Zhang Jimmy, Song Luo, Chan Kwun, Miller Zachary, Huang Kuan-Lin
Icahn School of Medicine at Mount Sinai.
School of Medicine, The University of Queensland.
Res Sq. 2023 Jan 20:rs.3.rs-2350961. doi: 10.21203/rs.3.rs-2350961/v1.
Dementia care is challenging due to the divergent trajectories in disease progression and outcomes. Predictive models are needed to identify patients at risk of near-term mortality. Here, we developed machine learning models predicting survival using a dataset of 45,275 unique participants and 163,782 visit records from the U.S. National Alzheimer's Coordinating Center (NACC). Our models achieved an AUC-ROC of over 0.82 utilizing nine parsimonious features for all one-, three-, five-, and ten-year thresholds. The trained models mainly consisted of dementia-related predictors such as specific neuropsychological tests and were minimally affected by other age-related causes of death, e.g., stroke and cardiovascular conditions. Notably, stratified analyses revealed shared and distinct predictors of mortality across eight dementia types. Unsupervised clustering of mortality predictors grouped vascular dementia with depression and Lewy body dementia with frontotemporal lobar dementia. This study demonstrates the feasibility of flagging dementia patients at risk of mortality for personalized clinical management.
由于疾病进展和预后的轨迹不同，痴呆症护理具有挑战性。需要预测模型来识别近期有死亡风险的患者。在此，我们利用来自美国国家阿尔茨海默病协调中心（NACC）的45275名独特参与者和163782次就诊记录的数据集，开发了预测生存的机器学习模型。我们的模型在所有1年、3年、5年和10年阈值下，利用9个简约特征实现了超过0.82的AUC-ROC。训练后的模型主要由与痴呆症相关的预测因素组成，如特定的神经心理学测试，并且受其他与年龄相关的死亡原因（如中风和心血管疾病）的影响最小。值得注意的是，分层分析揭示了八种痴呆类型中共同和不同的死亡预测因素。对死亡预测因素的无监督聚类将血管性痴呆与抑郁症归为一组，将路易体痴呆与额颞叶痴呆归为一组。这项研究证明了标记有死亡风险的痴呆症患者以进行个性化临床管理的可行性。
