Date: February 26, 2021
Source: University of Southern California
Summary: A research team has developed mathematical model to predict seizures that will give epilepsy patients an accurate warning five minutes to one hour before they are likely to experience a seizure.
Epilepsy is one of the most common neurological conditions, affecting more than 65 million worldwide. For those dealing with epilepsy, the advent of a seizure can feel like a ticking time bomb. It could happen at any time or any place, potentially posing a fatal risk when a seizure strikes during risky situations, such as while driving.
A research team at USC Viterbi School of Engineering and Keck Medicine of USC is tackling this dangerous problem with a powerful new seizure predicting mathematical model that will give epilepsy patients an accurate warning five minutes to one hour before they are likely to experience a seizure, offering enhanced freedom for the patient and cutting the need for medical intervention.
The research, published in the Journal of Neural Engineering, is led by corresponding authors Dong Song, research associate professor of biomedical engineering at USC Viterbi School of Engineering and Pen-Ning Yu, former PhD researcher in Song’s lab, in collaboration with Charles Liu, professor of clinical neurological surgery and director of the USC Neurorestoration Center. The other authors are David Packard Chair in Engineering and professor of biomedical engineering, Ted Berger, and medical director of the USC Comprehensive Epilepsy Program at the Keck Medical Center, Christianne Heck.
The mathematical model works by learning from large amounts of brain signal data collected from an electrical implant in the patient. Liu and his team have already been working with epilepsy patients with implantable devices, which are able to offer ongoing real-time monitoring of the brain’s electrical signals in the same way that an electroencephalogram (EEG) uses external electrodes to measure signals. The new mathematical model can take this data and learn each patient’s unique brain signals, looking out for precursors, or patterns of brain activity that show a “pre-ictal” state, in which a patient is at risk of seizure onset.
Song said the new model is able to accurately predict whether a seizure may happen within one hour, allowing the patient to take the necessary intervention.
“For example, it could be as simple as just alerting the patient their seizure is coming the next hour, so they shouldn’t drive their car right now, or they should take their medicine, or they should go and sit down” Song said. “Or ideally in future we can detect seizure signals and then send electrical stimulation through an implantable device to the brain to prevent the seizure from happening.”
Liu said that the discovery would have major positive implications for public health, given epilepsy treatment had been severely impacted in the past year by the pandemic.
“This is hopefully, going to change the way we deal with epilepsy going forward and it’s driven by the needs that have been in place for a long time, but have been highlighted and accelerated by COVID,” Liu said.
He said that currently, patients with medically intractable epilepsy-epilepsy that cannot be controlled with medication-are admitted electively to the hospital for video EEG monitoring. With the advent of COVID, these elective admissions completely halted and epilepsy programs across the country ground to a halt over the past year. Liu said this highlights the need for a new workflow by which EEG recordings from scalp or intradural electrodes can be acquired at home and analyzed computationally.
“So we need to create a new workflow by which, instead of bringing patients to the ICU, we take the recordings from their home and use the computation models to do everything they would have done in the hospital,” Liu said. “Not only can you manage patients using physical distancing, you can also scale in a way that only technology allows. Computation can analyze thousands of pages of data at once, whereas a single neurologist cannot.”
How the Seizure Prediction Model Works
Song said the new model was different to previous seizure prediction models in that it extracts both linear and non-linear information from the patient’s brain signals.
“Linear is the simple feature. If you understand the parts, you can understand the whole,” Song said. “Whereas the non-linear feature means that even if you understand the parts, when you scale up it has some emergent properties that cannot be explained.”
“For some patients, linear features are more important and for other patients, non-linear features are more important,” Song said.
Song said that while other models predict brain activity over a short time scale, a matter of milliseconds, his team’s model examined an extended time scale.
“The brain is a multi-temporal scale device so we need to understand what happens not just in the short term, but many more steps in the future,” Song said.
He said that the model is also unique in that it is patient-specific-it extracts the information that is significant for each individual patient. Because every brain is very different in terms of the signals that indicate a “pre-ictal” state.
“Patients are all different from each other, so in order to accurately predict seizures, we need to record signals, we need to look at a lot of different features and we need to have an algorithm to select the most important feature for prediction,” Song said.
“I can’t tell you how exciting, this is. At USC we’ve been very interested in trying to create tools that enhance the public health dimension of these diseases that we’re treating, and it’s really difficult,” Liu said
“Epileptologists are still relatively few in number in many parts of our country and world. While they can identify many subtle features on EEG, the kinds of models that Song can create can identify additional features at a massive scale necessary to help the millions of patients affected by epilepsy in our region and worldwide,” Liu said.
Heck, who is also co-director for the USC Neurorestoration Center, said that there are two important issues to the clinical relevance of this technology.
“One is that a majority of patients who suffer from epilepsy live with fear and anxiety about their next seizure which may strike like lightening in the most inopportune moment, perhaps while driving, or just walking in public. An ample warning provides a critical ‘get safe’ opportunity,” Heck said. “The second relevant issue clinically is that we have brain implants, smart devices, that this engineered technology can enhance, giving greater hope for efficacy of our existing therapies
- Pen-g Yu, Charles Y Liu, Christianne N Heck, Theodore W Berger, Dong Song. A sparse multiscale nonlinear autoregressive model for seizure prediction. Journal of Neural Engineering, 2021; 18 (2): 026012 DOI: 10.1088/1741-2552/abdd43
[Abstract] A Review of Structure and Function of Glove-like Power Hand Orthoses for Hand Rehabilitation of Patients with Hand Weakness and Paralysis
Power orthoses, due to their characteristics, can greatly assist in the recovery and improvement of people with problems in hand function. The purpose of this study was to review the glove-like power hand orthoses that were designed to practice, assist and improve performance in patients with weak or paralyzed hands.
PubMed, Scopus, ISI web of sciences and IEEE databases were searched from 2000 to 2019. The keywords used to search were selected based on the PICO strategy. By using the introduced keywords, 605 articles were obtained. After the final evaluation, 12 articles were selected. Criteria for the study included: design and deveplopment of glove-like power orthoses, use of orthoses for treatment, rehabilitation and improvement of hand function, use for people with weakness or paralysis of the hand muscles due to central nervous system disorder.
The study showed that of the 12 introduced orthoses, 10 orthoses used electric motors to generate propulsion, and 2 orthoses benefited from the pneumatic system. Regarding force transmission systems, most of these orthoses use cable transmission systems. What makes these orthoses even more differentiated is the control system, which can be referred to as positional signals, electrical muscle signals, and software systems.
Studies have shown that there are many different orthoses in terms of power transmission systems, drive systems, and control systems, and each of these devices has different capabilities to assist patients. Although each of the introduced orthotic designs has advantages to meet the needs of their target community, they are not without limitations. Removing the limitations of these designs could play a role in enhancing the efficiency and better meeting the needs of those who use these devices.
[ARTICLE] Upper Limb Rehabilitation System for Stroke Survivors Based on Multi-Modal Sensors and Machine Learning – Full Text PDF
Nowadays, rehabilitation training for stroke survivors is mainly completed under the guidance
of the physician. There are various treatment ways, however, most of them are affected by various factors
such as experience of physician and training intensity. The treatment effect cannot be fed back in time,
and objective evaluation data is lacking. In addition, the treatment method is complicated, costly, and highly
dependent on physicians. Moreover, stroke survivors’ compliance is poor, which leads to various limitations.
This paper combines the Internet-of-Things, machine learning, and intelligence system technologies to
design a smartphone-based intelligence system to help stroke survivors to improve upper limb rehabilitation.
With the built-in multi-modal sensors of the smart phone, training action data of users can be obtained,
and then transfer to the server through the Internet. This research presents a DTW-KNN joint algorithm
to recognize accuracy of rehabilitation actions and classify to multiple training completion levels. The
experimental results show that the DTW-KNN algorithm can evaluate the rehabilitation actions, the accuracy
rates of the classification in excellent, good, and normal are 85.7%, 66.7%, and 80% respectively. The
intelligence system presented in this paper can help stroke survivors to proceed rehabilitation training
independently and remotely, which reduces medical costs and psychological burden.
[ARTICLE] A computer-game-based rehabilitation platform for individuals with fine and gross motor upper extremity deficits post-stroke (CARE fOR U) – Protocol for a randomized controlled trial – Full Text
Background & purpose
Activity-based neuroplasticity and re-organization leads to motor learning via replicating real-life movements. Increased repetition of such movements has growing evidence over last few decades. In particular, computer-game-based rehabilitation is found to be effective, feasible and acceptable for post-stroke upper limb deficits. Our study aims to evaluate the feasibility and effectiveness of 12 weeks of computer-game-based rehabilitation platform (GRP) on fine and gross motor skills post-stroke in India.
Through this trial we will study the effect of adjunctive in-hospital GRP (using a motion-sensing airmouse with off-the-shelf computer games) in 80 persons with subacute stroke, for reduction of post-stroke upper limb deficits in a single-centre prospective Randomized Open, Blinded End- point trial when compared to conventional therapy alone.
We intend to evaluate between-group differences using Wolf Motor Function test, Stroke Specific Quality of Life, and GRP assessment tool. Feasibility will be assessed via recruitment rates, adherence to intervention periods, drop-out rate and qualitative findings of patient experience with the intervention.
The CARE FOR U trial is designed to test the feasibility and effectiveness of a computer-game based rehabilitation platform in treating upper limb deficits after stroke. In case of positive findings GRP can be widely applicable for stroke populations needing intensive and regular therapy with supervision.
Introduction & rationale
Over the last few decades, there has been an increase in stroke burden globally. Global burden of disease (GBD) 2016 reports 80.1 million prevalent cases of stroke globally. and 116.4 million disability adjusted life years.1 Asia accounts for almost two-thirds of the world’s stroke incidences.2
A significant proportion of individuals with stroke have long term residual disability3 and three-fourths of Indian stroke survivors are left with moderate to severe disabilities.4 Loss of arm function with stroke can impact a person’s ability to participate in home life, work and can reduce quality of life. Upper limb (UL) impairments are seen in 80% of stroke survivors and only 5–20% have complete functional recovery.5–7 with residual spasticity in 46% of cases5 and only 20.7% of stroke survivors returning to work by 2 years post-stroke (with half having changed their job).8 Early and targeted rehabilitation for UL deficits post-stroke is therefore crucial.9
Current evidence-based approaches used in rehabilitation of UL function after stroke emphasize that intensity, volume of training and task-specificity are pivotal.5 One such approach, the constraint-induced movement therapy, established strongly to be effective in rehabilitation of UL deficits, requires constraint of the unaffected limb and performance of repetitive functional training of upper extremity. This constraint can be applied for up to 60–90% of waking hours10,11 Questions arise on the ability of patients to adhere to such therapy regimes which are tedious and may lead to poor adherence in those with low motivation12 which is essential for improved compliance and adherence to rehabilitation regimes for individuals with UL deficits.13–15
Activity-based neuroplasticity and re-organization leading to motor learning by replicating real-life movements and repetition has growing evidence over last few decades.16,17 Virtual reality has been proven to improve UL function and ADLs when used as an adjunct to usual care (probably by increasing the duration of overall therapy).18 Such a mode of therapy has frequently been applied via the use of commercial gaming consoles like the Sony Playstation, Nintendo Wii and Microsoft Kinect. However VR based therapy has its cons: lack of computer skills of therapists, support infrastructure, initial investment, inadequate communication infrastructure in case of telerehabilitation and questionable long lasting effects.18,19 Studies also provide an increasing evidence for use of gaming technology in stroke rehabilitation of UE.20,21 Computer based systems may allow less dependence on rehabilitation personnel, improved standardization of rehabilitation protocols, increased intensity and frequency of activities and creative treatment delivery.22 A structured game-based rehabilitation protocol could effectively improve post-stroke upper limb function15,23,24 and is reported to be feasible, well-accepted by patient population with no adverse effects.21
Our study will therefore investigate the feasibility and effectiveness of a simplified in-hospital upper-limb rehabilitation program using off-the-shelf computer-games and a miniature wireless motion detecting mouse (Airmouse™) mounted on various objects to replicate activities of daily living (ADLs) for those with subacute stroke. We hypothesize that adjunctive Computer game-based rehabilitation platform for post-stroke upper extremity fine and gross motor deficits, will be feasible and effective in treating UL deficits due to stroke when compared to conventional therapy alone in the subacute phase.
CARE FOR U
A computer-game-based rehabilitation platform (GRP) previously developed for assessment and rehabilitation of UL functions of individuals with stroke and cerebral palsy will be used in this trial for those with stroke.25,26 This GRP includes three main components:
- A miniature wireless inertia-based motion-detecting mouse which translates movements performed to the motion of a computer cursor: Airmouse™ (Figure 1). When mounted on objects, the mouse is used to control the motion of the cursor/game paddle. The Airmouse™ can be mounted on a varied range of objects of differing physical properties (weight, texture, shape, size) that create diverse functional demands allowing for practice of manual dexterity, precision and power grasps.
[ARTICLE] Ultra-high field magnetic resonance imaging in human epilepsy: a systematic review – Full Text
- This review discusses 16 studies using 7T MRI to evaluate patients with chronic focal epilepsy.
- UHF MRI increases the sensitivity to detect an epileptogenic lesion.
- Diagnostic gain of 7T over conventional MRI was between 8-67%, pooled gain was 31%
- FCD, gliosis and HS were the most frequently diagnosed histopathological lesions.
- No conclusion can be drawn whether 7T improves surgical treatment and seizure outcome.
Resective epilepsy surgery is an evidence-based curative treatment option for patients with drug-resistant focal epilepsy. The major preoperative predictor of a good surgical outcome is detection of an epileptogenic lesion by magnetic resonance imaging (MRI). Application of ultra-high field (UHF) MRI, i.e. field strengths ≥7 Tesla (T), may increase the sensitivity to detect such a lesion.
A keyword search strategy was submitted to Pubmed, EMBASE, Cochrane Database and clinicaltrials.gov to select studies on UHF MRI in patients with epilepsy. Follow-up study selection and data extraction were performed following PRISMA guidelines. We focused on I) diagnostic gain of UHF- over conventional MRI, II) concordance of MRI-detected lesion, seizure onset zone and surgical decision-making, and III) postoperative histopathological diagnosis and seizure outcome.
Sixteen observational cohort studies, all using 7T MRI were included. Diagnostic gain of 7T over conventional MRI ranged from 8% to 67%, with a pooled gain of 31%. Novel techniques to visualize pathological processes in epilepsy and lesion detection are discussed. Seizure freedom was achieved in 73% of operated patients; no seizure outcome comparison was made between 7T MRI positive, 7T negative and 3T positive patients. 7T could influence surgical decision-making, with high concordance of lesion and seizure onset zone. Focal cortical dysplasia (54%), hippocampal sclerosis (12%) and gliosis (8.1%) were the most frequently diagnosed histopathological entities.
UHF MRI increases, yet variably, the sensitivity to detect an epileptogenic lesion, showing potential for use in clinical practice. It remains to be established whether this results in improved seizure outcome after surgical treatment. Prospective studies with larger cohorts of epilepsy patients, uniform scan and sequence protocols, and innovative post-processing technology are equally important as further increasing field strengths. Besides technical ameliorations, improved correlation of imaging features with clinical semiology, histopathology and clinical outcome has to be established.
In epilepsy surgery, magnetic resonance imaging (MRI) is the imaging technique of choice because of its ability to depict cerebral anatomy and small local aberrances with superior sensitivity compared to other imaging techniques. (Alvarez-Linera, 2008) Major predictive factors for satisfactory postoperative seizure outcome are, among others, appropriate detection and delineation of the epileptogenic zone, (Jehi, 2018) lesion detection on MRI, type of pathology, and complete resection of the epileptogenic zone and lesion. (Bien et al., 2009, Ji et al., 2010, Leach et al., 2014) To increase detection sensitivity, dedicated 3 Tesla (T) epilepsy protocols with a variety of sequences for lesion detection have been determined. (Wellmer et al., 2013) Despite this, even with improvements on 3T MRI like automated brain segmentation, in up to 30-40% of focal epilepsy patients, MRI shows no lesion (i.e. MRI-negative). (Griffiths et al., 2005, Kwan and Brodie, 2000, Kwan et al., 2010, Muhlhofer et al., 2017) In order to decrease numbers of MRI-negative patients, considerable efforts have been made by the scientific community to develop MRI scanners with increasingly higher magnetic field strengths, leading to enhanced signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and exquisite spatial resolution. (Kraff et al., 2015) This resulted in the application of ultra-high field (UHF; ≥7T) MRI, facilitating visualization of brain structure and function beyond what is available at conventional field strengths (≤ 3T), leading to better detection of smaller anatomical structures, improved delineation of doubtful lesions on 3T, and quantification of (sub)cortical abnormalities. (Barisano et al., 2019, Kraff et al., 2015, Lee, 2020) An improvement of field strength from 1.0/1.5T to 3T was associated with an increased lesion detection in epilepsy patients of 20-48%, (Knake et al., 2005, Strandberg et al., 2008) with further increase of lesion detection when assessed by a dedicated epilepsy-neuroradiologist. (Wellmer et al., 2013) Application of UHF MRI to patients with intracranial pathology, including epilepsy, has already been advocated in literature. (Obusez et al., 2016, Rondinoni et al., 2019, Springer et al., 2016) Consensus has been reached in literature that intracranial lesions or abnormalities are more readily assessable on 7T compared to 3T. (Springer et al., 2016) The role of experimental UHF MRI in epilepsy seems to increase as shown in recent literature. (Rondinoni et al., 2019)
The hypothesis is that UHF imaging can visualize structural abnormalities in a subset of these 3T MRI-negative focal epilepsy patients, e.g., focal cortical dysplasia (FCD) , early stage hippocampal sclerosis (HS), or amygdala abnormalities. (Bautista et al., 2003, Von Oertzen et al., 2002) FCD’s are congenital malformations of cortical development characterized by aberrant migration and differentiation. (Blümcke et al., 2011) It has been reported that up to 40% of FCDs cannot be visualized with current dedicated 3T MRI protocols. (Guerrini et al., 2008, Sepúlveda et al., 2020) FCD’s are a major cause of chronic epilepsy in children, (Blümcke et al., 2016) and the most frequent etiology (42%) in pediatric candidates for epilepsy surgery. In adults with chronic drug-resistant temporal lobe epilepsy, it is the third most common pathological substrate (13%) after HS (43%) (Blümcke et al., 2017) and tumors (30%). (Lerner et al., 2009) HS can be classified in three subtypes (ILAE subtype I – III). (Blümcke et al., 2013) UHF MRI has the potential to in-vivo visualize in detail hippocampal subfields, cornu ammonis 1-4 (CA), dentate gyrus (DG), and its pathology, which had until now only been possible by histopathological analysis of resected hippocampal tissue or at autopsy. (Santyr et al., 2016, Stefanits et al., 2017, Steve et al., 2020)
To date a systematic review about UHF MRI in-vivo diagnostics in epilepsy patients is not available, which prompted us to critically collect and review present UHF-literature and discuss recent developments in clinical application of UHF MRI in adult and pediatric epilepsy. In particular we focus on I) diagnostic gain of UHF MRI over conventional field strengths, II) discuss concordance of UHF MRI abnormalities with seizure onset zone and surgical decision-making, and finally III) in operative cases, concordance of UHF MRI with histopathology and postoperative seizure outcome.[…]
[Abstract] Integration of a smartwatch within an internet-delivered intervention for depression: Protocol for a feasibility randomized controlled trial on acceptance
Mood tracking is commonly employed within a range of mental health interventions. Physical activity and sleep are also important for contextualizing mood data but can be difficult to track manually and rely on retrospective recall. Smartwatches could enhance self-monitoring by addressing difficulties in recall of sleep and physical activity and reducing the burden on patients in terms of remembering to track and the effort of tracking. This feasibility study will explore the acceptance of a smartwatch app for self-monitoring of mood, sleep, and physical activity, in an internet-based cognitive-behavioral therapy (iCBT) for depression offered in a routine care setting.
Seventy participants will be randomly allocated to (i) iCBT intervention plus smartwatch app or (ii) iCBT intervention alone. Patient acceptance will be measured longitudinally using a theory-based acceptance questionnaire to understand and compare the evolution of acceptance of the technology-delivered self-report in the two groups. A post-treatment interview will explore participants subjective experience of using the smartwatch. Engagement with the intervention, including self-report, and clinical outcomes, will be measured across both groups to assess for any differences.
This is the first study investigating the evolution of patient acceptance of smartwatch self-report in an iCBT delivered intervention in a clinical sample. Through an engaging and convenient means of capturing ecologically valid mood data, the study has the potential to show that smartwatches are an acceptable means for patient self-monitoring within iCBT interventions for depression and support potential use-cases for smartwatches in the context of mental health interventions in general.
Researchers testing the ReWalk ReStore soft robotic exosuit for gait training in individuals undergoing post-stroke rehabilitation suggest it is safe and reliable during treadmill and overground walking under the supervision of physical therapists.
The results of the multi-center, single-arm trial was published open access recently in the Journal of NeuroEngineering and Rehabilitation.
The authors are the principal investigators of each of the five testing sites, per a media release from Kessler Foundation: Louis N. Awad, PT, DPT, PhD, of Spaulding Rehabilitation Hospital, Boston; Alberto Esquenazi, MD, of MossRehab Stroke and Neurological Disease Center, Elkins Park, Pa; Gerard E. Francisco, MD, of TIRR Memorial Hermann, Houston; Karen J. Nolan, PhD, of Kessler Foundation, West Orange, NJ; and lead investigator Arun Jayaramam, PT, PhD, of the Shirley Ryan AbilityLab, Chicago.
The ReStore exosuit, from ReWalk Robotics Ltd, Marlborough, Mass, is reportedly the first soft robotic exosuit cleared by the FDA for use in stroke survivors with mobility deficits. The device is indicated for individuals with hemiplegia undergoing stroke rehabilitation under the care of licensed physical therapists.
ReStore is designed to augment ankle plantarflexion and dorsiflexion, allowing a more normal gait pattern. Motors mounted on a waist belt transmit power through cables to attachment points on an insole and the patient’s calf. Sensors clipped to the patient’s shoes transmit data to a handheld smartphone controller used by a trained therapist to adjust levels of assistance and monitor and record key metrics of gait training, per the release.
TESTED ON STROKE PATIENTS WITH HEMIPARESIS
The trial enrolled 44 participants with post-stroke hemiparesis who were able to walk unassisted for 5 feet. The protocol consisted of 5 days of 20-minute sessions of treadmill and overground training under the supervision of licensed physical therapists.
To assess the therapeutic potential for ReStore in rehabilitation, the researchers also explored the effects of the device on maximum walking speed, measuring participants’ walking speed in and out of the device using the 10-m walk test, before and after the five training visits. For safety purposes, some participants were allowed to use an AFO or cane during walking sessions.
The trial determined the safety, reliability, and feasibility of the device in this stroke population.
“We found that the ReStore provided targeted assistance for plantarflexion and dorsiflexion of the paretic ankle, improving the gait pattern,” explained Dr. Nolan, senior research scientist in the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation. “This is an important first step toward expanding options for rehabilitative care for the millions of individuals with mobility impairments caused by ischemic and hemorrhagic stroke.”
— Karen J. Nolan, PhD, senior research scientist in the Center for Mobility and Rehabilitation Engineering Research at Kessler Foundation
The trial’s exploratory data indicated positive effects of the training on the walking speed of participants during exosuit-assisted walking and unassisted walking (walking without the device). More than one third of participants achieved a significant increase in unassisted walking speed, indicating that further research is warranted, the release continues.
Nolan emphasizes that the trial was not designed to measure the device’s efficacy, adding that controlled trials are needed to determine the efficacy of ReStore for improving mobility outcomes of stroke rehabilitation.
[Source(s): Kessler Foundation, Science Daily]
This work is devoted to the presentation of a Wireless Sensor System implementation for upper limb rehabilitation to function as a complementary system for a patient’s progress supervision during rehabilitation exercises. A cost effective motion capture sensor node composed by a 9 Degrees-of-Freedom (DoF) Inertial Measurement Unit (IMU) is mounted on the patient’s upper limb segments and sends wirelessly the corresponding measured signals to a base station. The sensor orientation and the upper limb individual segments movement in 3-Dimensional (3D) space are derived by processing the sensors’ raw data. For the latter purpose, a biomechanical model which resembles that of a kinematic model of a robotic arm based on the Denavit-Hartenberg (DH) configuration is used to approximate in real time the upper limb movements. The joint angles of the upper limb model are estimated from the extracted sensor node’s orientation angles. The experimental results of a human performing common rehabilitation exercises using the proposed motion capture sensor node are compared with the ones using an off-the-shelf sensor. This comparison results to very low error rates with the root mean square error (RMSE) being about 0.02 m.
[ARTICLE] Estimation of grip strength using monocular camera for home-based hand rehabilitation – Full Text
Grip strength exercises are commonly used rehabilitation methods for recovery of hand function. They are easy to perform even without the direct support of a healthcare professional. However, without objective feedback, the patient may not be fully engaged in the rehabilitation process. To solve this problem, we developed a system for measuring grip strength in real time using a soft ball and a monocular camera. The system estimates the grip strength using the modelled relationship between the finger joint angles extracted from the camera image and the person’s grip strength. A patient can get the feedback as numbers or movements displayed on the screen. Experimental results showed that there is a correlation between the finger joint angles and the air pressure of a ball when squeezed. The average estimation error was 16.1 hPa, and the average measurement range was 100–230 hPa. The estimation error was about 12% of the measurement range. They also showed that there is a correlation between the air pressure of a ball and the applied force.
Hands and fingers play an important role in performing such tasks as grasping and operating objects in daily life. Hand injuries such as fractures and symptoms such as paralysis can weaken the hand muscles, reduce the range of finger motion, and reduce reaction time, preventing the person from moving his or her hand as expected. This decline of hand function can prevent the person from living comfortably. Therefore, rehabilitation is often prescribed for improving hand function.
There are various types of hand rehabilitation, such as electrical stimulation , mirroring , object-based training , and virtual reality-based rehabilitation . These methods are performed in accordance with the condition of the hand. The commonly used methods in clinical practice are grip strength exercises such as squeezing a flexible object (often a ball or cylindrical object). A soft ball is generally favoured as it exerts less stress on the hand and fingers. By squeezing such an object, the patient can exercise the finger joints and strengthen the muscles. Repetitive training like this exercise is effective for the improvement of active movements, especially for paralyzed patients . Finger flexion exercise is also effective for muscle activation [6,7]. In addition, such exercises can be easily performed in a home environment as they do not require difficult instructions or specialized equipment.
Rehabilitation in the home environment can reduce the burden on healthcare workers and the time demands on patients. However, grip strength exercises do not provide objective feedback. Moreover, patients tend to lose motivation because the exercise movements are monotonous. The use of ball-type grip dynamometers has been proposed to solve this problem . These devices have built-in sensors for measuring grip strength and can communicate with a computer. A person using such a device gets feedback on their grip strength and its changes and can share the data with the doctor or the therapist. Previous research has shown that visual feedback during rehabilitation is effective . Therefore, feedback in real time could help promote rehabilitation. While a ball-type grip dynamometer is effective for home-based measurement, the user has to buy a special device with built-in electronics. This may prevent smooth progress in rehabilitation.
In this paper, we present a system for measuring grip strength in real time that uses the monocular camera in a smartphone or another mobile device and a soft tennis ball (Figure 1). A mobile device widely used by the general public  and an inexpensive ball make this system easy to use in the home environment. The monocular camera captures an image of the hand squeezing the ball, and the finger joint angles are estimated from the image. For an accurate image of the hand area to be obtained, the ball and background must be white. In addition, users need to turn the hand holding the ball towards the camera so that the finger contour is visible to the camera. A regression model is created on the basis of the finger joint angles and ball air pressure. The ball air pressure is estimated using the regression model, and the air pressure is transformed into grip force. Experimental results showed that there is a relationship between the estimated finger joint angles and the air pressure of the ball when squeezed. In addition, we found that the average estimation error was 16.1 hPa for within-participant evaluation and that the average measurement range was 100–230 hPa. The estimation error was about 12% of the measurement range. There was also a relationship between the air pressure and the force applied to the ball.