文献速递神经核医学

多项逻辑回归算法用于帕金森综合征患者分类

Multinomial logistic regression algorithm for the classification of patients with parkinsonisms.
PubMed 文献 · EJNMMI Res · 2025-03-16

研究基于18F-FDG PET脑图像,采用SSM/PCA与多项逻辑回归构建分类算法,在帕金森综合征患者队列中训练并验证。PSP的AUC最高为0.95,PD为0.93,MSA为0.90;在99%概率阈值下,PD、MSA、PSP分别有82%、29%、77%被正确识别。

要点

  • 算法在验证队列中区分PD、MSA、PSP的AUC分别为0.93、0.90、0.95。
  • 99%概率阈值下正确识别率:PD 82%、MSA 29%、PSP 77%。
  • 误分类率低(5%–6%),但MSA有65%被归为未确定。

核心结论

  • 与现有算法相比,该方法在诊断PD、MSA和PSP方面具有相当的准确性和可靠性,且无需健康对照图像。
  • 该方法可同时区分多种帕金森综合征,并灵活容纳新分组。

研究设计与样本

  • 研究使用多项逻辑回归与SSM/PCA构建分类算法,应用于18F-FDG PET脑图像。
  • 算法在神经退行性帕金森综合征患者队列中训练和优化,并在另一独立帕金森综合征患者队列中验证。

主要发现

  • AUC值最高为进行性核上性麻痹(PSP)(AUC=0.95),其次为帕金森病(PD)(AUC=0.93)和多系统萎缩(MSA)(AUC=0.90)。
  • 以99%概率阈值分类时,82%的PD患者、29%的MSA患者和77%的PSP患者被正确识别。
  • 仅5%的PD、6%的MSA和6%的PSP患者被误分类,其余患者(PD 13%、MSA 65%、PSP 18%)被算法归为未确定。

关键数值与推荐

  • PSP的AUC=0.95,PD的AUC=0.93,MSA的AUC=0.90。
  • 99%概率阈值下,正确识别率:PD 82%、MSA 29%、PSP 77%。
  • 误分类率:PD 5%、MSA 6%、PSP 6%;未确定率:PD 13%、MSA 65%、PSP 18%。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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: Accurate differential diagnosis of neurodegenerative parkinsonisms is challenging due to overlapping early symptoms and high rates of misdiagnosis. To improve the diagnostic accuracy, we developed an integrated classification algorithm using multinomial logistic regression and Scaled Subprofile Model/Principal Component Analysis (SSM/PCA) applied to 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) brain images. In this novel classification approach, SSM/PCA is applied to FDG-PET brain images of patients with various parkinsonisms, which are compared against the constructed undetermined images. This process involves spatial normalization of the images and dimensionality reduction via PCA. The resulting principal components are then used in a multinomial logistic regression model, which generates disease-specific topographies that can be used to classify new patients. The algorithm was trained and optimized on a cohort of patients with neurodegenerative parkinsonisms and subsequently validated on a separate cohort of patients with parkinsonisms. RESULTS: The Area Under the Curve (AUC) values were the highest for progressive supranuclear palsy (PSP) (AUC = 0.95), followed by Parkinson's disease (PD) (AUC = 0.93) and multiple system atrophy (MSA) (AUC = 0.90). When classifying the patients based on their calculated probability for each group, the desired tradeoff between sensitivity and specificity had to be selected. With a 99% probability threshold for classification into a disease group, 82% of PD patients, 29% of MSA patients, and 77% of PSP patients were correctly identified. Only 5% of PD, 6% of MSA and 6% of PSP patients were misclassified, whereas the remaining patients (13% of PD, 65% of MSA and 18% of PSP) are undetermined by our classification algorithm. CONCLUSIONS: Compared to existing algorithms, this approach offers comparable accuracy and reliability in diagnosing PD, MSA, and PSP with no need of healthy control images. It can also distinguish between multiple types of parkinsonisms simultaneously and offers the flexibility to easily accommodate new groups.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Štokelj E, Rus T, Jamšek J, et al. Multinomial logistic regression algorithm for the classification of patients with parkinsonisms. EJNMMI Res. 2025. PMID: 40091087. doi:10.1186/s13550-025-01210-0

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。