Wearables devices and body sensor networks are attracting most attention for the treatment of chronic diseases of elderly, which need continuous monitoring of the symptoms and adjustment of the therapy. In the Parkinson's Disease (PD) wearables based on inertial sensors can be very useful for performing an objective detection and classification of the motion disorders of different segments of the body. The PI of the present project has been leading a research on this specific topic, which was recipient in 2015 of an international award. The outcomes of that research are the starting point of this proposal. The accuracy of that wearable system based on inertial sensors only can be improved by completing the IMU with the study of the muscle activity. Cramps, muscle contractions, abnormalities in neuromuscular functions and a variety of symptoms related to dyskinesia in the progression of the PD can be studied quantitatively by capturing the muscle activity by surface electromyography (sEMG). The sEMG is a diagnostic technique that detects in real time the muscle activity using patch electrodes properly positioned on the skin along the studied muscle. Today it is performed by the means of cumbersome wired ambulatory equipment, which exhibits electrical artifacts and movement limitations due to wires, and noise at 50 Hz, i.e., in the most meaningful portion of the spectrum. To overcome those problems, here we propose to develop a system aiming to monitoring the motor status of PD patients at home for long time. It integrates in the same board the inertial sensors and algorithms based on inertial data analysis previously developed by the PI, together with sEMG circuits and algorithms for the sEMG data analysis, which are the core of the present project. The novel sensor solution will perform continuous, non-invasive measurements of PD patients conditions with high accuracy, long-time battery autonomy, and small form factor for wearable applications.
Application of ICT and sensor technologies to healthcare is an innovative strategy to treat the diseases which can help doctors in managing specific diseases in all those situations in which the conventional methods of medicine is poorly effective. This is the case of patients who are not in the physical conditions for going frequently to the hospital for outpatient visits, patients living far from the hospitals, patients who need continuous monitoring. In this frame, wearables devices and body sensor networks are attracting most attention for the treatment of chronic diseases of elderly, who need monitoring of the symptoms and adjustment of the therapy. In the first stage of the PD, administration of L-Dopa enables a clear and predictable clinical response. However, in later stages of the disease, the prolonged use of L-Dopa leads to a progressive reduction of efficacy leading to motor complications which become more frequent, intense, disabling, abrupt and unpredictable and expose the patient to bumps, loss of balance and falls, with the disease¿s progression. The clinical management of patients with advanced PD is therefore rather challenging. Unfortunately, PD is characterized by fluctuations in the clinical status that may vary significantly within the same day and between different days.
The innovation of the research is in the use of advanced medical techniques possibly helpful to achieve a long-term monitoring of patient's clinical conditions at home, automatically, objectively, continuously and precisely, which would gain tremendous advances in the management of PD patients in more advanced stages of the disease. Over recent years, novel techniques of movement analysis based on the use of wearable inertial biosensors appeared. However, current technologies based on inertial sensors are not able to discriminate passive and active movements, thus precluding clear identification of pathological muscle activation. Without any information on muscle activation, it is difficult to discriminate voluntary and involuntary movements that commonly lead to motor fluctuation. This can only be achieved by monitoring muscle activity in addition to body movements. The progress respect to the state-of-art is the creation and validation of innovative wearable and wireless technology based on integration of surface electromyography, able to recognize specific voluntary and involuntary movements of the limbs, with inertial sensors, able to monitor gait and movement disorders.
The accuracy of wearable systems based on IMU sensors will be improved by completing the inertial measurements with the study of the muscle activity, so that the clinical condition states will be better classified. The cramps, muscle contractions, abnormalities in neuromuscular functions and a variety of symptoms related to dyskinesia in the progression of the PD will be studied objectively and quantitatively by capturing also the muscle activity by sEMG.
This innovative system will enable a progress for clinicians, who will be able to better assess the motor condition of PD patients and consequently to better manage motor symptoms in advanced PD. The use of our innovative wearable biosensors would improve monitoring of medical treatment and thus obtain a better control with reduction of motor fluctuations, as well as quantify the risk of falls in patients with PD. The automatic remote long-term monitoring of motor symptoms would improve the therapeutic strategy and optimize drug therapy by reducing the overall load of L-Dopa/day.
The goal of avoiding hospitalization and replace it with home monitoring is relevant and is a progress because patients would increase their well-being with an optimized therapy, avoid hospitalization and keep their lifestyle. Finally, the National Health System would save a relevant amount of economic resources with relevant socio-economic advantages.
In conclusion, the proposed system is really innovative and a progress for the elderly healthcare, being a complete system for monitoring the motor status of PD patients at home for long time. It integrates in the same board inertial sensors and algorithms based on inertial data analysis, already developed by the PI of this project, together with sEMG circuits and algorithms for the sEMG data analysis, which are the core of the present project. The novel sensor solution will perform continuous, non-invasive measurements of PD patients conditions with high accuracy, long-time battery autonomy, and small form factor for mobile applications.