Gait Detection from a Wrist-Worn Sensor Using Machine Learning Methods: A Daily Living Study in Older Adults and People with Parkinson's Disease

In-Clinic and Natural Gait Observations master protocol (I-CAN-GO) to validate gait using a lumbar accelerometer

Traditional measurements of gait are typically performed in clinical or laboratory settings where functional assessments are used to collect episodic data, which may not reflect naturalistic gait and activity patterns. The emergence of digital health technologies has enabled reliable and continuous representation of gait and activity in free-living environments. To provide further evidence for naturalistic gait characterization, we designed a master protocol to validate and evaluate the performance of a method for measuring gait derived from a single lumbar-worn accelerometer with respect to reference methods. This evaluation included distinguishing between participants' self-perceived different gait speed levels, and effects of different floor surfaces such as carpet and tile on walking performance, and performance under different bouts, speed, and duration of walking during a wide range of simulated daily activities. Using data from 20 healthy adult participants, we found different self-paced walking speeds and floor surface effects can be accurately characterized. Furthermore, we showed accurate representation of gait and activity during simulated daily living activities and longer bouts of outside walking. Participants in general found that the devices were comfortable. These results extend our previous validation of the method to more naturalistic setting and increases confidence of implementation at-home.

Assisted technology in Parkinson's disease gait: what's up?

BACKGROUND

 Gait disturbances are prevalent and debilitating symptoms, diminishing mobility and quality of life for Parkinson's disease (PD) individuals. While traditional treatments offer partial relief, there is a growing interest in alternative interventions to address this challenge. Recently, a remarkable surge in assisted technology (AT) development was witnessed to aid individuals with PD.

OBJECTIVE

 To explore the burgeoning landscape of AT interventions tailored to alleviate PD-related gait impairments and describe current research related to such aim.

METHODS

 In this review, we searched on PubMed for papers published in English (2018-2023). Additionally, the abstract of each study was read to ensure inclusion. Four researchers searched independently, including studies according to our inclusion and exclusion criteria.

RESULTS

 We included studies that met all inclusion criteria. We identified key trends in assistive technology of gait parameters analysis in PD. These encompass wearable sensors, gait analysis, real-time feedback and cueing techniques, virtual reality, and robotics.

CONCLUSION

 This review provides a resource for guiding future research, informing clinical decisions, and fostering collaboration among researchers, clinicians, and policymakers. By delineating this rapidly evolving field's contours, it aims to inspire further innovation, ultimately improving the lives of PD patients through more effective and personalized interventions.

Real-World Gait Detection Using a Wrist-Worn Inertial Sensor: Validation Study

BACKGROUND

Wrist-worn inertial sensors are used in digital health for evaluating mobility in real-world environments. Preceding the estimation of spatiotemporal gait parameters within long-term recordings, gait detection is an important step to identify regions of interest where gait occurs, which requires robust algorithms due to the complexity of arm movements. While algorithms exist for other sensor positions, a comparative validation of algorithms applied to the wrist position on real-world data sets across different disease populations is missing. Furthermore, gait detection performance differences between the wrist and lower back position have not yet been explored but could yield valuable information regarding sensor position choice in clinical studies.

OBJECTIVE

The aim of this study was to validate gait sequence (GS) detection algorithms developed for the wrist position against reference data acquired in a real-world context. In addition, this study aimed to compare the performance of algorithms applied to the wrist position to those applied to lower back-worn inertial sensors.

METHODS

Participants with Parkinson disease, multiple sclerosis, proximal femoral fracture (hip fracture recovery), chronic obstructive pulmonary disease, and congestive heart failure and healthy older adults (N=83) were monitored for 2.5 hours in the real-world using inertial sensors on the wrist, lower back, and feet including pressure insoles and infrared distance sensors as reference. In total, 10 algorithms for wrist-based gait detection were validated against a multisensor reference system and compared to gait detection performance using lower back-worn inertial sensors.

RESULTS

The best-performing GS detection algorithm for the wrist showed a mean (per disease group) sensitivity ranging between 0.55 (SD 0.29) and 0.81 (SD 0.09) and a mean (per disease group) specificity ranging between 0.95 (SD 0.06) and 0.98 (SD 0.02). The mean relative absolute error of estimated walking time ranged between 8.9% (SD 7.1%) and 32.7% (SD 19.2%) per disease group for this algorithm as compared to the reference system. Gait detection performance from the best algorithm applied to the wrist inertial sensors was lower than for the best algorithms applied to the lower back, which yielded mean sensitivity between 0.71 (SD 0.12) and 0.91 (SD 0.04), mean specificity between 0.96 (SD 0.03) and 0.99 (SD 0.01), and a mean relative absolute error of estimated walking time between 6.3% (SD 5.4%) and 23.5% (SD 13%). Performance was lower in disease groups with major gait impairments (eg, patients recovering from hip fracture) and for patients using bilateral walking aids.

CONCLUSIONS

Algorithms applied to the wrist position can detect GSs with high performance in real-world environments. Those periods of interest in real-world recordings can facilitate gait parameter extraction and allow the quantification of gait duration distribution in everyday life. Our findings allow taking informed decisions on alternative positions for gait recording in clinical studies and public health.

TRIAL REGISTRATION

ISRCTN Registry 12246987; https://www.isrctn.com/ISRCTN12246987.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2021-050785.

Can Gait Characteristics Be Represented by Physical Activity Measured with Wrist-Worn Accelerometers?

Wearable accelerometers allow for continuous monitoring of function and behaviors in the participant's naturalistic environment. Devices are typically worn in different body locations depending on the concept of interest and endpoint under investigation. The lumbar and wrist are commonly used locations: devices placed at the lumbar region enable the derivation of spatio-temporal characteristics of gait, while wrist-worn devices provide measurements of overall physical activity (PA). Deploying multiple devices in clinical trial settings leads to higher patient burden negatively impacting compliance and data quality and increases the operational complexity of the trial. In this work, we evaluated the joint information shared by features derived from the lumbar and wrist devices to assess whether gait characteristics can be adequately represented by PA measured with wrist-worn devices. Data collected at the Pfizer Innovation Research (PfIRe) Lab were used as a real data example, which had around 7 days of continuous at-home data from wrist- and lumbar-worn devices (GENEActiv) obtained from a group of healthy participants. The relationship between wrist- and lumbar-derived features was estimated using multiple statistical methods, including penalized regression, principal component regression, partial least square regression, and joint and individual variation explained (JIVE). By considering multilevel models, both between- and within-subject effects were taken into account. This work demonstrated that selected gait features, which are typically measured with lumbar-worn devices, can be represented by PA features measured with wrist-worn devices, which provides preliminary evidence to reduce the number of devices needed in clinical trials and to increase patients' comfort. Moreover, the statistical methods used in this work provided an analytic framework to compare repeated measures collected from multiple data modalities.

Classifying Tremor Dominant and Postural Instability and Gait Difficulty Subtypes of Parkinson's Disease from Full-Body Kinematics

Characterizing motor subtypes of Parkinson's disease (PD) is an important aspect of clinical care that is useful for prognosis and medical management. Although all PD cases involve the loss of dopaminergic neurons in the brain, individual cases may present with different combinations of motor signs, which may indicate differences in underlying pathology and potential response to treatment. However, the conventional method for distinguishing PD motor subtypes involves resource-intensive physical examination by a movement disorders specialist. Moreover, the standardized rating scales for PD rely on subjective observation, which requires specialized training and unavoidable inter-rater variability. In this work, we propose a system that uses machine learning models to automatically and objectively identify some PD motor subtypes, specifically Tremor-Dominant (TD) and Postural Instability and Gait Difficulty (PIGD), from 3D kinematic data recorded during walking tasks for patients with PD (MDS-UPDRS-III Score, 34.7 ± 10.5, average disease duration 7.5 ± 4.5 years). This study demonstrates a machine learning model utilizing kinematic data that identifies PD motor subtypes with a 79.6% F1 score (N = 55 patients with parkinsonism). This significantly outperformed a comparison model using classification based on gait features (19.8% F1 score). Variants of our model trained to individual patients achieved a 95.4% F1 score. This analysis revealed that both temporal, spectral, and statistical features from lower body movements are helpful in distinguishing motor subtypes. Automatically assessing PD motor subtypes simply from walking may reduce the time and resources required from specialists, thereby improving patient care for PD treatments. Furthermore, this system can provide objective assessments to track the changes in PD motor subtypes over time to implement and modify appropriate treatment plans for individual patients as needed.

Physical Activity in Community-Dwelling Older Adults: Which Real-World Accelerometry Measures Are Robust? A Systematic Review

Measurement of real-world physical activity (PA) data using accelerometry in older adults is informative and clinically relevant, but not without challenges. This review appraises the reliability and validity of accelerometry-based PA measures of older adults collected in real-world conditions. Eight electronic databases were systematically searched, with 13 manuscripts included. Intraclass correlation coefficient (ICC) for inter-rater reliability were: walking duration (0.94 to 0.95), lying duration (0.98 to 0.99), sitting duration (0.78 to 0.99) and standing duration (0.98 to 0.99). ICCs for relative reliability ranged from 0.24 to 0.82 for step counts and 0.48 to 0.86 for active calories. Absolute reliability ranged from 5864 to 10,832 steps and for active calories from 289 to 597 kcal. ICCs for responsiveness for step count were 0.02 to 0.41, and for active calories 0.07 to 0.93. Criterion validity for step count ranged from 0.83 to 0.98. Percentage of agreement for walking ranged from 63.6% to 94.5%; for lying 35.6% to 100%, sitting 79.2% to 100%, and standing 38.6% to 96.1%. Construct validity between step count and criteria for moderate-to-vigorous PA was rs = 0.68 and 0.72. Inter-rater reliability and criterion validity for walking, lying, sitting and standing duration are established. Criterion validity of step count is also established. Clinicians and researchers may use these measures with a limited degree of confidence. Further work is required to establish these properties and to extend the repertoire of PA measures beyond "volume" counts to include more nuanced outcomes such as intensity of movement and duration of postural transitions.

Correlates of Person-Specific Rates of Change in Sensor-Derived Physical Activity Metrics of Daily Living in the Rush Memory and Aging Project

This study characterized person-specific rates of change of total daily physical activity (TDPA) and identified correlates of this change. TDPA metrics were extracted from multiday wrist-sensor recordings from 1083 older adults (average age 81 years; 76% female). Thirty-two covariates were collected at baseline. A series of linear mixed-effect models were used to identify covariates independently associated with the level and annual rate of change of TDPA. Though, person-specific rates of change varied during a mean follow-up of 5 years, 1079 of 1083 showed declining TDPA. The average decline was 16%/year, with a 4% increased rate of decline for every 10 years of age older at baseline. Following variable selection using multivariate modeling with forward and then backward elimination, age, sex, education, and 3 of 27 non-demographic covariates including motor abilities, a fractal metric, and IADL disability remained significantly associated with declining TDPA accounting for 21% of its variance (9% non-demographic and 12% demographics covariates). These results show that declining TDPA occurs in many very old adults. Few covariates remained correlated with this decline and the majority of its variance remained unexplained. Further work is needed to elucidate the biology underlying TDPA and to identify other factors that account for its decline.

The role of wrist-worn technology in the management of Parkinson's disease in daily life: A narrative review

Parkinson's disease (PD) is a neurodegenerative disorder that affects millions of people worldwide. Its slow and heterogeneous progression over time makes timely diagnosis challenging. Wrist-worn digital devices, particularly smartwatches, are currently the most popular tools in the PD research field due to their convenience for long-term daily life monitoring. While wrist-worn sensing devices have garnered significant interest, their value for daily practice is still unclear. In this narrative review, we survey demographic, clinical and technological information from 39 articles across four public databases. Wrist-worn technology mainly monitors motor symptoms and sleep disorders of patients in daily life. We find that accelerometers are the most commonly used sensors to measure the movement of people living with PD. There are few studies on monitoring the disease progression compared to symptom classification. We conclude that wrist-worn sensing technology might be useful to assist in the management of PD through an automatic assessment based on patient-provided daily living information.