Unveiling relevant non-motor Parkinson's disease severity symptoms using a machine learning approach

被引:45
作者
Armananzas, Ruben [1 ]
Bielza, Concha [1 ]
Chaudhuri, Kallol Ray [2 ]
Martinez-Martin, Pablo [3 ,4 ]
Larranaga, Pedro [1 ]
机构
[1] Univ Politecn Madrid, Dept Inteligencia Artificial, Computat Intelligence Grp, Boadilla Del Monte 28660, Spain
[2] Kings Coll Hosp London, Natl Parkinson Fdn, Ctr Excellence, London SE5 9RS, England
[3] Inst Salud Carlos III, Ctr Alzheimer Fdn Reina Sofia, Unidad Invest Proyecto Alzheimer, Madrid 28031, Spain
[4] Inst Salud Carlos III, Ctr Alzheimer Fdn Reina Sofia, CIBERNED, Madrid 28031, Spain
关键词
Estimation of distribution algorithms; Feature subset selection; Severity indexes; Parkinson's disease; AUTONOMIC DYSFUNCTION; SCALE; PREVALENCE; DEMENTIA;
D O I
10.1016/j.artmed.2013.04.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Objective: Is it possible to predict the severity staging of a Parkinson's disease (PD) patient using scores of non-motor symptoms? This is the kickoff question for a machine learning approach to classify two widely known PD severity indexes using individual tests from a broad set of non-motor PD clinical scales only. Methods: The Hoehn & Yahr index and clinical impression of severity index are global measures of PD severity. They constitute the labels to be assigned in two supervised classification problems using only non-motor symptom tests as predictor variables. Such predictors come from a wide range of PD symptoms, such as cognitive impairment, psychiatric complications, autonomic dysfunction or sleep disturbance. The classification was coupled with a feature subset selection task using an advanced evolutionary algorithm, namely an estimation of distribution algorithm. Results: Results show how five different classification paradigms using a wrapper feature selection scheme are capable of predicting each of the class variables with estimated accuracy in the range of 72-92%. In addition, classification into the main three severity categories (Mild, moderate and severe) was split into dichotomic problems where binary classifiers perform better and select different subsets of non-motor symptoms. The number of jointly selected symptoms throughout the whole process was low, suggesting a link between the selected non-motor symptoms and the general severity of the disease. Conclusion: Quantitative results are discussed from a medical point of view, reflecting a clear translation to the clinical manifestations of PD. Moreover, results include a brief panel of non-motor symptoms that could help clinical practitioners to identify patients who are at different stages of the disease from a limited set of symptoms, such as hallucinations, fainting, inability to control body sphincters or believing in unlikely facts. (c) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:195 / 202
页数:8
相关论文
共 48 条
[31]   The Impact of Non-Motor Symptoms on Health-Related Quality of Life of Patients with Parkinson's Disease [J].
Martinez-Martin, Pablo ;
Rodriguez-Blazquez, Carmen ;
Kurtis, Monica M. ;
Chaudhuri, K. Ray .
MOVEMENT DISORDERS, 2011, 26 (03) :399-406
[32]  
Navio M., 2001, P 2 INT S DAT AN ISM, P195
[33]   SVM Feature Selection Based Rotation Forest Ensemble Classifiers to Improve Computer-Aided Diagnosis of Parkinson Disease [J].
Ozcift, Akin .
JOURNAL OF MEDICAL SYSTEMS, 2012, 36 (04) :2141-2147
[34]   A prospective study of delusional misidentification syndromes in Parkinson's disease with dementia [J].
Pagonabarraga, Javier ;
Llebaria, Gisela ;
Garcia-Sanchez, Carmen ;
Pascual-Sedano, Berta ;
Gironell, Alexandre ;
Kulisevsky, Jaime .
MOVEMENT DISORDERS, 2008, 23 (03) :443-448
[35]  
Santana R, 2010, J STAT SOFTW, V35, P1
[36]   Prevalence of orthostatic hypotension in Parkinson's disease [J].
Senard, JM ;
Rai, S ;
LapeyreMestre, M ;
Brefel, C ;
Rascol, O ;
Rascol, A ;
Montastruc, JL .
JOURNAL OF NEUROLOGY NEUROSURGERY AND PSYCHIATRY, 1997, 63 (05) :584-589
[37]   Non-recognition of depression and other non-motor symptoms in Parkinson's disease [J].
Shulman, LM ;
Taback, RL ;
Rabinstein, AA ;
Weiner, WJ .
PARKINSONISM & RELATED DISORDERS, 2002, 8 (03) :193-197
[38]   Autonomic dysfunction in Parkinson's disease: a comprehensive symptom survey [J].
Siddiqui, MF ;
Rast, S ;
Lynn, MJ ;
Auchus, AP ;
Pfeiffer, RF .
PARKINSONISM & RELATED DISORDERS, 2002, 8 (04) :277-284
[39]  
SM Halawani, 2002, 13 INT C INT DAT ENG, P516
[40]   Toward a Redefinition of Parkinson's Disease [J].
Stern, Matthew B. ;
Lang, Anthony ;
Poewe, Werner .
MOVEMENT DISORDERS, 2012, 27 (01) :54-60