联合血浆蛋白与临床人口学指标预测未来帕金森病
基于英国生物银行(UKB)52,503名基线无帕金森病(PD)参与者(中位年龄58岁,54%女性),中位随访14.0年期间751人确诊PD(中位年龄65岁,37%女性)。研究通过机器学习从1,463种血浆蛋白和93项临床人口学变量中筛选预测因子,构建的LightGBM模型在外部PPMI队列验证中AUC为0.810(95%CI 0.740-0.873)。
要点
- 联合22种血浆蛋白的LightGBM模型预测PD的AUC为0.800(95%CI 0.785-0.815)。
- 整合血浆蛋白与临床人口学变量后模型AUC提升至0.832(95%CI 0.815-0.849)。
- 外部PPMI队列验证模型AUC为0.810(95%CI 0.740-0.873),预测因子改变可在诊断前数年检出。
核心结论
- 研究结果支持基于机器学习的模型整合临床人口学变量与血浆蛋白,用于在一般人群中识别PD高风险个体。
- 尽管这些预测因子已在PPMI中验证,但仍需在更能反映一般社区的更多样化人群中进行额外验证。
研究设计与样本
- 利用英国生物银行(UKB)数据开展纵向研究,纳入具有基线血浆蛋白且无PD的参与者。
- 通过机器学习从1,463种血浆蛋白和93项临床人口学变量中筛选预测因子。
- 预测因子在帕金森病进展标志物计划(PPMI)队列中进行外部验证。
- 在UKB内开展巢式病例对照研究以探究预测因子的时间趋势。
- 共纳入52,503名无PD参与者(中位年龄58岁,54%女性)。
主要发现
- 中位随访14.0年期间,751人被诊断为PD(中位年龄65岁,37%女性)。
- 采用前向选择法选出22种血浆蛋白组成最优预测组合。
- 使用集成树LightGBM算法,仅血浆蛋白模型的AUC为0.800(95%CI 0.785-0.815)。
- 整合血浆蛋白与临床人口学变量的LightGBM模型AUC为0.832(95%CI 0.815-0.849)。
- 外部验证于PPMI队列产生AUC为0.810(95%CI 0.740-0.873)。
关键数值与推荐
- 关键预测因子包括年龄、受教育年限、创伤性脑损伤史和血清肌酐。
- 纳入的11种血浆蛋白为:神经丝轻链、整合素αV亚基、造血型前列腺素D合成酶、组胺N-甲基转移酶、微管蛋白聚合促进蛋白家族成员3、外胚层发育不良素A2受体、Latexin、白细胞介素-13受体α-1亚基、BAG家族分子伴侣调节因子3、色氨酰-tRNA合成酶和分泌粒蛋白-2。
- 这些预测因子的改变可在PD诊断前数年检出。
临床怎么用
- 原文未据此给出推荐。
局限性
- 尽管这些预测因子已在PPMI中验证,但仍需在更能反映一般社区的更多样化人群中进行额外验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND AND OBJECTIVES: Identification of individuals at high risk of developing Parkinson disease (PD) several years before diagnosis is crucial for developing treatments to prevent or delay neurodegeneration. This study aimed to develop predictive models for PD risk that combine plasma proteins and easily accessible clinical-demographic variables. METHODS: Using data from the UK Biobank (UKB), which recruited participants across the United Kingdom, we conducted a longitudinal study to identify predictors for incident PD. Participants with baseline plasma proteins and no PD were included. Through machine learning, we narrowed down predictors from a pool of 1,463 plasma proteins and 93 clinical-demographic. These predictors were then externally validated using the Parkinson's Progression Marker Initiative (PPMI) cohort. To further investigate the temporal trends of predictors, a nested case-control study was conducted within the UKB. RESULTS: A total of 52,503 participants without PD (median age 58, 54% female) were included. Over a median follow-up duration of 14.0 years, 751 individuals were diagnosed with PD (median age 65, 37% female). Using a forward selection approach, we selected a panel of 22 plasma proteins for optimal prediction. Using an ensemble tree-based Light Gradient Boosting Machine (LightGBM) algorithm, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.800 (95% CI 0.785-0.815). The LightGBM prediction model integrating both plasma proteins and clinical-demographic variables demonstrated enhanced predictive accuracy, with an AUC of 0.832 (95% CI 0.815-0.849). Key predictors identified included age, years of education, history of traumatic brain injury, and serum creatinine. The incorporation of 11 plasma proteins (neurofilament light, integrin subunit alpha V, hematopoietic PGD synthase, histamine N-methyltransferase, tubulin polymerization promoting protein family member 3, ectodysplasin A2 receptor, Latexin, interleukin-13 receptor subunit alpha-1, BAG family molecular chaperone regulator 3, tryptophanyl-TRNA synthetase, and secretogranin-2) augmented the model's predictive accuracy. External validation in the PPMI cohort confirmed the model's reliability, producing an AUC of 0.810 (95% CI 0.740-0.873). Notably, alterations in these predictors were detectable several years before the diagnosis of PD. DISCUSSION: Our findings support the potential utility of a machine learning-based model integrating clinical-demographic variables with plasma proteins to identify individuals at high risk for PD within the general population. Although these predictors have been validated by PPMI, additional validation in a more diverse population reflective of the general community is essential.
引用
- You J, Wang L, Wang Y, et al. Prediction of Future Parkinson Disease Using Plasma Proteins Combined With Clinical-Demographic Measures. Neurology. 2024. PMID: 38976826. doi:10.1212/WNL.0000000000209531
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。