Advanced signal analysis for the detection of periodic limb movements from bilateral ankle actigraphy

Limb accelerations during sleep are related to measures of strength, sensation, and spasticity among individuals with spinal cord injury

BACKGROUND

To evaluate the relationship between measures of neuromuscular impairment and limb accelerations (LA) collected during sleep among individuals with chronic spinal cord injury (SCI) to provide evidence of construct and concurrent validity for LA as a clinically meaningful measure.

METHODS

The strength (lower extremity motor score), sensation (summed lower limb light touch scores), and spasticity (categorized lower limb Modified Ashworth Scale) were measured from 40 adults with chronic (≥ 1 year) SCI. Demographics, pain, sleep quality, and other covariate or confounding factors were measured using self-report questionnaires. Each participant then wore ActiGraph GT9X Link accelerometers on their ankles and wrist continuously for 1-5 days to measure LA from movements during sleep. Regression models with built-in feature selection were used to determine the most relevant LA features and the association to each measure of impairment.

RESULTS

LA features were related to measures of impairment with models explaining 69% and 73% of the variance (R²) in strength and sensation, respectively, and correctly classifying 81.6% (F1-score = 0.814) of the participants into spasticity categories. The most commonly selected LA features included measures of power and frequency (frequency domain), movement direction (correlation between axes), consistency between movements (relation to recent movements), and wavelet energy (signal characteristics). Rolling speed (change in angle of inclination) and movement smoothness (median crossings) were uniquely associated with strength. When LA features were included, an increase of 72% and 222% of the variance was explained for strength and sensation scores, respectively, and there was a 34% increase in spasticity classification accuracy compared to models containing only covariate features such as demographics, sleep quality, and pain.

CONCLUSION

LA features have shown evidence of having construct and concurrent validity, thus demonstrating that LA are a clinically-relevant measure related to lower limb strength, sensation, and spasticity after SCI. LA may be useful as a more detailed measure of impairment for applications such as clinical prediction models for ambulation.

Assessment of Sleep Duration and Number of Awakenings Based on Ankle and Wrist Actigraphy in Medical Hospitalized Older Patients

BACKGROUND

Most studies performed in the hospital assess sleep using self-reports; few rely on actigraphy. Although wrist actigraphy is commonly used for sleep assessment in field studies, in-hospital assessment may be challenging and cumbersome because other more necessary monitoring devices are often attached to patients' upper limbs; these may affect interpretation of wrist activity data. Placement on the ankle may be a viable solution.

OBJECTIVE

To compare total sleep time (TST) and number of awakenings (NOA) using concomitant wrist and ankle actigraphy, as well as self-reports in a sample of older adult patients hospitalized in medical units.

METHODS

This was a prospective observational study. Objective sleep data were collected using ankle and wrist actigraphy, and subjective data using sleep diary. Repeated measures mixed model analysis was performed, adjusting for age, gender, sleep medications, symptoms severity, interaction between types of measure, and night number.

RESULTS

Twenty-one older adults (65+) wore ankle and wrist actigraphy devices and subjectively estimated sleep parameters for an average of (2.15 ± 1.01) nights, with 40 nights available for analysis. TST was lower for wrist than ankle actigraphy (F_(2,87) = 7.92, p = .0007). Neither differed from self-reports. NOA differed between all types of measure (ankle, 8.58 ± 6.66; wrist, 15.49 ± 7.47; self-report, 1.81 ± 1.83; F_(2,85) = 47.66, p < .001). No significant within-subject variations and no interaction between devices and repeated measures were found.

CONCLUSIONS

Despite differences between ankle and wrist assessments, all three methods provided consistent TST estimation within participants. Findings provide preliminary support for the use of ankle actigraphy for sleep assessment in hospital settings.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Accelerometer-measured physical activity and its impact on sleep quality in patients suffering from restless legs syndrome

BACKGROUND

The primary symptoms of restless legs syndrome (RLS) are sleep onset insomnia and difficulty to maintain sleep. Previous studies have shown that regular physical activity can reduce the risk of developing RLS. However, the relationship between physical activity and sleep quality parameters in individuals suffering from RLS has not yet been investigated by applying accelerometry. Thus, the present study investigates the impact of physical activity (measuring both intensity levels and duration of physical activity) during the day (7-12 h, 12-18 h, 18-23 h) on sleep quality in patients suffering from idiopathic RLS by applying a real-time approach.

METHODS

In a sample of 47 participants suffering from idiopathic RLS, physical activity and sleep quality were measured over one week using accelerometers. For data analysis, physical activity levels and step counts during three periods of the day (morning, afternoon, evening) were correlated with sleep quality parameters of the subsequent night.

RESULTS

This observational study revealed that in most instances physical activity was not correlated with sleep parameters (two exceptions exist: steps taken in the morning were negatively correlated with periodic leg movements during sleep, and physical activity in the evening was negatively correlated with total sleep time). The physical activity levels of the participants in this study, however, were unexpectedly high compared to population-level data and variance in physical activity was low. The average activity was 13,817 (SD = 4086) steps and 347 (SD = 117) minutes of moderate physical activity per day in females, and 10,636 (SD = 3748) steps and 269 (SD = 69) minutes of moderate physical activity in males, respectively. Participants did not engage in any vigorous physical activity.

CONCLUSIONS

Further interventional studies are needed to investigate the daily effects of different intensities of physical activity on RLS symptoms.

Actigraphic detection of periodic limb movements: development and validation of a potential device-independent algorithm. A proof of concept study

STUDY OBJECTIVES

We propose a unique device-independent approach to analyze long-term actigraphy signals that can accurately quantify the severity of periodic limb movements in sleep (PLMS).

METHODS

We analyzed 6-8 hr of bilateral ankle actigraphy data for 166 consecutively consenting patients who simultaneously underwent routine clinical polysomnography. Using the proposed algorithm, we extracted 14 time and frequency features to identify PLMS. These features were then used to train a Naïve-Bayes learning tool which permitted classification of mild vs. severe PLMS (i.e. periodic limb movements [PLM] index less than vs. greater than 15 per hr), as well as classification for four PLM severities (i.e. PLM index < 15, between 15 and 29.9, between 30 and 49.9, and ≥50 movements per hour).

RESULTS

Using the proposed signal analysis technique, coupled with a leave-one-out cross-validation method, we obtained a classification accuracy of 89.6%, a sensitivity of 87.9%, and a specificity of 94.1% when classifying a PLM index less than vs. greater than 15 per hr. For the multiclass classification for the four PLM severities, we obtained a classification accuracy of 85.8%, with a sensitivity of 97.6%, and a specificity of 84.8%.

CONCLUSIONS

Our approach to analyzing long-term actigraphy data provides a method that can be used as a screening tool to detect PLMS using actigraphy devices from various manufacturers and will facilitate detection of PLMS in an ambulatory setting.

A Device-Independent Efficient Actigraphy Signal-Encoding System for Applications in Monitoring Daily Human Activities and Health

Actigraphs for personalized health and fitness monitoring is a trending niche market and fit aptly in the Internet of Medical Things (IoMT) paradigm. Conventionally, actigraphy is acquired and digitized using standard low pass filtering and quantization techniques. High sampling frequencies and quantization resolution of various actigraphs can lead to memory leakage and unwanted battery usage. Our systematic investigation on different types of actigraphy signals yields that lower levels of quantization are sufficient for acquiring and storing vital movement information while ensuring an increase in SNR, higher space savings, and in faster time. The objective of this study is to propose a low-level signal encoding method which could improve data acquisition and storage in actigraphs, as well as enhance signal clarity for pattern classification. To further verify this study, we have used a machine learning approach which suggests that signal encoding also improves pattern recognition accuracy. Our experiments indicate that signal encoding at the source results in an increase in SNR (signal-to-noise ratio) by at least 50⁻90%, coupled with a bit rate reduction by 50⁻80%, and an overall space savings in the range of 68⁻92%, depending on the type of actigraph and application used in our study. Consistent improvements by lowering the quantization factor also indicates that a 3-bit encoding of actigraphy data retains most prominent movement information, and also results in an increase of the pattern recognition accuracy by at least 10%.

Integrated Signal Encoding and Analysis System for Actigraphy-based Long-term Monitoring of Periodic Limb Movements in Sleep

There has been a boom in the development of wearable devices for wellness and healthcare applications. Numerous studies have been conducted on the utility of employing wearable devices for the long-term monitoring of biosignals. Despite their efficacy, the potential for practical implementation faces many hurdles such as memory usage, power consumption, denoising, and efficient data transmission. Of the many wearables being used, the actigraph has been a popular choice amongst experts for identifying motion abnormalities such as periodic leg movements (PLMs) in sleep and the activities of patients suffering from various medical illnesses. In this paper, we present an efficient pulse code modulation based, 3-bit, signal encoding technique, which when applied to long-term (6-8 hours), 16-bit sleep actigraphy signals, generates 3-bit encoded, accelerometry data with an average compression ratio of 92%, an average increase in the signal-to-noise (SNR) ratio by 20 dB and an average reduction of memory usage by 92%. The proposed technique also eliminates the need to apply filters for denoising, by retaining only characteristic signal information in the quantized version. The proposed technique, in general, could be applied to accelerometer-based wearables and has the potential to provide efficient memory and power usage in long-term monitoring applications.

Calibrating actigraphy to improve sleep efficiency estimates

Actigraphy (ACT) can enhance treatment for insomnia by providing objective estimates of sleep efficiency; however, only two studies have assessed the accuracy of actigraphy-based estimates of sleep efficiency (ACT-SE) in sleep-disordered samples studied at home. Both found poor correspondence with polysomnography-based estimates (PSG-SE). The current study tested that concordance in a third sample and piloted a method for improving ACT-SE. Participants in one of four diagnostic categories (panic disorder, post-traumatic stress disorder, comorbid post-traumatic stress and panic disorder and controls without sleep complaints) underwent in-home recording of sleep using concurrent ambulatory PSG and actigraphy. Precisely synchronized PSG and ACT recordings were obtained from 41 participants. Sleep efficiency was scored independently using conventional methods, and ACT-SE/PSG-SE concordance examined. Next, ACT data recorded initially at 0.5 Hz were resampled to 30-s epochs and rescaled on a per-participant basis to yield optimized concordance between PSG- and ACT-based sleep efficiency estimates. Using standard scoring of ACT, the correlation between ACT-SE and PSG-SE across participants was statistically significant (r = 0.35, P < 0.025), although ACT-SE failed to replicate a main effect of diagnosis. Individualized calibration of ACT against a night of PSG yielded a significantly higher correlation between ACT-SE and PSG-SE (r = 0.65, P < 0.001; z = 1.692, P = 0.0452, one-tailed) and a significant main effect of diagnosis that was highly correspondent with the effect on PSG-SE. ACT-based estimates of sleep efficiency in sleep-disordered patients tested at home can be improved significantly by calibration against a single night of concurrent PSG.