基于多变量逻辑回归的帕金森病认知障碍预测模型

巴梦茹; 尹晓红; 李少远

doi:10.11959/j.issn.2096-6652.202413

您当前的位置：

首页 >

文章列表页 >

基于多变量逻辑回归的帕金森病认知障碍预测模型

学术论文 | 更新时间：2024-08-06

- 基于多变量逻辑回归的帕金森病认知障碍预测模型
- A predictive model of cognitive impairment in Parkinson's disease based on multivariate logistic regression
- 智能科学与技术学报 2024年6卷第2期页码：232-243
- 作者机构：
  
  青岛科技大学自动化与电子工程学院，山东青岛 266061
- 作者简介：
  
  [ "巴梦茹（1997- ），女，青岛科技大学自动化与电子工程学院硕士生，主要研究方向为机器学习、智能优化、智慧医疗。" ]
  [ "尹晓红（1985- ），女，博士，青岛科技大学自动化与电子工程学院副教授，主要研究方向为复杂系统建模与优化、预测控制理论及其应用、绿色建筑节能优化。" ]
  [ "李少远（1965- ），男，博士，青岛科技大学自动化与电子工程学院教授，主要研究方向为网络化分布式系统的自适应预测控制、满意优化控制、生产全过程系统的优化控制、智能控制及工业应用。" ]
- 基金信息：
  
  山东省自然科学基金项目(ZR2023ZD49;ZR2023MF028);山东省重点研发项目（重大科技创新工程）(2020CXGC011402);青岛市临床重点专科项目;青岛市科技示范指导项目(20-3-4-37-NSH);山东大学青岛齐鲁医院灵活人才项目(QDKY2019RX05;QDKY2019RX13)
- DOI：10.11959/j.issn.2096-6652.202413
  中图分类号： TP181
- 收稿：2023-11-23，
  
  修回：2024-04-29，
  
  纸质出版：2024-06-15
- 稿件说明：
移动端阅览
巴梦茹,尹晓红,李少远.基于多变量逻辑回归的帕金森病认知障碍预测模型[J].智能科学与技术学报,2024,06(02):232-243.

BA Mengru,YIN Xiaohong,LI Shaoyuan.A predictive model of cognitive impairment in Parkinson's disease based on multivariate logistic regression[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):232-243.
巴梦茹,尹晓红,李少远.基于多变量逻辑回归的帕金森病认知障碍预测模型[J].智能科学与技术学报,2024,06(02):232-243. DOI： 10.11959/j.issn.2096-6652.202413.

BA Mengru,YIN Xiaohong,LI Shaoyuan.A predictive model of cognitive impairment in Parkinson's disease based on multivariate logistic regression[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):232-243. DOI： 10.11959/j.issn.2096-6652.202413.

摘要

帕金森病（Parkinson’s disease，PD）患者常伴随认知障碍，严重影响生活质量，因此对帕金森病认知障碍进行超前预测对于临床诊断和干预至关重要。然而，帕金森病受多变量因素（如年龄、性别、病程时间等）的耦合影响，使得认知障碍的超前预测面临严峻挑战。针对帕金森病认知障碍的多变量耦合特性，采用多变量逻辑回归方法，构建了一种新型列线图模型，旨在超前预测帕金森病患者发生认知障碍（cognitive impairment，CI）的风险。首先，应用最小绝对收缩选择算子（least absolute shrinkage and selection operator，LASSO）算法对可能影响患者认知能力的风险因素进行了分析，筛选出相关性高的临床变量。其次，采用多变量逻辑回归方法分析各变量之间的相关性，构建可视化的新型列线图模型，实现对帕金森病认知障碍的风险超前预测。最后，模型性能评估结果表明新型认知障碍预测模型具有良好的准确性、一致性和临床实用性，可显著地提高临床医生的诊断效率。此外，该模型还实现了对同一预测因子不同值的患者数量及分布的可视化对比和分析，能够辅助临床医生根据每位患者的个人风险制定个性化的医疗管理和咨询方案，有助于更早地展开对患者的干预和治疗，具备一定的临床诊断价值。

Abstract

Parkinson's disease (PD) patients were often accompanied by cognitive impairment

which seriously affected the quality of life

so the over-prediction of cognitive impairment in Parkinson's disease was crucial for clinical diagnosis and intervention. However

Parkinson's disease was affected by the coupling of multivariate factors

such as age

gender

and disease duration

which made the overprediction of cognitive impairment a serious challenge. Aiming at the multivariate coupling characteristics of cognitive impairment in Parkinson's disease

in this study

multivariate logistic regression was used to construct a novel column-linear graphical model aiming at over-predicting the risk of cognitive impairment (CI) in Parkinson's disease patients. First

the least absolute shrinkage and selection operator (LASSO) algorithm was applied to analyze the risk factors that may affect the cognitive ability of patients

and the clinical variables with high correlation were screened out. Second

multivariate logistic regression was used to analyze the correlation between variables and construct a visualized novel column-line diagram model to achieve the risk over prediction of cognitive impairment in Parkinson's disease. Finally

the results of model performance evaluation show that the novel cognitive impairment prediction model proposed in this paper has good accuracy

consistency and clinical practicability

which can significantly improve the diagnostic efficiency of clinicians; in addition

the model also realizes the visual comparison and analysis of the number and distribution of patients with different values of the same predictor

which can assist clinicians in formulating personalized healthcare management and consulting programs according to the individual risk of each patient

and help to start the intervention and treatment of the patients at an early stage

and it has a certain clinical diagnostic value.

关键词

Keywords

references

VOSSIUS C, LARSEN J P, JANVIN C, et al. The economic impact of cognitive impairment in Parkinson's disease[J]. Movement Disorders, 2011, 26(8): 1541-1544.

LEROI I, MCDONALD K, PANTULA H, et al. Cognitive impairment in Parkinson disease: impact on quality of life, disability, and caregiver burden[J]. Journal of Geriatric Psychiatry and Neurology, 2012, 25(4): 208-214.

KRAMER A A, ZIMMERMAN J E. Assessing the calibration of mortality benchmarks in critical care: the Hosmer-Lemeshow test revisited[J]. Critical Care Medicine, 2007, 35(9): 2052-2056.

李伟凯, 高欣, 纪同俭. 用于轻度认知障碍诊断的群体相似约束功能脑网络建模方法[J]. 智能科学与技术学报, 2019, 1(2): 145-153.

LI W K, GAO X, JI T J. Method of functional brain network modeling with group similarity constraint for mild cognitive impairment classification[J]. Journal of Intelligent Science and Technology, 2019, 1(2): 145-153.

SAUERBREI W, ROYSTON P, BINDER H. Selection of important variables and determination of functional form for continuous predictors in multivariable model building[J]. Stat Med, 2007, 26(30): 5512-5528.

HU M T, SZEWCZYK‐KRÓLIKOWSKI K, TOMLINSON P, et al. Predictors of cognitive impairment in an early stage Parkinson's disease cohort[J]. Movement Disorders, 2014, 29(3): 351-359.

钱忠立, 缪建良, 陈旭. 应用蒙特利尔认知评估量表评价睡眠剥夺对认知功能影响的研究[J]. 中国疗养医学, 2023, 32(7): 721-724.

QIAN Z L, MIAO J L, CHEN X. Study on the effect of sleep deprivation on cognitive function using the montreal cognitive assessment scale[J]. Chinese Convalescent Medicine, 2023, 32(7): 721-724.

HOBSON P, MEARA J. Mild cognitive impairment in Parkinson's disease and its progression onto dementia: a 16‐year outcome evaluation of the Denbighshire cohort[J]. International Journal of Geriatric Psychiatry, 2015, 30(10): 1048-1055.

NASKAR A, STEZIN A, DHARMAPPA A, et al. Fibrinogen and complement factor H are promising CSF protein biomarkers for Parkinson's disease with cognitive impairment─a proteomics-ELISA-based study[J]. ACS Chemical Neuroscience, 2022, 13(7): 1030-1045.

CHEN B, SONG L, YANG J, et al. P-roteomics of serum exosomes identified fibulin-1 as a novel biomarker for mild cognitive impairment[J]. Neural Regeneration Research, 2023, 18(3): 587-593.

LIU W L, LIN H W, HE X J, et al. Neurogranin as a cognitive biomarker in cerebrospinal fluid and blood exosomes for Alzheimer's disease and mild cognitive impairment[J]. Transl Psychiatry, 2020, 10(125): 1-9.

COSGROVE J, ALTY J E, JAMIESON S. Cognitive impairment in Parkinson's disease[J]. Postgraduate Medical Journal, 2015, 91(1074): 212-220.

MAREK K, JENNINGS D, LASCH S, et al. The Parkinson progression marker initiative (PPMI)[J]. Progress in Neurobiology, 2011, 95(4): 629-635.

杜淑慧, 何小海, 赵晓玲, 等. 基于时空和频域特征的EEG帕金森疾病识别[J] .电子测量技术, 2023, 46(3): 121-127.

DU S H, HE X H, ZHAO X L, et al. Parkinson's disease recognition by EEG based on spatiotemporal and frequency domain features[J]. Electronic Measure-Ment Technique, 2023, 46(3): 121-127.

TAJIRI Y, WADA-ISOE K, HAMADA M, et al. Comparison of MoCA and M-MSE for evaluating cognitive function in Japanese patients with Parkinson's disease[J] Movement Disorders, 2014: S367-S367.

ZORZON M, CAPUS L, PELLEGRINO A, et al. Familial and environmental risk factors in Parkinson's disease: a case-control study in north‐east Italy[J]. Acta Neurologica Scandinavica, 2002, 105(2): 77-82.

TIBSHIRANI R. Regression shrinkage and selection via the Lasso[J]. Journal of the Royal Statistical Society, 1996, 58(1): 267-288.

段俊伟, 许林灿, 全渝娟. 基于图正则化的贝叶斯宽度学习系统[J]. 智能科学与技术学报, 2022, 4(1): 109-117.

DUAN J W, XU L C, QUAN Y J. Bayesian width learning system based on graph regularization[J]. Journal of Intelligent Science and Technology, 2022, 4(1): 109-117.

龚永丽, 刘明, 刘蓉, 等. 基于Logistic回归的城市资源环境承载力预测研究——以武汉市为例[J]. 电子测量技术, 2018, 41(17): 42-46.

GONG Y L, LIU M, LIU R, et al. Prediction of urban resource and environment carrying capacity based on Logistic regression: a case study of Wuhan[J]. Electronic Measurement Technology, 2018, 41(17): 42-46.

曹汉平, 张晓晶, 祝睿杰, 等.数字金融时代机器学习模型在实时反欺诈中的应用与实践[J]. 智能科学与技术学报, 2019, 1(4): 342-351.

CAO H P, ZHANG X J, ZHU R J, et al. Application and practice of machine learning model in real-time anti-fraud in digital finance era[J]. Journal of Intelligent Science and Technology, 2019, 1(4): 342-351.

陈乐陶, 杨土保, 陈橙, 等. 决策曲线分析在 R 语言中的实现[J]. 中国卫生统计, 2018, 35(6): 955-957.

CHEN L T, YANG T B, CHEN C, et al. Implementation of decision curve analysis in R language[J]. China Health Statistics, 2018, 35(6): 955-957.

梁子超, 李智炜, 赖铿, 等. 10折交叉验证用于预测模型泛化能力评价及其R软件实现[J]. 中国医院统计, 2020, 18(4): 289-292

LIANG Z C, LI Z W, LAI K, et al. Application of 10-fold cross-validation in the evaluation of generalization ability of prediction models and the realization in R[J]. Chinese Hospital Statistics, 2020, 18(4): 289-292.

LITVAN I, GOLDMAN J G, TRÖSTER A I, et al. Diagnostic criteria for mild cognitive impairment in Parkinson's disease: movement disorder society task force guidelines[J]. Movement disorders, 2012, 27(3): 349-356.

WANG G, LAURI F, EL HASSANI A H. Feature selection by mRMR method for heart disease diagnosis[J]. IEEE Access, 2022, 10: 100786-100796.

GUAN H, YAN R, TANG H, et al. Intelligent fault diagnosis of hydraulic multi-way valve using the improved SECNN-GRU method with mRMR feature selection[J]. Sensors, 2023, 23(23): 9371.

LUSTED L B. Signal detectability and medical decision-making: signal detect-ability studies help radiologists evaluate equipment systems and performance of assistants[J]. Science, 1971, 171(3977): 1217-1219.

PENCINA M J, D'AGOSTINO R B. Overall C as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation[J]. Statistics in Medicine, 2004, 23(13): 2109-2123.

郭陈凤, 伍冬睿. 基于典型相关分析的多视图学习方法综述[J]. 智能科学与技术学报, 2022, 4(1): 14-26.

GUO C F, WU D R. A survey on canonical correlation analysis based multi-view learning[J]. Journal of Intelligence Science and Technology, 2022, 4(1): 14-26.

浏览量

299

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统