Role of arm reaching movement kinematics in friction perception at initial contact with smooth surfaces

When manipulating objects, humans begin adjusting their grip force to friction within 100 ms of contact. During motor adaptation, subjects become aware of the slipperiness of touched surfaces. Previously, we have demonstrated that humans cannot perceive frictional differences when surfaces are brought in contact with an immobilised finger, but can do so when there is submillimeter lateral displacement or subjects actively make the contact movement. Similarly, in, we investigated how humans perceive friction in the absence of intentional exploratory sliding or rubbing movements, to mimic object manipulation interactions. We used a two-alternative forced-choice paradigm in which subjects had to reach and touch one surface followed by another, and then indicate which felt more slippery. Subjects correctly identified the more slippery surface in 87 ± 8% of cases (mean ± SD; n = 12). Biomechanical analysis of finger pad skin displacement patterns revealed the presence of tiny (<1 mm) localised slips, known to be sufficient to perceive frictional differences. We tested whether these skin movements arise as a result of natural hand reaching kinematics. The task was repeated with the introduction of a hand support, eliminating the hand reaching movement and minimising fingertip movement deviations from a straight path. As a result, our subjects' performance significantly declined (66 ± 12% correct, mean ± SD; n = 12), suggesting that unrestricted reaching movement kinematics and factors such as physiological tremor, play a crucial role in enhancing or enabling friction perception upon initial contact. KEY POINTS: More slippery objects require a stronger grip to prevent them from slipping out of hands. Grip force adjustments to friction driven by tactile sensory signals are largely automatic and do not necessitate cognitive involvement; nevertheless, some associated awareness of grip surface slipperiness under such sensory conditions is present and helps to select a safe and appropriate movement plan. When gripping an object, tactile receptors provide frictional information without intentional rubbing or sliding fingers over the surface. However, we have discovered that submillimeter range lateral displacement might be required to enhance or enable friction sensing. The present study provides evidence that such small lateral movements causing localised partial slips arise and are an inherent part of natural reaching movement kinematics.

Energy-Efficient Sleep Apnea Detection Using a Hyperdimensional Computing Framework Based on Wearable Bracelet Photoplethysmography

OBJECTIVE

Sleep apnea syndrome (SAS) is a common sleep disorder, which has been shown to be an important contributor to major neurocognitive and cardiovascular sequelae. Considering current diagnostic strategies are limited with bulky medical devices and high examination expenses, a large number of cases go undiagnosed. To enable large-scale screening for SAS, wearable photoplethysmography (PPG) technologies have been used as an early detection tool. However, existing algorithms are energy-intensive and require large amounts of memory resources, which are believed to be the major drawbacks for further promotion of wearable devices for SAS detection.

METHODS

In this paper, an energy-efficient method of SAS detection based on hyperdimensional computing (HDC) is proposed. Inspired by the phenomenon of chunking in cognitive psychology as a memory mechanism for improving working memory efficiency, we proposed a one-dimensional block local binary pattern (1D-BlockLBP) encoding scheme combined with HDC to preserve dominant dynamical and temporal characteristics of pulse rate signals from wearable PPG devices.

RESULTS

Our method achieved 70.17% accuracy in sleep apnea segment detection, which is comparable with traditional machine learning methods. Additionally, our method achieves up to 67× lower memory footprint, 68× latency reduction, and 93× energy saving on the ARM Cortex-M4 processor.

CONCLUSION

The simplicity of hypervector operations in HDC and the novel 1D-BlockLBP encoding effectively preserve pulse rate signal characteristics with high computational efficiency.

SIGNIFICANCE

This work provides a scalable solution for long-term home-based monitoring of sleep apnea, enhancing the feasibility of consistent patient care.

Open-Source Instrumented Object to Study Dexterous Object Manipulation

Humans use tactile feedback to perform skillful manipulation. When tactile sensory feedback is unavailable, for instance, if the fingers are anesthetized, dexterity is severely impaired. Imaging the deformation of the finger pad skin when in contact with a transparent plate provides information about the tactile feedback received by the central nervous system. Indeed, skin deformations are transduced into neural signals by the mechanoreceptors of the finger pad skin. Understanding how this feedback is used for active object manipulation would improve our understanding of human dexterity. In this paper, we present a new device for imaging the skin of the finger pad of one finger during manipulation performed with a precision grip. The device's mass (300 g) makes it easy to use during unconstrained dexterous manipulation. Using this device, we reproduced the experiment performed in Delhaye et al. (2021) We extracted the strains aligned with the object's movement, i.e., the vertical strains in the ulnar and radial parts of the fingerpad, to see how correlated they were with the grip force (GF) adaptation. Interestingly, parts of our results differed from those in Delhaye et al. (2021) due to weight and inertia differences between the devices, with average GF across participants differing significantly. Our results highlight a large variability in the behavior of the skin across participants, with generally low correlations between strain and GF adjustments, suggesting that skin deformations are not the primary driver of GF adaptation in this manipulation scenario.

Design, Fabrication, and Characterization of a Novel Optical Six-Axis Distributed Force and Displacement Tactile Sensor for Dexterous Robotic Manipulation

Real-time multi-axis distributed tactile sensing is a critical capability if robots are to perform stable gripping and dexterous manipulation, as it provides crucial information about the sensor-object interface. In this paper, we present an optical-based six-axis tactile sensor designed in a fingertip shape for robotic dexterous manipulation. The distributed sensor can precisely estimate the local XYZ force and displacement at ten distinct locations and provide the global XYZ force and torque measurements. Its compact size, comparable to that of a human thumb, and minimal thickness allow seamless integration onto existing robotic fingers, eliminating the need for complex modifications to the gripper. The proposed sensor design uses a simple, low-cost fabrication method. Moreover, the optical transduction approach uses light angle and intensity sensing to infer force and displacement from deformations of the individual sensing units that form the overall sensor, providing distributed six-axis sensing. The local force precision at each sensing unit in the X, Y, and Z axes is 20.89 mN, 19.19 mN, and 43.22 mN, respectively, over a local force range of approximately ±1.5 N in X and Y and 0 to -2 N in Z. The local displacement precision in the X, Y, and Z axes is 56.70 μm, 50.18 μm, and 13.83 μm, respectively, over a local displacement range of ±2 mm in the XY directions and 0 to -1.5 mm in Z (i.e., compression). Additionally, the sensor can measure global torques, Tx, Ty, and Tz, with a precision of of 1.90 N-mm, 1.54 N-mm, and 1.26 N-mm, respectively. The fabricated design is showcased by integrating it with an OnRobot RG2 gripper and illustrating real-time measurements during in simple demonstration task, which generated changing global forces and torques.

Automatic Segmentation of the Paediatric Femoral Head

Developmental dysplasia of the hip (DDH) is a developmental deformity occurring in 0.1-3.4% of infants. Timely surgical intervention can ameliorate the condition in stable hips and reduce future cases of osteoarthritis and total hip replacement. However, current definitions of DDH are subjective, and thus would benefit from a more objective and reliable assessment metric. Since the shape of the femoral head and its congruence with the acetabulum are disrupted by DDH, analysis of the femoral head could potentially play a role in the development of novel objective morphological metric for stable DDH. Therefore, this paper aimed to segment the paediatric femoral head in stable hips from radiographs, which has not been attempted before in the chosen focus age group (1-16 years) where the pelvis and hip joint undergo significant development. Two techniques were compared against a baseline U-Net: data augmentation and region-of-interest (ROI) networks. Four models were developed either without, with just one, or with both techniques. Evaluated using tenfold cross-validation, the U-Net trained with both techniques achieved the best results, with a Dice Similarity Coefficient (DSC) of 0.951±0.037 (mean ± standard deviation, calculated with 720 images). Future work will use this segmentation algorithm to accurately characterise hip joint morphology and estimate the benefit of early surgical intervention in DDH.

Biomechanics of the finger pad in response to torsion

Surface skin deformation of the finger pad during partial slippage at finger-object interfaces elicits firing of the tactile sensory afferents. A torque around the contact normal is often present during object manipulation, which can cause partial rotational slippage. Until now, studies of surface skin deformation have used stimuli sliding rectilinearly and tangentially to the skin. Here, we study surface skin dynamics under pure torsion of the right index finger of seven adult participants (four males). A custom robotic platform stimulated the finger pad with a flat clean glass surface, controlling the normal forces and rotation speeds applied while monitoring the contact interface using optical imaging. We tested normal forces between 0.5 N and 10 N at a fixed angular velocity of 20° s^-1 and angular velocities between 5° s^-1 and 100° s^-1 at a fixed normal force of 2 N. We observe the characteristic pattern by which partial slips develop, starting at the periphery of the contact and propagating towards its centre, and the resulting surface strains. The 20-fold range of normal forces and angular velocities used highlights the effect of those parameters on the resulting torque and skin strains. Increasing normal force increases the contact area, the generated torque, strains and the twist angle required to reach full slip. On the other hand, increasing angular velocity causes more loss of contact at the periphery and higher strain rates (although it has no impact on resulting strains after the full rotation). We also discuss the surprisingly large inter-individual variability in skin biomechanics, notably observed in the twist angle the stimulus needs to rotate before reaching full slip.

A Smartphone-Based Model of Care to Support Patients With Cardiac Disease Transitioning From Hospital to the Community (TeleClinical Care): Pilot Randomized Controlled Trial

Background

Patients hospitalized with acute coronary syndrome (ACS) or heart failure (HF) are frequently readmitted. This is the first randomized controlled trial of a mobile health intervention that combines telemonitoring and education for inpatients with ACS or HF to prevent readmission.

Objective

This study aims to investigate the feasibility, efficacy, and cost-effectiveness of a smartphone app–based model of care (TeleClinical Care [TCC]) in patients discharged after ACS or HF admission.

Methods

In this pilot, 2-center randomized controlled trial, TCC was applied at discharge along with usual care to intervention arm participants. Control arm participants received usual care alone. Inclusion criteria were current admission with ACS or HF, ownership of a compatible smartphone, age ≥18 years, and provision of informed consent. The primary end point was the incidence of unplanned 30-day readmissions. Secondary end points included all-cause readmissions, cardiac readmissions, cardiac rehabilitation completion, medication adherence, cost-effectiveness, and user satisfaction. Intervention arm participants received the app and Bluetooth-enabled devices for measuring weight, blood pressure, and physical activity daily plus usual care. The devices automatically transmitted recordings to the patients’ smartphones and a central server. Thresholds for blood pressure, heart rate, and weight were determined by the treating cardiologists. Readings outside these thresholds were flagged to a monitoring team, who discussed salient abnormalities with the patients’ usual care providers (cardiologists, general practitioners, or HF outreach nurses), who were responsible for further management. The app also provided educational push notifications. Participants were followed up after 6 months.

Results

Overall, 164 inpatients were randomized (TCC: 81/164, 49.4%; control: 83/164, 50.6%; mean age 61.5, SD 12.3 years; 130/164, 79.3% men; 128/164, 78% admitted with ACS). There were 11 unplanned 30-day readmissions in both groups (P=.97). Over a mean follow-up of 193 days, the intervention was associated with a significant reduction in unplanned hospital readmissions (21 in TCC vs 41 in the control arm; P=.02), including cardiac readmissions (11 in TCC vs 25 in the control arm; P=.03), and higher rates of cardiac rehabilitation completion (20/51, 39% vs 9/49, 18%; P=.03) and medication adherence (57/76, 75% vs 37/74, 50%; P=.002). The average usability rating for the app was 4.5/5. The intervention cost Aus $6028 (US $4342.26) per cardiac readmission saved. When modeled in a mainstream clinical setting, enrollment of 237 patients was projected to have the same expenditure compared with usual care, and enrollment of 500 patients was projected to save approximately Aus $100,000 (approximately US $70,000) annually.

Conclusions

TCC was feasible and safe for inpatients with either ACS or HF. The incidence of 30-day readmissions was similar; however, long-term benefits were demonstrated, including fewer readmissions over 6 months, improved medication adherence, and improved cardiac rehabilitation completion.

Trial Registration

Australian New Zealand Clinical Trials Registry ACTRN12618001547235; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=375945

Process Evaluation of a Randomised Controlled Trial for TeleClinical Care, a Smartphone-App Based Model of Care

Background

A novel smartphone app-based model of care (TeleClinical Care – TCC) for patients with acute coronary syndrome (ACS) and heart failure (HF) was evaluated in a two-site, pilot randomised control trial of 164 participants in Sydney, Australia. The program included a telemonitoring system whereby abnormal blood pressure, weight and heart rate readings were monitored by a central clinical team, who subsequently referred clinically significant alerts to the patients' usual general practitioner (GP, also known as primary care physician in the United States), HF nurse or cardiologist. While the primary endpoint, 30-day readmissions, was neutral, intervention arm participants demonstrated improvements in readmission rates over 6 months, cardiac rehabilitation (CR) completion and medication compliance. A process evaluation was designed to identify contextual factors and mechanisms that influenced the results, as well as strategies of improving site and participant recruitment and the delivery of the intervention, for a planned larger effectiveness trial of over 1,000 patients across the state of New South Wales, Australia (TCC-Cardiac).

Methods

Multiple data sources were used in this mixed-methods process evaluation, including interviews with four TCC team members, three GPs and three cardiologists. CR completion rates, HF outreach service (HFOS) referrals and cardiologist follow-up appointments were audited. A patient questionnaire was also analysed for evidence of improved self-care as a hypothesised mechanism of the TCC app. An implementation research logic model was used to synthesise our findings.

Results

Rates of HFOS referral (83 vs. 72%) and cardiologist follow-up (96 vs. 93%) were similarly high in the intervention and control arms, respectively. Team members were largely positive towards their orientation and training, but highlighted several implementation strategies that could be optimised for TCC-Cardiac: streamlining of the enrolment process, improving the reach of the trial by screening patients in non-cardiac wards, and ensuring team members had adequate time to recruit (>15 h per week). GPs and cardiologists viewed the intervention acceptably regarding potential benefit of closely monitoring, and responding to abnormalities for their patients, though there were concerns of the potential additional workload generated by alerts that did not merit clinical intervention. Clear delineation of which clinician (GP or cardiologist) was primarily responsible for alert management was also recommended, as well as a preference to receive regular summary data. Several patients commented on the mechanisms of improved self-management because of TCC, which could have led to the outcome of improved medication compliance.

Discussion

Use of TCC was associated with several benefits, including higher patient engagement and completion rates with CR. The conduct and delivery of TCC-Cardiac will be improved by the findings of this process evaluation to optimise recruitment, and establishing the roles of GPs and cardiologists as part of the model.

Submillimeter Lateral Displacement Enables Friction Sensing and Awareness of Surface Slipperiness

Human tactile perception and motor control rely on the frictional estimates that stem from the deformation of the skin and slip events. However, it is not clear how exactly these mechanical events relate to the perception of friction. This study aims to quantify how minor lateral displacement and speed enables subjects to feel frictional differences. In a 2-alternative forced-choice protocol, an ultrasonic friction-reduction device was brought in contact perpendicular to the skin surface of an immobilized index finger; after reaching 1N normal force, the plate was moved laterally. A combination of four displacement magnitudes (0.2, 0.5, 1.2 and 2 mm), two levels of friction (high, low) and three displacement speeds (1, 5 and 10 mm/s) were tested. We found that the perception of frictional difference was enabled by submillimeter range lateral displacement. Friction discrimination thresholds were reached with lateral displacements ranging from 0.2 to 0.5 mm and surprisingly speed had only a marginal effect. These results demonstrate that partial slips are sufficient to cause awareness of surface slipperiness. These quantitative data are crucial for designing haptic devices that render slipperiness. The results also show the importance of subtle lateral finger movements present during dexterous manipulation tasks.

Trials and Tribulations: mHealth Clinical Trials in the COVID-19 Pandemic

INTRODUCTION

Mobile phone-based interventions in cardiovascular disease are growing in popularity. A randomised control trial (RCT) for a novel smartphone app-based model of care, named TeleClinical Care - Cardiac (TCC-Cardiac), commenced in February 2019, targeted at patients being discharged after care for an acute coronary syndrome or episode of decompensated heart failure. The app was paired to a digital sphygmomanometer, weighing scale and a wearable fitness band, all loaned to the patient, and allowed clinicians to respond to abnormal readings. The onset of the COVID-19 pandemic necessitated several modifications to the trial in order to protect participants from potential exposure to infection. The use of TCC-Cardiac during the pandemic inspired the development of a similar model of care (TCC-COVID), targeted at patients being managed at home with a diagnosis of COVID-19.

METHODS

Recruitment for the TCC-Cardiac trial was terminated shortly after the World Health Organization announced COVID-19 as a global pandemic. Telephone follow-up was commenced, in order to protect patients from unnecessary exposure to hospital staff and patients. Equipment was returned or collected by a 'no-contact' method. The TCC-COVID app and model of care had similar functionality to the original TCC-Cardiac app. Participants were enrolled exclusively by remote methods. Oxygen saturation and pulse rate were measured by a pulse oximeter, and symptomatology measured by questionnaire. Measurement results were manually entered into the app and transmitted to an online server for medical staff to review.

RESULTS

A total of 164 patients were involved in the TCC-Cardiac trial, with 102 patients involved after the onset of the pandemic. There were no hospitalisations due to COVID-19 in this cohort. The study was successfully completed, with only three participants lost to follow-up. During the pandemic, 5 of 49 (10%) of patients in the intervention arm were readmitted compared to 12 of 53 (23%) in the control arm. Also, in this period, 28 of 29 (97%) of all clinically significant alerts received by the monitoring team were managed successfully in the outpatient setting, avoiding hospitalisation. Patients found the user experience largely positive, with the average rating for the app being 4.56 out of 5. 26 patients have currently been enrolled for TCC-COVID. Recruitment is ongoing. All patients have been safely and effectively monitored, with no major adverse clinical events or technical malfunctions. Patient satisfaction has been high.

CONCLUSION

The TCC-Cardiac RCT was successfully completed despite the challenges posed by COVID-19. Use of the app had an added benefit during the pandemic as participants could be monitored safely from home. The model of care inspired the development of an app with similar functionality designed for use with patients diagnosed with COVID-19.

Estimating Lower Limb Kinematics Using a Reduced Wearable Sensor Count

GOAL

This paper presents an algorithm for accurately estimating pelvis, thigh, and shank kinematics during walking using only three wearable inertial sensors.

METHODS

The algorithm makes novel use of a constrained Kalman filter (CKF). The algorithm iterates through the prediction (kinematic equation), measurement (pelvis position pseudo-measurements, zero velocity update, flat-floor assumption, and covariance limiter), and constraint update (formulation of hinged knee joints and ball-and-socket hip joints).

RESULTS

Evaluation of the algorithm using an optical motion capture-based sensor-to-segment calibration on nine participants (7 men and 2 women, weight [Formula: see text] kg, height [Formula: see text] m, age [Formula: see text] years old), with no known gait or lower body biomechanical abnormalities, who walked within a [Formula: see text] m ² capture area shows that it can track motion relative to the mid-pelvis origin with mean position and orientation (no bias) root-mean-square error (RMSE) of [Formula: see text] cm and [Formula: see text], respectively. The sagittal knee and hip joint angle RMSEs (no bias) were [Formula: see text] and [Formula: see text], respectively, while the corresponding correlation coefficient (CC) values were [Formula: see text] and [Formula: see text].

CONCLUSION

The CKF-based algorithm was able to track the 3D pose of the pelvis, thigh, and shanks using only three inertial sensors worn on the pelvis and shanks.

SIGNIFICANCE

Due to the Kalman-filter-based algorithm's low computation cost and the relative convenience of using only three wearable sensors, gait parameters can be computed in real-time and remotely for long-term gait monitoring. Furthermore, the system can be used to inform real-time gait assistive devices.

Friction sensing mechanisms for perception and motor control: passive touch without sliding may not provide perceivable frictional information

Perception of the frictional properties of a surface contributes to the multidimensional experience of exploring various materials; we slide our fingers over a surface to feel it. In contrast, during object manipulation, we grip objects without such intended exploratory movements. Given that we are aware of the slipperiness of objects or tools that are held in the hand, we investigated whether the initial contact between the fingertip skin and the surface of the object is sufficient to provide this consciously perceived frictional information. Using a two-alternative forced-choice protocol, we examined human capacity to detect frictional differences using touch, when two otherwise structurally identical surfaces were brought in contact with the immobilized finger perpendicularly or under an angle (20° or 30°) to the skin surface (passive touch). An ultrasonic friction reduction device was used to generate three different frictions over each of three flat surfaces with different surface structure: 1) smooth glass, 2) textured surface with dome-shaped features, and 3) surface with sharp asperities (sandpaper). Participants (n = 12) could not reliably indicate which of the two surfaces was more slippery under any of these conditions. In contrast, when slip was induced by moving the surface laterally by a total of 5 mm (passive slip), participants could clearly perceive frictional differences. Thus making contact with the surface, even with moderate tangential forces, was not enough to perceive frictional differences, instead conscious perception required a sufficient size slip.NEW & NOTEWORTHY This study contributes to understanding how frictional information is obtained and used by the brain. When the skin is contacting surfaces of identical topography but varying frictional properties, the deformation pattern is different; however, available sensory cues did not get translated into perception of frictional properties unless a sufficiently large lateral movement was present. These neurophysiological findings may inform how to design and operate haptic devices relying on friction modulation principles.

Deep Learning for Activity Recognition in Older People Using a Pocket-Worn Smartphone

Activity recognition can provide useful information about an older individual's activity level and encourage older people to become more active to live longer in good health. This study aimed to develop an activity recognition algorithm for smartphone accelerometry data of older people. Deep learning algorithms, including convolutional neural network (CNN) and long short-term memory (LSTM), were evaluated in this study. Smartphone accelerometry data of free-living activities, performed by 53 older people (83.8 ± 3.8 years; 38 male) under standardized circumstances, were classified into lying, sitting, standing, transition, walking, walking upstairs, and walking downstairs. A 1D CNN, a multichannel CNN, a CNN-LSTM, and a multichannel CNN-LSTM model were tested. The models were compared on accuracy and computational efficiency. Results show that the multichannel CNN-LSTM model achieved the best classification results, with an 81.1% accuracy and an acceptable model and time complexity. Specifically, the accuracy was 67.0% for lying, 70.7% for sitting, 88.4% for standing, 78.2% for transitions, 88.7% for walking, 65.7% for walking downstairs, and 68.7% for walking upstairs. The findings indicated that the multichannel CNN-LSTM model was feasible for smartphone-based activity recognition in older people.

Estimating Lower Limb Kinematics Using a Lie Group Constrained Extended Kalman Filter with a Reduced Wearable IMU Count and Distance Measurements

Tracking the kinematics of human movement usually requires the use of equipment that constrains the user within a room (e.g., optical motion capture systems), or requires the use of a conspicuous body-worn measurement system (e.g., inertial measurement units (IMUs) attached to each body segment). This paper presents a novel Lie group constrained extended Kalman filter to estimate lower limb kinematics using IMU and inter-IMU distance measurements in a reduced sensor count configuration. The algorithm iterates through the prediction (kinematic equations), measurement (pelvis height assumption/inter-IMU distance measurements, zero velocity update for feet/ankles, flat-floor assumption for feet/ankles, and covariance limiter), and constraint update (formulation of hinged knee joints and ball-and-socket hip joints). The knee and hip joint angle root-mean-square errors in the sagittal plane for straight walking were 7.6±2.6∘ and 6.6±2.7∘, respectively, while the correlation coefficients were 0.95±0.03 and 0.87±0.16, respectively. Furthermore, experiments using simulated inter-IMU distance measurements show that performance improved substantially for dynamic movements, even at large noise levels (σ=0.2 m). However, further validation is recommended with actual distance measurement sensors, such as ultra-wideband ranging sensors.

Estimating Lower Limb Kinematics using Distance Measurements with a Reduced Wearable Inertial Sensor Count

This paper presents an algorithm that makes novel use of distance measurements alongside a constrained Kalman filter to accurately estimate pelvis, thigh, and shank kinematics for both legs during walking and other body movements using only three wearable inertial measurement units (IMUs). The distance measurement formulation also assumes hinge knee joint and constant body segment length, helping produce estimates that are near or in the constraint space for better estimator stability. Simulated experiments have shown that inter-IMU distance measurement is indeed a promising new source of information to improve the pose estimation of inertial motion capture systems under a reduced sensor count configuration. Furthermore, experiments show that performance improved dramatically for dynamic movements even at high noise levels (e.g., σ_dist = 0.2 m), and that acceptable performance for normal walking was achieved at σ_dist = 0.1 m. Nevertheless, further validation is recommended using actual distance measurement sensors.

SENSOR-BASED ASSESSMENT OF FALLS RISK OF THE TIMED UP AND GO IN REAL-WORLD SETTINGS

Falls are the leading cause of older adult injury and cost $50bn annually. New digital technologies can quantitatively measure falls risk. Objective is to report on a validated wearable sensor-based Timed Up and Go (QTUG) assessment detailing 11 measures of falls risk, frailty and mobility impairment in older adults in six countries in 38 clinical and community settings. Second objective is to generate individual targeted falls prevention programs. 14,611 QTUG records from 8,521 participants (63% female) (72.7±10.7 years) available for analysis. QTUG time was 13.9±7.4 s; gait velocity was 101.9±32.5 cm/s. 25.8% of patients reported falling in previous 12 months; 26.2% of patients were at high fall risk. 21.5% not reporting a fall, were high fall risk. Participants had slow walking speed (29.8%); high gait variability (19.8%); problems with transfers (17.5%). Easily captured and interpreted sensor data is useful in a population-based approach to quantify falls risk stratification.

Peripheral Nerve Activation Evokes Machine-Learnable Signals in the Dorsal Column Nuclei

The brainstem dorsal column nuclei (DCN) are essential to inform the brain of tactile and proprioceptive events experienced by the body. However, little is known about how ascending somatosensory information is represented in the DCN. Our objective was to investigate the usefulness of high-frequency (HF) and low-frequency (LF) DCN signal features (SFs) in predicting the nerve from which signals were evoked. We also aimed to explore the robustness of DCN SFs and map their relative information content across the brainstem surface. DCN surface potentials were recorded from urethane-anesthetized Wistar rats during sural and peroneal nerve electrical stimulation. Five salient SFs were extracted from each recording electrode of a seven-electrode array. We used a machine learning approach to quantify and rank information content contained within DCN surface-potential signals following peripheral nerve activation. Machine-learning of SF and electrode position combinations was quantified to determine a hierarchy of information importance for resolving the peripheral origin of nerve activation. A supervised back-propagation artificial neural network (ANN) could predict the nerve from which a response was evoked with up to 96.8 ± 0.8% accuracy. Guided by feature-learnability, we maintained high prediction accuracy after reducing ANN algorithm inputs from 35 (5 SFs from 7 electrodes) to 6 (4 SFs from one electrode and 2 SFs from a second electrode). When the number of input features were reduced, the best performing input combinations included HF and LF features. Feature-learnability also revealed that signals recorded from the same midline electrode can be accurately classified when evoked from bilateral nerve pairs, suggesting DCN surface activity asymmetry. Here we demonstrate a novel method for mapping the information content of signal patterns across the DCN surface and show that DCN SFs are robust across a population. Finally, we also show that the DCN is functionally asymmetrically organized, which challenges our current understanding of somatotopic symmetry across the midline at sub-cortical levels.

Smart Triggering of the Barometer in a Fall Detector Using a Semi-Permeable Membrane

The inclusion of a barometer in a wearable fall detector has been shown to improve the detection accuracy by measuring the altitude change associated with a fall event. However, the barometer is a power-hungry sensor, and the sensing power of barometer can be the dominant power consumption source in a wearable fall detector. In this study, we propose a triggering method that reduces barometer power consumption and prolongs the battery life. This approach utilizes a hermetically sealed and waterproof enclosure, with a small inlet covered by a semi-permeable membrane (SPM) to delay the time at which equilibrium between the internal and external pressures is reached, allowing the barometer to be woken from an idle low-power mode and capture the rising air pressure caused by the decrease in altitude during the fall. Two alternative signal processing methods were applied to the pressure waveform to detect the rising pressure pattern, a differential moving average filter (DMAF) and a Kalman filter (KF). The proposed fall detector was evaluated with data collected from a laboratory-based trial and a free-living trial, in which the barometric pressure data, recorded in open-air, were passed through a mathematical model of the leaky enclosure and the SPM assembly. The results show that the proposed fall detector with a 3.7 V, 140 mAh lithium-polymer battery provides a long battery life (DMAF 447 days, KF 444 days) while not compromising the sensitivity (DMAF 91.8%, KF 91.9%), specificity (DMAF 95.2% and KF 95.5%), or the false alarm rate (DMAF 0.035 alarms/hour and KF 0.064 alarms/hour).

Adaptive template matching of photoplethysmogram pulses to detect motion artefact

OBJECTIVE

The photoplethysmography (PPG) signal, commonly used in the healthcare settings, is easily affected by movement artefact leading to errors in the extracted heart rate and SpO₂ estimates. This study aims to develop an online artefact detection system based on adaptive (dynamic) template matching, suitable for continuous PPG monitoring during daily living activities or in the intensive care units (ICUs).

APPROACH

Several master templates are initially generated by applying principal component analysis to data obtained from the PhysioNet MIMIC II database. The master template is then updated with each incoming clean PPG pulse. The correlation coefficient is used to classify the PPG pulse into either good or bad quality categories. The performance of our algorithm was evaluated using data obtained from two different sources: (i) our own data collected from 19 healthy subjects using the wearable Sotera Visi Mobile system (Sotera Wireless Inc.) as they performed various movement types; and (ii) ICU data provided by the PhysioNet MIMIC II database. The developed algorithm was evaluated against a manually annotated 'gold standard' (GS).

MAIN RESULTS

Our algorithm achieved an overall accuracy of 91.5%  ±  2.9%, with a sensitivity of 94.1%  ±  2.7% and a specificity of 89.7%  ±  5.1%, when tested on our own data. When applying the algorithm to data from the PhysioNet MIMIC II database, it achieved an accuracy of 98.0%, with a sensitivity and specificity of 99.0% and 96.1%, respectively.

SIGNIFICANCE

The proposed method is simple and robust against individual variations in the PPG characteristics, thus making it suitable for a diverse range of datasets. Integration of the proposed artefact detection technique into remote monitoring devices could enhance reliability of the PPG-derived physiological parameters.

Selecting Power-Efficient Signal Features for a Low-Power Fall Detector

Falls are a serious threat to the health of older people. A wearable fall detector can automatically detect the occurrence of a fall and alert a caregiver or an emergency response service so they may deliver immediate assistance, improving the chances of recovering from fall-related injuries. One constraint of such a wearable technology is its limited battery life. Thus, minimization of power consumption is an important design concern, all the while maintaining satisfactory accuracy of the fall detection algorithms implemented on the wearable device. This paper proposes an approach for selecting power-efficient signal features such that the minimum desirable fall detection accuracy is assured. Using data collected in simulated falls, simulated activities of daily living, and real free-living trials, all using young volunteers, the proposed approach selects four features from a set of ten commonly used features, providing a power saving of 75.3%, while limiting the error rate of a binary classification decision tree fall detection algorithm to 7.1%.Falls are a serious threat to the health of older people. A wearable fall detector can automatically detect the occurrence of a fall and alert a caregiver or an emergency response service so they may deliver immediate assistance, improving the chances of recovering from fall-related injuries. One constraint of such a wearable technology is its limited battery life. Thus, minimization of power consumption is an important design concern, all the while maintaining satisfactory accuracy of the fall detection algorithms implemented on the wearable device. This paper proposes an approach for selecting power-efficient signal features such that the minimum desirable fall detection accuracy is assured. Using data collected in simulated falls, simulated activities of daily living, and real free-living trials, all using young volunteers, the proposed approach selects four features from a set of ten commonly used features, providing a power saving of 75.3%, while limiting the error rate of a binary classification decision tree fall detection algorithm to 7.1%.

Evaluation of an mHealth-Based Adjunct to Outpatient Cardiac Rehabilitation

A pilot study was conducted to determine if a smartphone-based adjunct to standard care could increase the completion rate of a cardiac rehabilitation program (CRP). Based on historical completion rates, 66 participants who were about to commence a hospital-based CRP were randomized so that half received three devices embedded with near-field communication, namely, a smartphone [pre-installed with an application (app) designed specifically for cardiac rehabilitation], portable blood pressure monitor, and weight scale while completing the CRP. The completion rate among participants who were randomized to the intervention group was 88%, compared to 67% in the control group ( = 0.038). This combined with the week-to-week frequency with which participants in the intervention group measured their blood pressure ( 5/week) demonstrated the ability of the intervention to increase the proportion of patients who completed the CRP. No significant differences were found between the treatment groups for the measurements taken at baseline and prior to discharge from the CRP. A statistically significant correlation ( = 0.472; = 0.013) was found between the average time participants walked each day (as estimated via the smartphone app) and participants' six minute walking distance (6MWD) before they were discharged from the CRP (a clinically validated measurement).

A Low-Power Fall Detector Balancing Sensitivity and False Alarm Rate

Falls in older people are a major challenge to public health. A wearable fall detector can detect falls automatically based on kinematic information of the human body, allowing help to arrive sooner. To date, most studies have focused on the accuracy of an offline algorithm to distinguish real-world or simulated falls from activities of daily living, while neglecting the false alarm rate and battery life of a real device. To address these two important metrics, which significantly influence user compliance, this paper proposes a low-power fall detector using triaxial accelerometry and barometric pressure sensing. This fall detector minimizes power consumption using both hardware- and firmware-based techniques. Additionally, the fall detection algorithm used in this device is optimized to achieve a balance between sensitivity and false alarm rate, while minimizing the power consumption due to algorithm execution. The fall detector achieved a high sensitivity (91%) with a low false alarm rate (0.1149 alarms per hour), and a commercially-viable battery life (1125 days).

Beat-to-beat variability of fetal myocardial performance index

OBJECTIVES

To determine whether there is beat-to-beat (BTB) variability in the fetal left myocardial performance index (MPI), as evaluated by an automated system, and whether there is a correlation between MPI and fetal heart rate (FHR).

METHODS

This was a prospective cross-sectional study of uncomplicated, morphologically normal, singleton pregnancies at 20-38 weeks' gestation. Multiple cineloops for left MPI measurement were acquired during a single examination of each fetus. Raw cineloop data were analyzed by our automated MPI system (intraclass correlation coefficient of 1.0 for any given waveform) to produce a set of MPIs. The corresponding instantaneous FHR was measured for each individual cardiac cycle for which MPI was calculated.

RESULTS

Data from 29 fetuses were analyzed; mean MPI was 0.52, mean FHR was 150 beats per min and the median number of cardiac cycles examined per fetus was 70 (interquartile range, 31-115). Marked BTB variability was noted; median coefficient of variation was 10% (range, 5.5-13.9%). FHR was weakly correlated with absolute MPI (r = 0.22; P < 0.05). BTB variation in MPI as a percentage of the mean MPI was not significantly correlated with FHR (r = 0.031; P = 0.146). When standard error of the mean of all MPI values was divided by the mean for each case, it showed that at least four cardiac cycles should be averaged to reduce MPI variability to approximately ± 5%.

CONCLUSION

There is significant BTB variability in fetal left MPI, which has an overall weak correlation with FHR. This could be a factor affecting the consistency of MPI values reported by different research groups. Variability would be reduced by averaging 4-5 cardiac cycles per fetus. Copyright © 2016 ISUOG. Published by John Wiley & Sons Ltd.

Characterisation and functional mapping of surface potentials in the rat dorsal column nuclei

KEY POINTS

The brainstem dorsal column nuclei (DCN) process sensory information arising from the body before it reaches the brain and becomes conscious. Despite significant investigations into sensory coding in peripheral nerves and the somatosensory cortex, little is known about how sensory information arising from the periphery is represented in the DCN. Following stimulation of hind-limb nerves, we mapped and characterised the evoked electrical signatures across the DCN surface. We show that evoked responses recorded from the DCN surface are highly reproducible and are unique to nerves carrying specific sensory information.

ABSTRACT

The brainstem dorsal column nuclei (DCN) play a role in early processing of somatosensory information arising from a variety of functionally distinct peripheral structures, before being transmitted to the cortex via the thalamus. To improve our understanding of how sensory information is represented by the DCN, we characterised and mapped low- (<200 Hz) and high-frequency (550-3300 Hz) components of nerve-evoked DCN surface potentials. DCN surface potentials were evoked by electrical stimulation of the left and right nerves innervating cutaneous structures (sural nerve), or a mix of cutaneous and deep structures (peroneal nerve), in 8-week-old urethane-anaesthetised male Wistar rats. Peroneal nerve-evoked DCN responses demonstrated low-frequency events with significantly longer durations, more high-frequency events and larger magnitudes compared to responses evoked from sural nerve stimulation. Hotspots of low- and high-frequency DCN activity were found ipsilateral to stimulated nerves but were not symmetrically organised. In conclusion, we find that sensory inputs from peripheral nerves evoke unique and characteristic DCN activity patterns that are highly reproducible both within and across animals.

Differences Between Gait on Stairs and Flat Surfaces in Relation to Fall Risk and Future Falls

We used body-worn inertial sensors to quantify differences in semi-free-living gait between stairs and on normal flat ground in older adults, and investigated the utility of assessing gait on these terrains for predicting the occurrence of multiple falls. Eighty-two community-dwelling older adults wore two inertial sensors, on the lower back and the right ankle, during several bouts of walking on flat surfaces and up and down stairs, in between rests and activities of daily living. Derived from the vertical acceleration at the lower back, step rate was calculated from the signal's fundamental frequency. Step rate variability was the width of this fundamental frequency peak from the signal's power spectral density. Movement vigor was calculated at both body locations from the signal variance. Partial Spearman correlations between gait parameters and physiological fall risk factors (components from the Physiological Profile Assessment) were calculated while controlling for age and gender. Overall, anteroposterior vigor at the lower back in stair descent was lower in subjects with longer reaction times. Older adults walked more slowly on stairs, but they were not significantly slower on flat surfaces. Using logistic regression, faster step rate in stair descent was associated with multiple prospective falls over 12 months. No significant associations were shown from gait parameters derived during walking upstairs or on flat surfaces. These results suggest that stair descent gait may provide more insight into fall risk than regular walking and stair ascent, and that further sensor-based investigation into unsupervised gait on different terrains would be valuable.

Unintended Consequences of Wearable Sensor Use in Healthcare. Contribution of the IMIA Wearable Sensors in Healthcare WG

OBJECTIVES

As wearable sensors take the consumer market by storm, and medical device manufacturers move to make their devices wireless and appropriate for ambulatory use, this revolution brings with it some unintended consequences, which we aim to discuss in this paper.

METHODS

We discuss some important unintended consequences, both beneficial and unwanted, which relate to: modifications of behavior; creation and use of big data sets; new security vulnerabilities; and unforeseen challenges faced by regulatory authorities, struggling to keep pace with recent innovations. Where possible, we proposed potential solutions to unwanted consequences.

RESULTS

Intelligent and inclusive design processes may mitigate unintended modifications in behavior. For big data, legislating access to and use of these data will be a legal and political challenge in the years ahead, as we trade the health benefits of wearable sensors against the risk to our privacy. The wireless and personal nature of wearable sensors also exposes them to a number of unique security vulnerabilities. Regulation plays an important role in managing these security risks, but also has the dual responsibility of ensuring that wearable devices are fit for purpose. However, the burden of validating the function and security of medical devices is becoming infeasible for regulators, given the many software apps and wearable sensors entering the market each year, which are only a subset of an even larger 'internet of things'.

CONCLUSION

Wearable sensors may serve to improve wellbeing, but we must be vigilant against the occurrence of unintended consequences. With collaboration between device manufacturers, regulators, and end-users, we balance the risk of unintended consequences occurring against the incredible benefit that wearable sensors promise to bring to the world.

Wavelet-Based Sit-To-Stand Detection and Assessment of Fall Risk in Older People Using a Wearable Pendant Device

GOAL

Wearable devices provide new ways to identify people who are at risk of falls and track long-term changes of mobility in daily life of older people. The aim of this study was to develop a wavelet-based algorithm to detect and assess quality of sit-to-stand movements with a wearable pendant device.

METHODS

The algorithm used wavelet transformations of the accelerometer and barometric air pressure sensor data. Detection accuracy was tested in 25 older people performing 30 min of typical daily activities. The ability to differentiate between people who are at risk of falls from people who are not at risk was investigated by assessing group differences of sensor-based sit-to-stand measurements in 34 fallers and 60 nonfallers (based on 12-month fall history) performing sit-to-stand movements as part of a laboratory study.

RESULTS

Sit-to-stand movements were detected with 93.1% sensitivity and a false positive rate of 2.9% during activities of daily living. In the laboratory study, fallers had significantly lower maximum acceleration, velocity, and power during the sit-to-stand movement compared to nonfallers.

CONCLUSION

The new wavelet-based algorithm accurately detected sit-to-stand movements in older people and differed significantly between older fallers and nonfallers.

SIGNIFICANCE

Accurate detection and quantification of sit-to-stand movements may provide objective assessment and monitoring of fall risk during daily life in older people.

A Kalman filter to estimate altitude change during a fall

Barometers have been incorporated into fall detectors in order to enhance the accuracy of fall detection algorithms, however they are power-hungry devices. We present an offline evaluation of a Kalman filter (KF) for estimating the pressure change during a fall that enables low-power operation of the barometer. The KF takes advantage of the fact that a semi-permeable air membrane on a waterproof fall detector enclosure causes a delay in the equilibrium between internal and external enclosure pressure, and this delay enables the barometer to be switched off until a free-fall is detected. We assessed the KF using data obtained from simulated falls and activities of daily living. The KF was able to differentiate between fall and non-fall activities, with the average measured pressure change during a fall of 8 Pa best determined using a delay in pressure equalization of 20 seconds. The KF detected a change in altitude faster than a simple moving average filter (MAF), reaching 66% of its final value before the MAF was able to initialize.

Low-power operation of a barometric pressure sensor for use in an automatic fall detector

The use of a barometric pressure sensor in a wearable fall detector has been shown to improve the detection accuracy by determining the altitude change associated with the fall event. However, the barometer is a high-power-consuming sensor. This paper proposes a fall detection approach using a hermetically sealed and waterproof enclosure incorporating a small window covered by a semi-permeable membrane (SPM) to delay the equilibrium of internal and external pressures. This feature can be utilized to limit the time the barometer is powered but still capturing critical pressure information to discriminate fall and non-fall events. The proposed fall detection system is evaluated with an existing data set of simulated fall and activities of daily living in which the barometric pressure data are delayed using a mathematical model of the enclosure and SPM assembly. Also, a benchtop test is performed to estimate the power and battery life. The proposed fall detection system achieves 94.0% sensitivity and 90.0% specificity with an estimated battery life of 995.7 days.

A Comparison of Magnetic Resonance Imaging and Neuropsychological Examination in the Diagnostic Distinction of Alzheimer's Disease and Behavioral Variant Frontotemporal Dementia

The clinical distinction between Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD) remains challenging and largely dependent on the experience of the clinician. This study investigates whether objective machine learning algorithms using supportive neuroimaging and neuropsychological clinical features can aid the distinction between both diseases. Retrospective neuroimaging and neuropsychological data of 166 participants (54 AD; 55 bvFTD; 57 healthy controls) was analyzed via a Naïve Bayes classification model. A subgroup of patients (n = 22) had pathologically-confirmed diagnoses. Results show that a combination of gray matter atrophy and neuropsychological features allowed a correct classification of 61.47% of cases at clinical presentation. More importantly, there was a clear dissociation between imaging and neuropsychological features, with the latter having the greater diagnostic accuracy (respectively 51.38 vs. 62.39%). These findings indicate that, at presentation, machine learning classification of bvFTD and AD is mostly based on cognitive and not imaging features. This clearly highlights the urgent need to develop better biomarkers for both diseases, but also emphasizes the value of machine learning in determining the predictive diagnostic features in neurodegeneration.

Fall Risk Assessment Through Automatic Combination of Clinical Fall Risk Factors and Body-Worn Sensor Data

Falls are the leading global cause of accidental death and disability in older adults and are the most common cause of injury and hospitalization. Accurate, early identification of patients at risk of falling, could lead to timely intervention and a reduction in the incidence of fall-related injury and associated costs. We report a statistical method for fall risk assessment using standard clinical fall risk factors (N = 748). We also report a means of improving this method by automatically combining it, with a fall risk assessment algorithm based on inertial sensor data and the timed-up-and-go test. Furthermore, we provide validation data on the sensor-based fall risk assessment method using a statistically independent dataset. Results obtained using cross-validation on a sample of 292 community dwelling older adults suggest that a combined clinical and sensor-based approach yields a classification accuracy of 76.0%, compared to either 73.6% for sensor-based assessment alone, or 68.8% for clinical risk factors alone. Increasing the cohort size by adding an additional 130 subjects from a separate recruitment wave (N = 422), and applying the same model building and validation method, resulted in a decrease in classification performance (68.5% for combined classifier, 66.8% for sensor data alone, and 58.5% for clinical data alone). This suggests that heterogeneity between cohorts may be a major challenge when attempting to develop fall risk assessment algorithms which generalize well. Independent validation of the sensor-based fall risk assessment algorithm on an independent cohort of 22 community dwelling older adults yielded a classification accuracy of 72.7%. Results suggest that the present method compares well to previously reported sensor-based fall risk assessment methods in assessing falls risk. Implementation of objective fall risk assessment methods on a large scale has the potential to improve quality of care and lead to a reduction in associated hospital costs, due to fewer admissions and reduced injuries due to falling.

Automated cardiac time interval measurement for Modified Myocardial Performance Index calculation of right ventricle

The Modified Myocardial Performance Index (Mod-MPI) has sparked great interest as a parameter for fetal cardiac function assessment. However, measurement of this index requires expertise and its clinical application might be limited, owing to its poor repeatability. Research groups have been investigating left Mod-MPI (that is, Mod-MPI from left ventricle valve events), and an automated algorithm has been developed for left Mod-MPI calculation in our previous study. Right MPI is also important as it becomes abnormal earlier than left MPI in some pathologies; however, for use across the gestational age spectrum, it requires two-image acquisition. This paper presents an automated method to detect valve movements during atrioventricular outflow and ventricular inflow and to further calculate the time intervals required for right MPI calculation. Ninety pulsed-wave Doppler ultrasound images of the right ventricle in fetuses, forty-five showing outflow and forty-five inflow, were analyzed to automatically detect the valve clicks generated by tricuspid valve movement in inflow waves, and pulmonary valve movement in outflow waves. The morphological characteristics of waves were combined with intensity information to locate clicks. This automated method can detect valve movement events with a high positive predictive value (96.20-98.96%) and sensitivity (97.95-100.00%), using manual annotation from an expert ultrasonographer as the gold standard for evaluation.

An eight-legged tactile sensor to estimate coefficient of static friction

It is well known that a tangential force larger than the maximum static friction force is required to initiate the sliding motion between two objects, which is governed by a material constant called the coefficient of static friction. Therefore, knowing the coefficient of static friction is of great importance for robot grippers which wish to maintain a stable and precise grip on an object during various manipulation tasks. Importantly, it is most useful if grippers can estimate the coefficient of static friction without having to explicitly explore the object first, such as lifting the object and reducing the grip force until it slips. A novel eight-legged sensor, based on simplified theoretical principles of friction is presented here to estimate the coefficient of static friction between a planar surface and the prototype sensor. Each of the sensor's eight legs are straight and rigid, and oriented at a specified angle with respect to the vertical, allowing it to estimate one of five ranges (5 = 8/2 + 1) that the coefficient of static friction can occupy. The coefficient of friction can be estimated by determining whether the legs have slipped or not when pressed against a surface. The coefficients of static friction between the sensor and five different materials were estimated and compared to a measurement from traditional methods. A least-squares linear fit of the sensor estimated coefficient showed good correlation with the reference coefficient with a gradient close to one and an r(2) value greater than 0.9.

Tactile afferents encode grip safety before slip for different frictions

Adjustments to frictional forces are crucial to maintain a safe grip during precision object handling in both humans and robotic manipulators. The aim of this work was to investigate whether a population of human tactile afferents can provide information about the current tangential/normal force ratio expressed as the percentage of the critical load capacity - the tangential/normal force ratio at which the object would slip. A smooth stimulation surface was tested on the fingertip under three frictional conditions, with a 4 N normal force and a tangential force generated by motion in the ulnar or distal direction at a fixed speed. During stimulation, the responses of 29 afferents (12 SA-I, 2 SA-II, 12 FA-I, 3 FA-II) were recorded. A multiple regression model was trained and tested using cross-validation to estimate the percentage of the critical load capacity in real-time as the tangential force increased. The features for the model were the number of spikes from each afferent in windows of fixed length (50, 100 or 200 ms) around points spanning the range from 50% to 100% of the critical load capacity, in 5% increments. The mean regression estimate error was less than 1% of the critical load capacity with a standard deviation between 5% and 10%. A larger number of afferents is expected to improve the estimate error. This work is important for understanding human dexterous manipulation and inspiring improvements in robotic grippers and prostheses.

Validation of an accelerometer-based fall prediction model

Falls are a common and serious problem faced by older populations. There is a growing interest in estimating the risk of falling for older people using body-worn sensors and simple movement tasks, allowing appropriate fall prevention programs to be administered in a timely manner to the high risk population. This study investigated the capability and validity of using a waist-mounted triaxial accelerometer (TA) and a directed routine (DR) that includes three movement tasks to discriminate between fallers and non-fallers and between multiple fallers and non-multiple fallers. Data were collected from 98 subjects who were stratified into two separate groups, one for model training and the other for model validation. Logistic regression models were constructed using the TA features from the entire DR and from each single DR task, and were validated using unseen data. The best models were obtained using features from the alternate step test to classify between fallers and non-fallers with κ = 0.34-0.41, sensitivity = 68%-71% and specificity = 63%-73%. However, the overall validation performances were poor. The study emphasizes the importance of independent validation in fall prediction studies.

Indoor location-aware medical systems for smart homecare and telehealth monitoring: state-of-the-art

This paper presents a comprehensive literature review of current progress in the application of state-of-the-art indoor positioning systems for telecare and telehealth monitoring. This review is the first in the literature that provides a comprehensive discussion on how existing wireless indoor positioning systems can benefit the development of home-based care systems. More specifically, this review provides an in-depth comparative study of how both system users and medical practitioners can get benefit from indoor positioning technologies; e.g. for real-time monitoring of patients suffering chronic cardiovascular conditions, general monitoring of activities of daily living (ADLs), fall detection systems for the elderly as well as indoor navigation systems for those suffering from visual impairments. Furthermore, it also details various aspects worth considering when choosing a certain technology for a specific healthcare application; e.g. the spatial precision demanded by the application, trade-offs between unobtrusiveness and complexity, and issues surrounding compliance and adherence with the use of wearable tags. Beyond the current state-of-the-art, this review also rigorously discusses several research opportunities and the challenges associated with each.

Design of an unobtrusive system for fall detection in multiple occupancy residences

A small trial was conducted to examine the feasibility of detecting falls using a combination of ambient passive infrared (PIR) and pressure mat (PM) sensors in a home with multiple occupants. The key tracking method made use of graph theoretical concepts to track each individual in the residence and to monitor them independently for falls. The proposed algorithm attempts to recognize falls where the subject experiences a hard fall on an indoor surface that leads to loss of consciousness or an inability to get up from the floor without assistance, due to severe injuries. The sensitivity, specificity and accuracy of the algorithm in detecting falls are 85.00%, 80.00% and 82.86%, respectively.

Review: Are we stumbling in our quest to find the best predictor? Over-optimism in sensor-based models for predicting falls in older adults

The field of fall risk testing using wearable sensors is bustling with activity. In this Letter, the authors review publications which incorporated features extracted from sensor signals into statistical models intended to estimate fall risk or predict falls in older people. A review of these studies raises concerns that this body of literature is presenting over-optimistic results in light of small sample sizes, questionable modelling decisions and problematic validation methodologies (e.g. inherent problems with the overly-popular cross-validation technique, lack of external validation). There seem to be substantial issues in the feature selection process, whereby researchers select features before modelling begins based on their relation to the target, and either perform no validation or test the models on the same data used for their training. This, together with potential issues related to the large number of features and their correlations, inevitably leads to models with inflated accuracy that are unlikely to maintain their reported performance during everyday use in relevant populations. Indeed, the availability of rich sensor data and many analytical options provides intellectual and creative freedom for researchers, but should be treated with caution, and such pitfalls must be avoided if we desire to create generalisable prognostic tools of any clinical value.

Improved Measurement of Blood Pressure by Extraction of Characteristic Features from the Cuff Oscillometric Waveform

We present a novel approach to improve the estimation of systolic (SBP) and diastolic blood pressure (DBP) from oscillometric waveform data using variable characteristic ratios between SBP and DBP with mean arterial pressure (MAP). This was verified in 25 healthy subjects, aged 28 ± 5 years. The multiple linear regression (MLR) and support vector regression (SVR) models were used to examine the relationship between the SBP and the DBP ratio with ten features extracted from the oscillometric waveform envelope (OWE). An automatic algorithm based on relative changes in the cuff pressure and neighbouring oscillometric pulses was proposed to remove outlier points caused by movement artifacts. Substantial reduction in the mean and standard deviation of the blood pressure estimation errors were obtained upon artifact removal. Using the sequential forward floating selection (SFFS) approach, we were able to achieve a significant reduction in the mean and standard deviation of differences between the estimated SBP values and the reference scoring (MLR: mean ± SD = −0.3 ± 5.8 mmHg; SVR and −0.6 ± 5.4 mmHg) with only two features, i.e., Ratio₂ and Area₃, as compared to the conventional maximum amplitude algorithm (MAA) method (mean ± SD = −1.6 ± 8.6 mmHg). Comparing the performance of both MLR and SVR models, our results showed that the MLR model was able to achieve comparable performance to that of the SVR model despite its simplicity.

Decoding tactile afferent activity to obtain an estimate of instantaneous force and torque applied to the fingerpad

Dexterous manipulation is not possible without sensory information about object properties and manipulative forces. Fundamental neuroscience has been unable to demonstrate how information about multiple stimulus parameters may be continuously extracted, concurrently, from a population of tactile afferents. This is the first study to demonstrate this, using spike trains recorded from tactile afferents innervating the monkey fingerpad. A multiple-regression model, requiring no a priori knowledge of stimulus-onset times or stimulus combination, was developed to obtain continuous estimates of instantaneous force and torque. The stimuli consisted of a normal-force ramp (to a plateau of 1.8, 2.2, or 2.5 N), on top of which -3.5, -2.0, 0, +2.0, or +3.5 mNm torque was applied about the normal to the skin surface. The model inputs were sliding windows of binned spike counts recorded from each afferent. Models were trained and tested by 15-fold cross-validation to estimate instantaneous normal force and torque over the entire stimulation period. With the use of the spike trains from 58 slow-adapting type I and 25 fast-adapting type I afferents, the instantaneous normal force and torque could be estimated with small error. This study demonstrated that instantaneous force and torque parameters could be reliably extracted from a small number of tactile afferent responses in a real-time fashion with stimulus combinations that the model had not been exposed to during training. Analysis of the model weights may reveal how interactions between stimulus parameters could be disentangled for complex population responses and could be used to test neurophysiologically relevant hypotheses about encoding mechanisms.

Classification of Implantable Rotary Blood Pump States With Class Noise

A medical case study related to implantable rotary blood pumps is examined. Five classifiers and two ensemble classifiers are applied to process the signals collected from the pumps for the identification of the aortic valve nonopening pump state. In addition to the noise-free datasets, up to 40% class noise has been added to the signals to evaluate the classification performance when mislabeling is present in the classifier training set. In order to ensure a reliable diagnostic model for the identification of the pump states, classifications performed with and without class noise are evaluated. The multilayer perceptron emerged as the best performing classifier for pump state detection due to its high accuracy as well as robustness against class noise.

Predicting days in hospital using health insurance claims

Health-care administrators worldwide are striving to lower the cost of care while improving the quality of care given. Hospitalization is the largest component of health expenditure. Therefore, earlier identification of those at higher risk of being hospitalized would help health-care administrators and health insurers to develop better plans and strategies. In this paper, a method was developed, using large-scale health insurance claims data, to predict the number of hospitalization days in a population. We utilized a regression decision tree algorithm, along with insurance claim data from 242 075 individuals over three years, to provide predictions of number of days in hospital in the third year, based on hospital admissions and procedure claims data. The proposed method performs well in the general population as well as in subpopulations. Results indicate that the proposed model significantly improves predictions over two established baseline methods (predicting a constant number of days for each customer and using the number of days in hospital of the previous year as the forecast for the following year). A reasonable predictive accuracy (AUC =0.843) was achieved for the whole population. Analysis of two subpopulations-namely elderly persons aged 63 years or older in 2011 and patients hospitalized for at least one day in the previous year-revealed that the medical information (e.g., diagnosis codes) contributed more to predictions for these two subpopulations, in comparison to the population as a whole.

Automated fetal cardiac valve movement detection for modified myocardial performance index calculation

The Modified Myocardial Performance Index (Mod-MPI) is becoming an important index in fetal cardiac function evaluation. However, the current method for Mod-MPI calculation can be time-consuming and demonstrates poor inter-operator repeatability. This paper presents an automated method for detecting the opening and closing events of fetal cardiac valves with the aim of automating the Mod-MPI calculation. Fifty-four Doppler ultrasound images, showing blood inflow and outflow for the left ventricle, are analyzed to attempt to automatically detect the timings of a total of 905 opening and closing events for both aortic and mitral valves. Timings are found according to the morphological characteristics of waveforms as well as intensity information of images. The proposed method can detect the four valve movement events with high sensitivity (95.60-98.64%) and precision (96.85-100.00%). Results are verified by comparison with manual annotation of same images from an expert.

A low-power fall detection algorithm based on triaxial acceleration and barometric pressure

This paper proposes a low-power fall detection algorithm based on triaxial accelerometry and barometric pressure signals. The algorithm dynamically adjusts the sampling rate of an accelerometer and manages data transmission between sensors and a controller to reduce power consumption. The results of simulation show that the sensitivity and specificity of the proposed fall detection algorithm are both above 96% when applied to a previously collected dataset comprising 20 young actors performing a combination of simulated falls and activities of daily living. This level of performance can be achieved despite a 10.9% reduction in power consumption.

Pilot evaluation of an unobtrusive system to detect falls at nighttime

Research shows that older people (aged 65 years and over) suffer many unintentional indoor falls which often lead to severe injuries. As a result of an increasingly aged population in developed countries, a sizable portion of healthcare funding is consumed in the treatment of fall-related injuries and associated long-term care. Detecting falls soon after they occur can be potentially live saving. In addition, early treatment of fall-related injuries can reduce treatment costs by minimizing health deterioration resulting from long periods spent incapacitated on the floor after a fall (a scenario known as a `long lie') and decreasing the number of hospital bed-days required. In this study, a previously proposed unobtrusive nighttime fall detection system based on wireless passive infrared sensors and furniture load sensors is evaluated in a pilot study involving three older subjects, monitored for a combined total of 174 days. No falls occurred during the study. The system reported a false alarm rate of 0.53 falls per day, which is comparable with similar unobtrusive and wearable sensor fall detection solutions.