Machine Learning Application to Quantify the Tremor Level for Parkinson’s Disease Patients

Pedrosa, Taígo; Vasconcelos, Felipe F.; Medeiros, Leonardo; Silva, Leandro Dias

doi:10.1016/j.procs.2018.10.031

Cited by 17 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The present study observed that mean frequency for both accelerometer and gyroscope sensors, linear prediction coefficients for the accelerometer, and skew power ratio, and the power density skew and kurtosis for the gyroscope frequently figure among the fifteen top features. Frequency domain features have been successfully employed in the machine learning algorithms by other researchers (Bazgir et al, 2018;Pedrosa et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…Literature has proposed alternative ways to quantify PD symptoms in order to assist its diagnosis and progression ( Jilbab et al, 2017 ). Inertial measures of the hand resting tremor associated to machine learning algorithms have been extensively investigated to distinct data from healthy people and patients with PD ( Jeon et al, 2017a , b ), to quantify the progression of the disease ( Pedrosa et al, 2018 ), and to evaluate the effect of therapeutics on hands’ tremor ( LeMoyne et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

“…Several investigations have used a number of machine learning algorithms to classify and/or to quantify the resting hand tremor of patients with PD, obtaining high accuracy levels ( Kostikis et al, 2015 : 78–94%; Jeon et al, 2017a : 80–85%; Pedrosa et al, 2018 : 92.8%). There is no consensus about what machine learning algorithms are preferable to classify features of inertial readings or what are the optimal conditions to use any of the algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hand Resting Tremor Assessment of Healthy and Patients With Parkinson’s Disease: An Exploratory Machine Learning Study

Araújo

Santos

Sá

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hand Resting Tremor Assessment of Healthy and Patients With Parkinson’s Disease: An Exploratory Machine Learning Study

Araújo

Santos

Sá

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…Works that utilized this dataset so far used deep learning to predict different attack stimulations in DBS [34], employed discrete non-Markovian stochastic processes to study the Parkinsonian pathological tremor [16], applied nonlinear analysis to characterize tremor properties as chaotic or stochastic [35], or considered Long-Term Correlations (LTC) and Multifractal (MF) properties to tackle three different classification problems [17]. The Fast Fourier Transform (FFT) [36] and the Power Spectrum (PS) [8] have also been utilized to analyze tremor amplitude and frequency characteristics of resting tremor signals.…”

Section: B Parkinsonian Tremor Characterization and Identification Fr...mentioning

confidence: 99%

Bispectral Analysis of Parkinsonian Rest Tremor: New Characterization and Classification Insights Pre-/Post-DBS and Medication Treatment

Ziogas,

Lamprou,

Hadjileontiadis

2023

IEEE Access

View full text Add to dashboard Cite

Rest tremor is a most common symptom of Parkinson's Disease (PD), with diagnosis and severity estimation often being hindered by subjectivity and limitations of existing methods. Additionally, treatment strategies for PD face challenges in monitoring symptom fluctuations with clinical methods, like the MDS-UPDRS and motor diaries, suffering from subjectivity, limited sensitivity, and infrequent sampling, potentially impacting treatment effectiveness. Hence, methods that can yield explainable biomarkers that accurately describe properties of PD rest tremor, while accounting for the presence of ongoing treatments, such as Deep Brain Stimulation (DBS) and medication, are important for integration in accurate AI-powered wearable systems. To that end, a Higher Order Spectrum (HOS)-based analysis to extract features from index finger velocity recordings of 16 PD patients is proposed. Two different scenarios are implemented for characterizing and classifying treatment (medication/DBS) effectiveness and tremor severity (Low-/High-Amplitude (LAT/HAT)), by means of statistical tests and a leave-one-subject-out cross-validation classification scheme, respectively. The proposed analysis resulted in area under the Receiver Operating Characteristics curve (AUC) score of 0.94 for the Medication treatment classification, 0.71 for the DBS treatment and 0.83 for LAT/HAT prediction. Our results demonstrate that the proposed approach can effectively assess the influence of medication and DBS and recognize rest tremor severity. Finally, our HOS-based methodology enables the establishment of new rest tremor classes, based on its nonlinearity and allows for new insights about the dynamic nature of the resting tremor production system.

show abstract

“…Modelin doğruluğunun elde edilmesi için yinelemelerin ortalaması alınır [29]. Biri dışarda çapraz doğrulamada (leave-one-out cross validation) ise veri kümesindeki bir örnek test verisi olarak, geriye kalan veriler ise eğitim verisi olarak kullanılır [30]. Bu işlem her bir verinin test verisi olarak kullanılmasıyla devam eder ve ortalama hata hesaplanır [31].…”

Section: Model Değerlendirme Yöntemleriunclassified

Hava Araçlarinda Buzlanma Ri̇sk Derecesi̇ni̇n Yapay Zeka İle Tahmi̇n Edi̇lmesi̇

Ateş¹,

Şenol

2021

International Journal of 3D Printing Technologies and Digital Industry

View full text Add to dashboard Cite

Hava araçlarında buzlanma geçmişten günümüze havacılık alanında ciddi problemlerden biridir. Buzlanma hava araçlarının performansını düşürür ve hava aracının hakimiyetinin kaybedilip düşmesine, bunun sonucu olarak ise ölüm ve yaralanmalara sebep olabilir. Literatürde hava aracı üzerinde oluşan buzlanmadan ötürü pek çok kaza meydana gelmiştir ve günümüzde de halen meydana gelmektedir. Hava araçlarında buzlanma probleminin önüne geçebilmek için buz önleme ve buz giderme sistemleri önerilmiştir. Buz önleme ve giderme sistemlerinin doğru zamanda devreye alınıp çıkarılması önem arz eder. Aynı zamanda buz önleme ve giderme sistemlerinin çalıştırılıp kapatılması için buzlanmanın varlığına göre kararı pilota bırakmamakta insan kaynaklı hataların önüne geçmeyi sağlar. Bu çalışmada buzlanma risk derecesinin karar ağaçları algoritması kullanarak tahmin edilmesi gerçekleştirilmiştir. Karar ağacı algoritması hold-out, k kat çapraz doğrulama ve biri dışarda çapraz doğrulama modelleri için kurulmuştur. Hold-out yöntemi için farklı doğrulama verisi oranları kullanılmış, k kat çapraz doğrulama modeli için ise farklı k kat değerleri kullanılmıştır. Sonuçlar performans değerlendirme metriklerinden doğruluk, duyarlılık, kesinlik ve F-ölçütü kullanılarak belirlenmiştir.

show abstract

Machine Learning Application to Quantify the Tremor Level for Parkinson’s Disease Patients

Cited by 17 publications

References 5 publications

Hand Resting Tremor Assessment of Healthy and Patients With Parkinson’s Disease: An Exploratory Machine Learning Study

Hand Resting Tremor Assessment of Healthy and Patients With Parkinson’s Disease: An Exploratory Machine Learning Study

Bispectral Analysis of Parkinsonian Rest Tremor: New Characterization and Classification Insights Pre-/Post-DBS and Medication Treatment

Hava Araçlarinda Buzlanma Ri̇sk Derecesi̇ni̇n Yapay Zeka İle Tahmi̇n Edi̇lmesi̇

Contact Info

Product

Resources

About