Analysis and comparison of sleeping posture classification methods using pressure sensitive bed system

Sleep Position Detection for Closed-Loop Treatment of Sleep-Related Breathing Disorders

Reliable detection of sleep positions is essential for the development of technical aids for patients with position-dependent sleep-related breathing disorders. We compare personalized and generalizable sleeping position classifiers using unobtrusive eight-channel pressure-sensing mats. Data of six male patients with confirmed position-dependent sleep apnea was recorded during three subsequent nights. Personalized position classifiers trained using leave-one-night-out cross-validation on average reached an F1-score of 61.3% for supine/non-supine and an F1-score of 46.2% for supine/lateral-left/lateral-right classification. The generalizable classifiers reached average F1-scores of 62.1% and 49.1% for supine/non-supine and supine/lateral-left/lateral-right classification, respectively. In-bed presence ("bed occupancy") could be detected with an average F1-score of 98.1%. This work shows that personalized sleep-position classifiers trained with data from two nights have comparable performance to classifiers trained with large interpatient datasets. Simple eight-channel sensor mattresses can be used to accurately detect in-bed presence required for closed-loop systems but their use to classify sleep-positions is limited.

A Review of Intelligent Sensor-Based Systems for Pressure Ulcer Prevention

Pressure ulcers are a critical issue not only for patients, decreasing their quality of life, but also for healthcare professionals, contributing to burnout from continuous monitoring, with a consequent increase in healthcare costs. Due to the relevance of this problem, many hardware and software approaches have been proposed to ameliorate some aspects of pressure ulcer prevention and monitoring. In this article, we focus on reviewing solutions that use sensor-based data, possibly in combination with other intrinsic or extrinsic information, processed by some form of intelligent algorithm, to provide healthcare professionals with knowledge that improves the decision-making process when dealing with a patient at risk of developing pressure ulcers. We used a systematic approach to select 21 studies that were thoroughly reviewed and summarized, considering which sensors and algorithms were used, the most relevant data features, the recommendations provided, and the results obtained after deployment. This review allowed us not only to describe the state of the art regarding the previous items, but also to identify the three main stages where intelligent algorithms can bring meaningful improvement to pressure ulcer prevention and mitigation. Finally, as a result of this review and following discussion, we drew guidelines for a general architecture of an intelligent pressure ulcer prevention system.

Exploring a Fuzzy Rule Inferred ConvLSTM for Discovering and Adjusting the Optimal Posture of Patients with a Smart Medical Bed

Several countries nowadays are facing a tough social challenge caused by the aging population. This public health issue continues to impose strain on clinical healthcare, such as the need to prevent terminal patients’ pressure ulcers. Provocative approaches to resolve this issue include health information technology (HIT). In this regard, this paper explores one technological solution based on a smart medical bed (SMB). By integrating a convolutional neural network (CNN) and long-short term memory (LSTM) model, we found this model enhanced performance compared to prior solutions. Further, we provide a fuzzy inferred solution that can control our proposed proprietary automated SMB layout to optimize patients’ posture and mitigate pressure ulcers. Therefore, our proposed SMB can allow autonomous care to be given, helping prevent medical complications when lying down for a long time. Our proposed SMB also helps reduce the burden on primary caregivers in fighting against staff shortages due to public health issues such as the increasing aging population.

Pressure Injury Prevention: A Survey

Pressure injuries are caused by prolonged pressure to an area of the body, which can result in open wounds that descend to the bone. Pressure injuries should not occur in healthcare settings, and yet, they still affect 2.5 million patients in the United States and have an impact on quality of life. Pressure injuries come at a cost of $11 billion in the United States, and 90% of pressure injuries are a secondary condition. In this paper, we survey the literature on preventative techniques to address pressure injures, which we classify into two categories: active prevention strategies and sensor-based risk-factor monitoring. Within each category of techniques, we discuss the literature and assess each class of strategies based on its commercial availability, results of clinical trials when available, the ability for the strategy to save time for healthcare staff, and whether the technique can be tuned to an individual. Based on our findings, the most promising current solutions, supplementary to nursing guidelines, are electrical stimulation, pressure monitoring, and inertial measurement unit monitoring. We also find a need for a clinical software system that can easily integrate with custom sensors, use custom analysis algorithms, and provide visual feedback to the healthcare staff.

Artificial Neural Network for in-Bed Posture Classification Using Bed-Sheet Pressure Sensors

Pressure ulcer prevention is a vital procedure for patients undergoing long-term hospitalization. A human body lying posture (HBLP) monitoring system is essential to reschedule posture change for patients. Video surveillance, the conventional method of HBLP monitoring, suffers from various limitations, such as subject's privacy, and field-of-view obstruction. We propose an autonomous method for classifying the four state-of-the-art HBLPs in healthy adults subjects: supine, prone, left and right lateral, with no sensors or cables attached on the body and no constraints imposed on the subject. Experiments have been conducted on 12 healthy adults (age 27.35 ± 5.39 years) using a collection of textile pressure sensors embedded in a cover placed under the bed sheet. Histogram of oriented gradients and local binary patterns were extracted and fed to a supervised artificial neural network classification model. The model was trained based on the scaled conjugate gradient backpropagation. A nested cross validation with an exhaustive outer validation loop was performed to validate the classification's generalization performance. A high testing prediction accuracy of 97.9% with a Cohen's Kappa coefficient of 97.2% has been interestingly obtained. Prone and supine postures were successfully separated in the classification, in contrast to the majority of previous similar works. We found that using the information of body weight distribution along with the shape and edges contributes to a better classification performance and the ability to separate supine and prone postures. The results are satisfactorily promising toward unobtrusively monitoring posture for ulcer prevention. The method can be used in sleep studies, post-surgical procedures, or applications requiring HBLP identification.

Distinguishing positions and movements in bed from load cell signals

OBJECTIVE

To characterize and classify six positions and movements for individuals in a bed using the output signals of four load cell sensors.

APPROACH

A bed equipped with four load cell sensors and synchronized video was used to assess the load cell response of 54 healthy individuals in prescribed positions and as they moved between positions. Stationary positions were characterized by the signals from the four load cells and the coordinates of the center of mass (CoM). Movements were characterized by the changes in load cell signals, four parameters associated with the trajectory of the CoM between the initial and final position (Euclidean distance, length of the trajectory, and the x- and y- variances), and the initial position's CoM coordinates. Classification and decision tree models were used to assess the ability of these parameters to identify specific positions or movements.

MAIN RESULTS

Six positions were classified with an accuracy of 74.9% and six movements were classified with an accuracy of 79.7%.

SIGNIFICANCE

This study demonstrates the feasibility of distinguishing certain positions and movements with load cell sensors. The identification of positions and movements for individuals in bed can be used as a tool in a variety of clinical settings.

A lightweight sensing platform for monitoring sleep quality and posture: a simulated validation study

Background

The prevalence of self-reported shoulder pain in the UK has been estimated at 16%. This has been linked with significant sleep disturbance. It is possible that this relationship is bidirectional, with both symptoms capable of causing the other. Within the field of sleep monitoring, there is a requirement for a mobile and unobtrusive device capable of monitoring sleep posture and quality. This study investigates the feasibility of a wearable sleep system (WSS) in accurately detecting sleeping posture and physical activity.

Methods

Sixteen healthy subjects were recruited and fitted with three wearable inertial sensors on the trunk and forearms. Ten participants were entered into a ‘Posture’ protocol; assuming a series of common sleeping postures in a simulated bedroom. Five participants completed an ‘Activity’ protocol, in which a triphasic simulated sleep was performed including awake, sleep and REM phases. A combined sleep posture and activity protocol was then conducted as a ‘Proof of Concept’ model. Data were used to train a posture detection algorithm, and added to activity to predict sleep phase. Classification accuracy of the WSS was measured during the simulations.

Results

The WSS was found to have an overall accuracy of 99.5% in detection of four major postures, and 92.5% in the detection of eight minor postures. Prediction of sleep phase using activity measurements was accurate in 97.3% of the simulations. The ability of the system to accurately detect both posture and activity enabled the design of a conceptual layout for a user-friendly tablet application.

Conclusions

The study presents a pervasive wearable sensor platform, which can accurately detect both sleeping posture and activity in non-specialised environments. The extent and accuracy of sleep metrics available advances the current state-of-the-art technology. This has potential diagnostic implications in musculoskeletal pathology and with the addition of alerts may provide therapeutic value in a range of areas including the prevention of pressure sores.

Electronic supplementary material

The online version of this article (10.1186/s40001-018-0326-9) contains supplementary material, which is available to authorized users.

In-bed posture classification using deep autoencoders

Pressure ulcers are high prevalence complications among bed-bound patients which are not only extremely painful and difficult to treat, but also impose a great burden in our health-care system. We target automatic posture detection which is a key module in all pressure ulcer monitoring platforms. Using data collected from a commercially-available pressure mapping system, we applied deep neural networks to automatically classify in-bed posture using features extracted from the histogram of gradient technique. High accuracy of up to 98% was achieved in classifying five different in-bed postures for more than 60,000 pressure images.

Detection of motion and posture change using an IR-UWB radar

Impulse radio ultra-wide band (IR-UWB) radar has recently emerged as a promising candidate for non-contact monitoring of respiration and heart rate. Different studies have reported various radar based algorithms for estimation of these physiological parameters. The radar can be placed under a subject's mattress as he lays stationary on his back or it can be attached to the ceiling directly above the subject's bed. However, advertent or inadvertent movement on part of the subject and different postures can affect the radar returned signal and also the accuracy of the estimated parameters from it. The detection and analysis of these postural changes can not only lead to improvement in estimation algorithms but also towards prevention of bed sores and ulcers in patients who require periodic posture changes. In this paper, we present an algorithm that detects and quantifies different types of motion events using an under-the-mattress IR-UWB radar. The algorithm also indicates a change in posture after a macro-movement event. Based on the findings of this paper, we anticipate that IR-UWB radar can be used for extracting posture related information in non-clinical enviroments for patients who are bed-ridden.

Motion monitoring in palliative care using unobtrusive bed sensors

Palliative care needs are growing with the aging population. Ambient sensors offer patients comfortable and discreet point-of-care monitoring. In this study, two palliative care participants were monitored in a sensorized bed. Motion monitoring by a two-tier gross and fine movement detector provided accurate detection and classification of movement, compared to annotations by an observer. However, ascribing the motion to the patient rather than caregivers or visitors would require supplemental sensors. Motion was indicative of pain, with 13% of time spent moving while in pain versus 3% while not noted as in pain.

Measurement of bed turning and comparison with age, gender, and body mass index in a healthy population: application of a novel mobility detection system

We developed a mobility detection system to analyze pressure changes over time during side-turns in 29 healthy volunteers (17 males and 12 females) with a mean age of 46.1 ± 19.64 years (ranging from 23 to 86 years) in order to determine the effect of gender, age, and BMI on performance during bed postural change. Center of gravity (COG) location, peak pressure of counteraction, and time to reach peak pressure were the main outcomes used to gauge the ability to make a spontaneous side-turn. Men exhibited significantly higher side-turning force (P = 0.002) and back-turning force (P = 0.002) compared with women. Subjects with BMI ≥27 kg/m² had significantly higher side-turning force (P = 0.007) and back-turning force (P = 0.007) compared with those with BMI < 27 kg/m². After adjusting for other covariates, age positively correlated with back-turning time (P = 0.033) and negatively correlated with side-turning speed (P = 0.005), back-turning speed (P = 0.014), side-turning force (P = 0.010), and back-turning force (P = 0.016), respectively. Turning times negatively correlated with time to reach peak pressure (P = 0.008). Our system was effective in detecting changes in turning swiftness in the bed-ridden subject.

An enhanced sensing application based on a flexible projected capacitive-sensing mattress

This paper presents a cost-effective sensor system for mattresses that can classify the sleeping posture of an individual and prevent pressure ulcers. This system applies projected capacitive sensing to the field of health care. The charge time (CT) method was used to sensitively and accurately measure the capacitance of the projected electrodes. The required characteristics of the projected capacitor were identified to develop large-area applications for sensory mattresses. The area of the electrodes, the use of shielding, and the increased length of the transmission line were calibrated to more accurately measure the capacitance of the electrodes in large-size applications. To offer the users comfort in the prone position, a flexible substrate was selected and covered with 16 × 20 electrodes. Compared with the static charge sensitive bed (SCSB), our proposed system-flexible projected capacitive-sensing mattress (FPCSM) comes with more electrodes to increase the resolution of posture identification. As for the body pressure system (BPS), the FPCSM has advantages such as lower cost, higher aging-resistance capability, and the ability to sense the capacitance of the covered regions without physical contact. The proposed guard ring design effectively absorbs the noise and interrupts leakage paths. The projected capacitive electrode is suitable for proximity-sensing applications and succeeds at quickly recognizing the sleeping pattern of the user.

Estimation of body postures on bed using unconstrained ECG measurements

We developed and tested a system for estimating body postures on a bed using unconstrained measurements of electrocardiogram (ECG) signals using 12 capacitively coupled electrodes and a conductive textile sheet. Thirteen healthy subjects participated in the experiment. After detecting the channels in contact with the body among the 12 electrodes, the features were extracted on the basis of the morphology of the QRS (Q wave, R wave, and S wave of ECG) complex using three main steps. The features were applied to linear discriminant analysis, support vector machines with linear and radial basis function (RBF) kernels, and artificial neural networks (one and two layers), respectively. SVM with RBF kernel had the highest performance with an accuracy of 98.4% for estimation of four body postures on the bed: supine, right lateral, prone, and left lateral. Overall, although ECG data were obtained from few sensors in an unconstrained manner, the performance was better than the results that have been reported to date. The developed system and algorithm can be applied to the obstructive apnea detection and analyses of sleep quality or sleep stages, as well as body posture detection for the management of bedsores.

Bed posture classification for pressure ulcer prevention

Pressure ulcer is an age-old problem imposing a huge cost to our health care system. Detecting and keeping record of the patient's posture on bed, help care givers reposition patient more efficiently and reduce the risk of developing pressure ulcer. In this paper, a commercial pressure mapping system is used to create a time-stamped, whole-body pressure map of the patient. An image-based processing algorithm is developed to keep an unobtrusive and informative record of patient's bed posture over time. The experimental results show that proposed algorithm can predict patient's bed posture with up to 97.7% average accuracy. This algorithm could ultimately be used with current support surface technologies to reduce the risk of ulcer development.

Unobtrusive assessment of motor patterns during sleep based on mattress indentation measurements

This study investigates how integrated bed measurements can be used to assess motor patterns (movements and postures) during sleep. An algorithm has been developed that detects movements based on the time derivate of mattress surface indentation. After each movement, the algorithm recognizes the adopted sleep posture based on an image feature vector and an optimal separating hyperplane constructed with the theory of support vector machines. The developed algorithm has been tested on a dataset of 30 fully recorded nights in a sleep laboratory. Movement detection has been compared to actigraphy, whereas posture recognition has been validated with a manual posture scoring based on video frames and chest orientation. Results show a high sensitivity for movement detection (91.2%) and posture recognition (between 83.6% and 95.9%), indicating that mattress indentation provides an accurate and unobtrusive measure to assess motor patterns during sleep.