Preliminary results of ON/OFF detection using an integrated system for Parkinson's disease monitoring

Abstract

Abstract-This paper describes the experimental set up of a system composed by a set of wearable sensors devices for the recording of the motion signals and software algorithms for the signal analysis. This system is able to automatically detect and assess the severity of bradykinesia, tremor, dyskinesia and akinesia motor symptoms. Based on the assessment of the akinesia, the ON-OFF status of the patient is determined for each moment. The assessment performed through the automatic evaluation of the akinesia is compared with the status reported by the patients in their diaries. Preliminary results with a total recording period of 32 hours with two PD patients are presented, where a good correspondence (88.2 +/-3.7 %) was observed. Best (93.7%) and worst (87%) correlation results are illustrated, together with the analysis of the automatic assessment of the akinesia symptom leading to the status determination. The results obtained are promising, and if confirmed with further data, this automatic assessment of PD motor symptoms will lead to a better adjustment of medication dosages and timing, cost savings and an improved quality of life of the patients.

Assessing Motor Fluctuations in Parkinson’s Disease Patients Based on a Single Inertial Sensor

“…Similarly, the work of Keijsers et al and Patel et al was performed with several inertial systems, being very cumbersome for patients [21]. Finally, it is difficult to compare the results obtained in this work with the one presented by Pastorino et al in 2013, in which only two patients performed the test obtaining a 88.2% of correspondence between patient’s diary and ON/OFF phases identified by the system [41]. …”

“…In addition, in another set of signals obtained from 24 PD patients at home during 7 days, the same method was applied, obtaining an error rate of 25.6% ± 14.9%. As part of the PERFORM project as well, Pastorino et al [41] presented a preliminary result of the PERFORM project where a correlation between the algorithms developed in the project and motor states in two patients were reported. In this paper, the algorithms used were not specified and also the resulting specificity and sensitivity values are not available, only data correlation between the system output and patients’ diary were offered (88.2% ± 3.7%).…”

High-Resolution Motor State Detection in Parkinson’s Disease Using Convolutional Neural Networks

“…Most research on this topic has been undertaken under laboratory conditions, and only a few researchers have addressed the measurement of motor fluctuations in a free-living setting, e.g. 16,17,[22][23][24][25][26][27][28][29] . While relevant progress has been shown for sensor technologies and data analyses, the critical issue of validation has not been convincingly answered [30][31][32] .…”

A holistic approach to assess the feasability of telehealth for Parkinson's disease management

“…A step forward requires the exploration of performing the assessment of PD patient on unsupervised environments. Part of the work presented in this chapter, including figures and tables, have been already published in Cancela et al [482] as well as in the proceedings of several international conferences [1], [3], [5], [8]- [10], [12], [14]- [16], [531].…”

“…Finally, the definition of the Approximate Entropy presents a different formulation ( 12 ) and ( 13 ) The features were used in 12 different combinations: SampEn+Range, rms+ApEn+Range, xcorr+SampEn+Range, xcorr+ApEn+range, rms+range, xcorr+range, rms+ApEn, rms+SampEn, xcorr+ApEn, xcorr+SampEn, range+ApEn and Range+SampEn. Once the features were calculated each epoch was tagged with the clinical assessment (in this case the question 31 of the UPRDS was used as gold standard for the assessment of the bradykinesia in PD patients) and finally these tagged epochs were used to train and test different classifiers.…”