Sensor-supported Classification of Gait Patterns in Everyday Movement of Patients With Parkinson's Disease

The aim of the study is to collect a database for the development of algorithms for the classification of everyday movement patterns of PD patients with the underlying sensor concepts. From the recorded movement data of PD patients and healthy volunteers (reference basis), characteristic features will be derived which could allow a distinction between pathological and unobtrusive non-disturbed movement patterns (e.g. on/off-state classification) and an assessment of the fall potential.

Study Timeline

The present study will be carried out in three, partly successive stages. The first two stages are measurements with the presented system during a medical examination (or afterwards) under annotation of certain motor exercises to determine the state of health of the patient or test person. In order to generate a sufficient reference database of comparable movement patterns, a series of measurements with subjects of a similar average age is carried out in parallel with the same sensor configuration and the same motor exercises. The third part of the study includes measurements in the home environment of Parkinson's patients. These measurements are used to identify the previously annotated movement patterns in the everyday life of the patient of the same previously included patient group. The individual stages of the study comprise in detail:

1. Acquisition of patients/test persons The voluntary participants of this study will be recruited during the doctor's visit. The group of study participants with PD may consist of both outpatients and inpatients with Parkinson's disease (see also sub-section 4). The group of healthy volunteers is recruited from relatives or acquaintances of the patients or by request of uninvolved persons (in each case without motor impairments, see inclusion/exclusion criteria). If a patient or subject is suitable to participate in the study based on the inclusion and exclusion criteria, he or she will be informed and sign the consent form so that he or she can be included in the study. Each study participant receives an individual identification number, which is used to identify all other patient-specific documents.
2. Annotation Measurements Parkinson Patients As soon as the patients have agreed to voluntarily participate in the study, the current disease status is first determined during a medical examination on the basis of a UPDRS and documented for the study evaluation. Following this, typical exercises for recording motor deficits are carried out. For this purpose, the patient is equipped with the intended sensor system and instructed in its use. The sensor system comprises three different sensor nodes, which are placed around the wrist, as a collar and in the trouser pocket. The wrist sensor is fixed to the patient's wrist by a flexible strap with a Velcro fastener. The neck sensor is positioned under the upper layer of clothing and hung around the neck by means of a special textile collar (approx. 35g). The third sensor knot has no special fastening device and is carried loosely in the trouser pocket. The attachment of the sensors is illustrated in Fig. 1. The movement data are recorded parallel to the exercises and extensively annotated according to the exercise characteristics. The exercises contain typical everyday movement patterns, which are to be identified in the further course of the study in the measurements in the domestic environment (subitem 3) and used for the evaluation of the state of health. These include among others: sit-to-stand test (STS), five-times-sit-to-stand test (5STS), sit-to-walk test (STW) or timed-up-and-go test (TUG), normal walking, climbing stairs, and handwriting.
3. Annotation measurements reference group The volunteers participating in the study will be equipped with the same measuring equipment as the group of Parkinson's patients. The measurements on subjects of comparable average age serve as a reference to physiological movement sequences during the same motor exercises. On the one hand, the aim is to cover as broad a spectrum as possible for the classification of the various movement patterns. On the other hand, the data are to be used to identify pathological features that distinguish them from healthy movement patterns.
4. Movement monitoring in the domestic/clinical environment of patients The group of outpatient/inpatient Parkinson's patients also take part in a long-term measurement in the domestic/clinical environment. Following the first motor examination, 5 consecutive measurements over a longer period of one day each are carried out in this section of the study. The equipment with the required measuring electronics takes place at the patient's place of residence/ in the clinic. In addition to the three previously used sensor nodes, the patient is equipped with a further node for recording on an SD card, which is also carried in the trouser pocket (approx. 35g). The SD card is written using low-level access and an internally developed protocol. This prevents third parties from accessing the transaction data. The measuring equipment is handed over on the morning of the scheduled day by a co-investigator. The patient is equipped with the system and the necessary handling of the sensor nodes is explained over the course of the day. As a daily form dependent annotated reference, the motor exercises mentioned under 2. are repeated - as far as possible in the patient's home environment / in the clinic. The patient is asked to keep an event log of the day at his own discretion and ability. On the evening of the same day, the measuring system is received again on site by a co-investigator. Any complications or questions regarding the further study protocol will be received, documented and, if necessary, reported to the study director.
5. Final motor examination After completion of the third part of the study, each participant undergoes a final medical examination. This will take place following the nearest routine visit. In this examination, the motor exercises are carried out again in order to establish a basis for comparison with the initial situation (UPDRS Trend).