been designed to assess and monitor the neurocognitive status of patients with neurodegenerative diseases such as Alzheimer’s disease. Important research efforts have been devoted so far to the development of multivariate machine learning models that combine the different test indexes to predict the diagnosis and prognosis of cognitive decline with remarkable results. However, less attention has been devoted to the explainability of these models. In this work, we present a robust framework to (i) perform a threefold classification between healthy control subjects, individuals with cognitive impairment, and subjects with dementia using different cognitive indexes and (ii) analyze the variability of the explainability SHAP values associated with the decisions taken by the predictive models. We demonstrate that the SHAP values can accurately characterize how each index affects a patient’s cognitive status. Furthermore, we show that a longitudinal analysis of SHAP values can provide effective information on Alzheimer’s disease progression.

中文翻译：

---

一个强大的框架，用于调查可解释的轻度认知障碍和阿尔茨海默病人工智能标记的可靠性和稳定性

在临床实践中，已经设计了几种标准化的神经心理学测试来评估和监测患有神经退行性疾病（如阿尔茨海默病）的患者的神经认知状态。迄今为止，重要的研究工作一直致力于开发多变量机器学习模型，该模型结合不同的测试指标来预测认知衰退的诊断和预后，并取得了显著成果。然而，很少有人关注这些模型的可解释性。在这项工作中，我们提出了一个稳健的框架来 (i) 在健康对照受试者、有认知障碍的个体、和使用不同认知指数的痴呆症患者，以及 (ii) 分析与预测模型做出的决策相关的可解释性 SHAP 值的可变性。我们证明 SHAP 值可以准确地描述每个指标如何影响患者的认知状态。此外，我们表明，对 SHAP 值的纵向分析可以提供有关阿尔茨海默病进展的有效信息。