Random Survival Forests (RSF) has recently showed better performance than statistical survival methods as Cox proportional hazard (CPH) in predicting conversion risk from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). However, RSF application in real-world clinical setting is still limited due to its black-box nature. For this reason, we aimed at providing a comprehensive study of RSF explainability with SHapley Additive exPlanations (SHAP) on biomarkers of stable and progressive patients (sMCI and pMCI) from Alzheimer’s Disease Neuroimaging Initiative. We evaluated three global explanations—RSF feature importance, permutation importance and SHAP importance—and we quantitatively compared them with Rank-Biased Overlap (RBO). Moreover, we assessed whether multicollinearity among variables may perturb SHAP outcome. Lastly, we stratified pMCI test patients in high, medium and low risk grade, to investigate individual SHAP explanation of one pMCI patient per risk group. We confirmed that RSF had higher accuracy (0.890) than CPH (0.819), and its stability and robustness was demonstrated by high overlap (RBO > 90%) between feature rankings within first eight features. SHAP local explanations with and without correlated variables had no substantial difference, showing that multicollinearity did not alter the model. FDG, ABETA42 and HCI were the first important features in global explanations, with the highest contribution also in local explanation. FAQ, mPACCdigit, mPACCtrailsB and RAVLT immediate had the highest influence among all clinical and neuropsychological assessments in increasing progression risk, as particularly evident in pMCI patients’ individual explanation. In conclusion, our findings suggest that RSF represents a useful tool to support clinicians in estimating conversion-to-AD risk and that SHAP explainer boosts its clinical utility with intelligible and interpretable individual outcomes that highlights key features associated with AD prognosis.

中文翻译：

---

随机生存森林预测从轻度认知障碍到阿尔茨海默病的转化风险的可解释性

最近，随机生存森林 (RSF) 在预测从轻度认知障碍 (MCI) 转变为阿尔茨海默氏病 (AD) 的风险方面，表现出比 Cox 比例风险 (CPH) 等统计生存方法更好的性能。然而，由于其黑盒性质，RSF 在现实临床环境中的应用仍然受到限制。因此，我们的目的是利用 SHapley Additive exPlanations (SHAP) 对阿尔茨海默病神经影像计划的稳定和进展患者（sMCI 和 pMCI）的生物标志物进行 RSF 可解释性的全面研究。我们评估了三种全局解释——RSF 特征重要性、排列重要性和 SHAP 重要性——并将它们与排名偏向重叠 (RBO) 进行定量比较。此外，我们评估了变量之间的多重共线性是否会干扰 SHAP 结果。最后，我们将 pMCI 测试患者分为高、中、低风险等级，以研究每个风险组一名 pMCI 患者的个体 SHAP 解释。我们确认 RSF 的准确度 (0.890) 比 CPH (0.819) 更高，并且其稳定性和鲁棒性通过前八个特征内的特征排名之间的高度重叠 (RBO > 90%) 得到证明。有相关变量和没有相关变量的 SHAP 局部解释没有显着差异，表明多重共线性不会改变模型。FDG、ABETA42 和 HCI 是全局解释中最重要的特征，在局部解释中贡献也最高。FAQ、mPACCdigit、mPACCtrailsB 和 RAVLT 立即在所有临床和神经心理学评估中对增加进展风险的影响最大，这在 pMCI 患者的个人解释中尤其明显。总之，我们的研究结果表明，RSF 是支持临床医生估计转化为 AD 风险的有用工具，SHAP 解释器通过可理解和可解释的个体结果增强了其临床实用性，突出了与 AD 预后相关的关键特征。