Discrimination between healthy and patients with Parkinson’s disease from hand resting activity using inertial measurement unit

Abstract

Background Parkinson’s disease (PD) is a neurological disease that affects the motor system. The associated motor symptoms are muscle rigidity or stiffness, bradykinesia, tremors, and gait disturbances. The correct diagnosis, especially in the initial stages, is fundamental to the life quality of the individual with PD. However, the methods used for diagnosis of PD are still based on subjective criteria. As a result, the objective of this study is the proposal of a method for the discrimination of individuals with PD (in the initial stages of the disease) from healthy groups, based on the inertial sensor recordings. Methods A total of 27 participants were selected, 15 individuals previously diagnosed with PD and 12 healthy individuals. The data collection was performed using inertial sensors (positioned on the back of the hand and on the back of the forearm). Different numbers of features were used to compare the values of sensitivity, specificity, precision, and accuracy of the classifiers. For group classification, 4 classifiers were used and compared, those being [Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Naive Bayes (NB)]. Results When all individuals with PD were analyzed, the best performance for sensitivity and accuracy (0.875 and 0.800, respectively) was found in the SVM classifier, fed with 20% and 10% of the features, respectively, while the best performance for specificity and precision (0.933 and 0.917, respectively) was associated with the RF classifier fed with 20% of all the features. When only individuals with PD and score 1 on the Hoehn and Yahr scale (HY) were analyzed, the best performances for sensitivity, precision and accuracy (0.933, 0.778 and 0.848, respectively) were from the SVM classifier, fed with 40% of all features, and the best result for precision (0.800) was connected to the NB classifier, fed with 20% of all features. Conclusion Through an analysis of all individuals in this study with PD, the best classifier for the detection of PD (sensitivity) was the SVM fed with 20% of the features and the best classifier for ruling out PD (specificity) was the RF classifier fed with 20% of the features. When analyzing individuals with PD and score HY = 1, the SVM classifier was superior across the sensitivity, precision, and accuracy, and the NB classifier was superior in the specificity. The obtained result indicates that objective methods can be applied to help in the evaluation of PD.

Wrist Rigidity Evaluation in Parkinson’s Disease: A Scoping Review

“…Eight studies were included, which are summarized in Table 2 . Inertial sensors were used in four studies [ 41 , 42 , 43 , 44 ], in combination with EMG in one study [ 37 ], and combined with force sensors in two other studies [ 15 , 45 ]. The study [ 46 ] utilized the UPDRS.…”

“…The study [ 46 ] utilized the UPDRS. Three studies applied the evaluation during the DBS surgery [ 41 , 43 , 44 ], and applied a classification model to differentiate rigid and non-rigid states.…”

An Auxiliary Diagnostic System for Parkinson’s Disease Based on Wearable Sensors and Genetic Algorithm Optimized Random Forest

“…Unusable data due to nonstandard action or inappropriate sensor location were removed, and the units of angular velocity were converted from "°/s" to "rad/s". Considering that the complete data of a movement task can better demonstrate the rhythmicity of the movement, thus the data collected for a subject completing one movement task was treated as one window [30], [41], [42]. The remaining sample sizes of PSML, PSMR, and AHM were 200, 200, and 196, respectively.…”

Discriminação do tremor em repouso do punho entre indivíduos com e sem a doença de parkinson por meio de sensores inerciais e classificadores

“…Desta forma, o mesmo paciente pode receber diagnósticos diferentes de diferentes avaliadores. 2017) também não explicam o motivo da escolha por esses classificadores, mas seu uso neste trabalho, pode ser justificado devido à sua presença em diversos outros estudos similares MANSUR et al, 2007;PERES et al, 2021).…”

“…é importante destacar a afirmação de(DE ARAÚJO et al, 2020), onde se coloca ênfase em seu trabalho na comparação de desempenho dos classificadores entre diversos estudos, que devem ser realizados com cuidado, devido às diferenças envolvidas no cálculo das métricas, como os parâmetros dos algoritmos e as características utilizadas. Vale ressaltar mais uma vez que o SVM é mais bem aproveitado quando o número de observações é maior que o número de variáveis, de forma que é possível que um estudo envolvendo mais participantes venha a afetar positivamente seus resultados.Este estudo concorda em parte comPeres et al (2021) que usou os mesmos classificadores para discriminar indivíduos saudáveis de indivíduos com a DP. No estudo de Peres, o classificador SVM sob determinadas circunstâncias obteve a maior acurácia e os pesquisadores também concluíram que métodos objetivos para avaliar os sintomas da DP podem ser usados para ajudar no diagnóstico.…”