Classifying Different Stages of Parkinson’s Disease Through Random Forests

Parkinson’s disease (PD) is a progressive, neurodegenerative and age-related disease whose clinical characteristics include both motor and non-motor symptoms. Gait analysis, a three dimensional, non-invasive and computerized analysis of gait, can analyse walking features and carry out spatial and temporal parameters that can be included in machine learning algorithms. Knime analytics platform is employed to implement Random Forests. The aim of the present research is to distinguish De Novo PD patients (patients in early phase, without treatment) and Stable PD patients (patients in intermediate phase, in stable treatment) using spatial and temporal parameters of gait analysis. The dataset consists of 59 people, 32.2% De Novo and 67.8% Stable patients. Results show high accuracy (84.6%) and capacity to detect De Novo patients (94.9% of sensitivity). Recall and precision got high values, too. Despite needing further investigation, this pilot research should encourage health policy and facilities to introduce machine learning techniques and gait analysis in clinical practice. Moreover, results suggest the existence of gait patterns characterizing each phase of Parkinson’s disease.

[1]  R. Crowther,et al.  α-Synuclein in filamentous inclusions of Lewy bodies from Parkinson’s disease and dementia with Lewy bodies , 1998 .

[2]  J. Pearce,et al.  Aetiology and natural history of Parkinson's disease. , 1978, British medical journal.

[3]  Yash Mittra,et al.  Classification of Subjects with Parkinson's Disease Using Gait Data Analysis , 2018, 2018 International Conference on Automation and Computational Engineering (ICACE).

[4]  Liberatina Carmela Santillo,et al.  Use of the AHP methodology in system dynamics: Modelling and simulation for health technology assessments to determine the correct prosthesis choice for hernia diseases. , 2018, Mathematical biosciences.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Jorik Nonnekes,et al.  Unmasking levodopa resistance in Parkinson's disease , 2016, Movement disorders : official journal of the Movement Disorder Society.

[7]  Lynn Rochester,et al.  Progression of gait dysfunction in incident Parkinson's disease: Impact of medication and phenotype , 2015, Movement disorders : official journal of the Movement Disorder Society.

[8]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[9]  Ana Luiza,et al.  Machine learning applications in healthcare , 2020 .

[10]  Saman K. Halgamuge,et al.  Classification of Parkinson's Disease Gait Using Spatial-Temporal Gait Features , 2015, IEEE Journal of Biomedical and Health Informatics.

[11]  Roberto Revetria,et al.  An Innovative Contribution to Health Technology Assessment , 2012, Modern Advances in Intelligent Systems and Tools.

[12]  Maria Romano,et al.  Submovements composition and quality assessment of reaching movements in subjects with Parkinson's Disease , 2015, 2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings.

[13]  Maria Romano,et al.  Lean thinking to improve emergency department throughput at AORN Cardarelli hospital , 2018, BMC Health Services Research.

[14]  Wanda Acampa,et al.  Head-to-head comparison of diagnostic accuracy of stress-only myocardial perfusion imaging with conventional and cadmium-zinc telluride single-photon emission computed tomography in women with suspected coronary artery disease , 2019, Journal of Nuclear Cardiology.

[15]  Mario Cesarelli,et al.  Lean Six Sigma in healthcare , 2019, The TQM Journal.

[16]  Max A. Little,et al.  High accuracy discrimination of Parkinson's disease participants from healthy controls using smartphones , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Maria Triassi,et al.  THE CONDROPROTECTOR ROLE IN THE OSTEOARTHRITIS OF THE KNEE Il ruolo del condroprotettore nell'osteoartrosi del ginocchio , 2013 .

[18]  Patricia Carlson-Kuhta,et al.  Pharmacological treatment in Parkinson's disease: Effects on gait. , 2016, Parkinsonism & related disorders.

[19]  Lynn Rochester,et al.  Decrease in Aβ42 predicts dopa-resistant gait progression in early Parkinson disease , 2017, Neurology.

[20]  Hesham H. Ali,et al.  Machine Learning and Similarity Network Approaches to Support Automatic Classification of Parkinson's Diseases Using Accelerometer-based Gait Analysis , 2019, HICSS.

[21]  Andrea Lee,et al.  Epidemiology of Parkinson Disease. , 2016, Neurologic clinics.

[22]  Paolo Bifulco,et al.  Comparison between clinical and instrumental assessing using Wii Fit system on balance control , 2014, 2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA).

[23]  A. Brunetti,et al.  Machine learning analysis of MRI-derived texture features to predict placenta accreta spectrum in patients with placenta previa. , 2019, Magnetic resonance imaging.

[24]  Maria Romano,et al.  The effects of the vibratory stimulation of the neck muscles for the evaluation of stepping performance in Parkinson's Disease , 2015, 2015 IEEE International Symposium on Medical Measurements and Applications (MeMeA) Proceedings.

[25]  Antonio Pescapè,et al.  Using fuzzy logic for improving clinical daily-care of β-thalassemia patients , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[26]  Maria Romano,et al.  Comparison of measured and predicted reaching movements with a robotic rehabilitation device , 2014, 2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA).

[27]  P. M. Pradhan,et al.  A machine learning approach to distinguish Parkinson’s disease (PD) patient’s with shuffling gait from older adults based on gait signals using 3D motion analysis , 2018, International Journal of Engineering & Technology.