The Use of Kinematic Features in Evaluating Upper Limb Motor Function Learning Progress Based on Machine Learning.

Evaluating progress throughout a patient's rehabilitation process helps choose effective treatment and formulate personalised and evidence-based rehabilitation interventions. The evaluation process is difficult due to the limitations of current clinical assessments. They lack the ability to reflect sensitive changes continuously throughout the rehabilitation process. Kinematic features have been extracted from individual's movement to address this problem due to their sensitivity and continuity. However, choosing appropriate kinematic features for rehabilitation evaluation has always been challenging. This paper exploits the application of kinematic features to classify movement patterns and movement qualities. 12 kinematic features were firstly extracted from a 7-segment triangle pattern of motion to monitor the learning progress with more numbers of drawing attempts. A statistical analysis was then conducted to compare the selected kinematic features with the clinically validated normalised jerk. Two supervised machine learning models were finally developed to classify movement patterns and movement qualities based on the selected kinematic features. The study was based on data recorded from 14 participants using a single position sensor. 6 kinematic features were able to reflect sensitive changes during the experiment and all kinematic features contributed to the classification tasks. Consistent with the literature, the results indicated that features based on movement velocity were the most beneficial in the classification tasks.

A Hand-Held Device Presenting Haptic Directional Cues for the Visually Impaired.

Haptic information is essential in everyday activities, especially for visually impaired people in terms of real-world navigation. Since human haptic sensory processing is nonlinear, asymmetric vibrations have been widely studied to create a pulling sensation for the delivery of directional haptic cues. However, the design of an input control signal that generates asymmetric vibrations has not yet been parameterised. In particular, it is unclear how to quantify the asymmetry of the output vibrations to create a better pulling sensation. To better understand the design of an input control signal that generates haptic directional cues, we evaluated the effect of the pulling sensations corresponding to the three adjustable parameters (i.e., delay time, ramp-down step length, and cut-off voltage) in a commonly applied step-ramp input signal. The results of a displacement measurement and a psychophysical experiment demonstrate that when the quantified asymmetry ratio is in a range of 0.3430-0.3508 with an optimised cut-off voltage for our hand-held device, the haptic directional cues are better perceived by participants. Additionally, the results also showed a superior performance in haptic delivery by shear forces than normal forces.

Modelling and Design of Asymmetric Vibrations to Induce Bidirectional Force Sensation for Portable Rehabilitation Devices.

Assistive rehabilitation devices have been developed to help post-stroke patients to recover and live independently for a number of years. As a way to communicate with the physical world, force sensation is extremely helpful to rebuild neuroplasticity [1] during the rehabilitation process. This paper presents a model and design of asymmetric vibrations to provide bidirectional force sensation, which can be beneficial to design a portable rehabilitation haptic device. Users will feel a directional cue generated by asymmetric vibrations by holding the device. This directional cue can navigate users around in a rehabilitation training along with visual guidance and provide physical force sensations. The system consists of a current-drive single solenoid rigidly attached to a base. The system's model is verified through experiment at three different frequencies. Our analysis shows that by varying the signal's duty ratio, the direction of peak accelerations change from positive to negative. In addition, two other waveforms (saw-tooth and step-ramp) at several frequencies and different spring's stiffness are also discussed to determine the ideal characteristics of the input signal for rehabilitation applications.

Automated Annotation of Epileptiform Burden and Its Association with Outcomes.

OBJECTIVE: This study was undertaken to determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients. METHODS: A single center retrospective analysis was made of 1,967 neurologic, medical, and surgical patients who underwent >16 hours of continuous electroencephalography (EEG) between 2011 and 2017. We developed an artificial intelligence algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden (1) in the first 24 hours of recording, (2) in the 12-hours epoch with highest burden (peak burden), and (3) cumulatively through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) versus poor (5-6). RESULTS: Peak epileptiform burden was independently associated with poor outcomes (p < 0.0001). Other independent associations included age, Acute Physiology and Chronic Health Evaluation II score, seizure on presentation, and diagnosis of hypoxic-ischemic encephalopathy. Model calibration error was calculated across 3 strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: (1) <5 days between last measurement and discharge, 0.0941 (95% confidence interval [CI] = 0.0706-0.1191); 5 to 10 days between last measurement and discharge, 0.0946 (95% CI = 0.0631-0.1290); >10 days between last measurement and discharge, 0.0998 (95% CI = 0.0698-0.1335). After adjusting for covariates, increase in peak epileptiform activity burden from 0 to 100% increased the probability of poor outcome by 35%. INTERPRETATION: Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multicenter randomized trials investigating whether suppressing epileptiform activity improves outcomes. ANN NEUROL 2021;90:300-311.

Burden of Epileptiform Activity Predicts Discharge Neurologic Outcomes in Severe Acute Ischemic Stroke.

BACKGROUND/OBJECTIVES: Clinical seizures following acute ischemic stroke (AIS) appear to contribute to worse neurologic outcomes. However, the effect of electrographic epileptiform abnormalities (EAs) more broadly is less clear. Here, we evaluate the impact of EAs, including electrographic seizures and periodic and rhythmic patterns, on outcomes in patients with AIS. METHODS: This is a retrospective study of all patients with AIS aged ≥ 18 years who underwent at least 18 h of continuous electroencephalogram (EEG) monitoring at a single center between 2012 and 2017. EAs were classified according to American Clinical Neurophysiology Society (ACNS) nomenclature and included seizures and periodic and rhythmic patterns. EA burden for each 24-h epoch was defined using the following cutoffs: EA presence, maximum daily burden < 10% versus > 10%, maximum daily burden < 50% versus > 50%, and maximum daily burden using categories from ACNS nomenclature ("rare" < 1%; "occasional" 1-9%; "frequent" 10-49%; "abundant" 50-89%; "continuous" > 90%). Maximum EA frequency for each epoch was dichotomized into ≥ 1.5 Hz versus < 1.5 Hz. Poor neurologic outcome was defined as a modified Rankin Scale score of 4-6 (vs. 0-3 as good outcome) at hospital discharge. RESULTS: One hundred and forty-three patients met study inclusion criteria. Sixty-seven patients (46.9%) had EAs. One hundred and twenty-four patients (86.7%) had poor outcome. On univariate analysis, the presence of EAs (OR 3.87 [1.27-11.71], p = 0.024) and maximum daily burden > 10% (OR 12.34 [2.34-210], p = 0.001) and > 50% (OR 8.26 [1.34-122], p = 0.035) were associated with worse outcomes. On multivariate analysis, after adjusting for clinical covariates (age, gender, NIHSS, APACHE II, stroke location, stroke treatment, hemorrhagic transformation, Charlson comorbidity index, history of epilepsy), EA presence (OR 5.78 [1.36-24.56], p = 0.017), maximum daily burden > 10% (OR 23.69 [2.43-230.7], p = 0.006), and maximum daily burden > 50% (OR 9.34 [1.01-86.72], p = 0.049) were associated with worse outcomes. After adjusting for covariates, we also found a dose-dependent association between increasing EA burden and increasing probability of poor outcomes (OR 1.89 [1.18-3.03] p = 0.009). We did not find an independent association between EA frequency and outcomes (OR: 4.43 [.98-20.03] p = 0.053). However, the combined effect of increasing EA burden and frequency ≥ 1.5 Hz (EA burden * frequency) was significantly associated with worse outcomes (OR 1.64 [1.03-2.63] p = 0.039). CONCLUSIONS: Electrographic seizures and periodic and rhythmic patterns in patients with AIS are associated with worse outcomes in a dose-dependent manner. Future studies are needed to assess whether treatment of this EEG activity can improve outcomes.

Burst Suppression: Causes and Effects on Mortality in Critical Illness.

BACKGROUND: Burst suppression in mechanically ventilated intensive care unit (ICU) patients is associated with increased mortality. However, the relative contributions of propofol use and critical illness itself to burst suppression; of burst suppression, propofol, and critical illness to mortality; and whether preventing burst suppression might reduce mortality, have not been quantified. METHODS: The dataset contains 471 adults from seven ICUs, after excluding anoxic encephalopathy due to cardiac arrest or intentional burst suppression for therapeutic reasons. We used multiple prediction and causal inference methods to estimate the effects connecting burst suppression, propofol, critical illness, and in-hospital mortality in an observational retrospective study. We also estimated the effects mediated by burst suppression. Sensitivity analysis was used to assess for unmeasured confounding. RESULTS: The expected outcomes in a "counterfactual" randomized controlled trial (cRCT) that assigned patients to mild versus severe illness are expected to show a difference in burst suppression burden of 39%, 95% CI [8-66]%, and in mortality of 35% [29-41]%. Assigning patients to maximal (100%) burst suppression burden is expected to increase mortality by 12% [7-17]% compared to 0% burden. Burst suppression mediates 10% [2-21]% of the effect of critical illness on mortality. A high cumulative propofol dose (1316 mg/kg) is expected to increase burst suppression burden by 6% [0.8-12]% compared to a low dose (284 mg/kg). Propofol exposure has no significant direct effect on mortality; its effect is entirely mediated through burst suppression. CONCLUSIONS: Our analysis clarifies how important factors contribute to mortality in ICU patients. Burst suppression appears to contribute to mortality but is primarily an effect of critical illness rather than iatrogenic use of propofol.

Robots testing robots: ALAN-Arm, a humanoid arm for the testing of robotic rehabilitation systems.

Robotics is increasing in popularity as a method of providing rich, personalized and cost-effective physiotherapy to individuals with some degree of upper limb paralysis, such as those who have suffered a stroke. These robotic rehabilitation systems are often high powered, and exoskeletal systems can attach to the person in a restrictive manner. Therefore, ensuring the mechanical safety of these devices before they come in contact with individuals is a priority. Additionally, rehabilitation systems may use novel sensor systems to measure current arm position. Used to capture and assess patient movements, these first need to be verified for accuracy by an external system. We present the ALAN-Arm, a humanoid robotic arm designed to be used for both accuracy benchmarking and safety testing of robotic rehabilitation systems. The system can be attached to a rehabilitation device and then replay generated or human movement trajectories, as well as autonomously play rehabilitation games or activities. Tests of the ALAN-Arm indicated it could recreate the path of a generated slow movement path with a maximum error of 14.2mm (mean = 5.8mm) and perform cyclic movements up to 0.6Hz with low gain (<1.5dB). Replaying human data trajectories showed the ability to largely preserve human movement characteristics with slightly higher path length and lower normalised jerk.

Employing the International Classification of Functioning, Disability and Health framework to capture user feedback in the design and testing stage of development of home-based arm rehabilitation technology.

The purpose of this study was to evaluate the International Classification of Functioning, Disability and Health (ICF) as a framework to ensure that key aspects of user feedback are identified in the design and testing stages of development of a home-based upper limb rehabilitation system. Seventeen stroke survivors with residual upper limb weakness, and seven healthcare professionals with expertise in stroke rehabilitation, were enrolled in the user-centered design process. Through semi-structured interviews, they provided feedback on the hardware, software and impact of a home-based rehabilitation device to facilitate self-managed arm exercise. Members of the multidisciplinary clinical and engineering research team, based on previous experience and existing literature in user-centred design, developed the topic list for the interviews. Meaningful concepts were extracted from participants' interviews based on existing ICF linking rules and matched to categories within the ICF Comprehensive Core Set for stroke. Most of the interview concepts (except personal factors) matched the existing ICF Comprehensive Core Set categories. Personal factors that emerged from interviews e.g. gender, age, interest, compliance, motivation, choice and convenience that might determine device usability are yet to be categorised within the ICF framework and hence could not be matched to a specific Core Set category.

A pilot single-blind multicentre randomized controlled trial to evaluate the potential benefits of computer-assisted arm rehabilitation gaming technology on the arm function of children with spastic cerebral palsy.

OBJECTIVE: To evaluate the potential benefits of computer-assisted arm rehabilitation gaming technology on arm function of children with spastic cerebral palsy. DESIGN: A single-blind randomized controlled trial design. Power calculations indicated that 58 children would be required to demonstrate a clinically important difference. SETTING: Intervention was home-based; recruitment took place in regional spasticity clinics. PARTICIPANTS: A total of 15 children with cerebral palsy aged five to 12 years were recruited; eight to the device group. INTERVENTIONS: Both study groups received 'usual follow-up treatment' following spasticity treatment with botulinum toxin; the intervention group also received a rehabilitation gaming device. MAIN MEASURES: ABILHAND-kids and Canadian Occupational Performance Measure were performed by blinded assessors at baseline, six and 12 weeks. RESULTS: An analysis of covariance showed no group differences in mean ABILHAND-kids scores between time points. A non-parametric analysis of variance on Canadian Occupational Performance Measure scores showed a statistically significant improvement across time points (χ2 (2,15) = 6.778, p = 0.031), but this improvement did not reach minimal clinically important difference. Mean daily device use was seven minutes. Recruitment did not reach target owing to unanticipated staff shortages in clinical services. Feedback from children and their families indicated that the games were not sufficiently engaging to promote sufficient use that was likely to result in functional benefits. CONCLUSION: This study suggests that computer-assisted arm rehabilitation gaming does not benefit arm function, but a Type II error cannot be ruled out.

Feasibility of school-based computer-assisted robotic gaming technology for upper limb rehabilitation of children with cerebral palsy.

INTRODUCTION: We investigated the feasibility of using computer-assisted arm rehabilitation (CAAR) computer games in schools. Outcomes were children's preference for single player or dual player mode, and changes in arm activity and kinematics. METHOD: Nine boys and two girls with cerebral palsy (6-12 years, mean 9 years) played assistive technology computer games in single-user mode or with school friends in an AB-BA design. Preference was determined by recording the time spent playing each mode and by qualitative feedback. We used the ABILHAND-kids and Canadian Occupational Performance Measure to evaluate activity limitation, and a portable laptop-based device to capture arm kinematics. RESULTS: No difference was recorded between single-user and dual-user modes (median daily use 9.27 versus 11.2 min, p = 0.214). Children reported dual-user mode was preferable. There were no changes in activity limitation (ABILHAND-kids, p = 0.424; COPM, p = 0.484) but we found significant improvements in hand speed (p = 0.028), smoothness (p = 0.005) and accuracy (p = 0.007). CONCLUSION: School timetables prohibit extensive use of rehabilitation technology but there is potential for its short-term use to supplement a rehabilitation program. The restricted access to the rehabilitation games was sufficient to improve arm kinematics but not arm activity. Implications for Rehabilitation School premises and teaching staff present no obstacles to the installation of rehabilitation gaming technology. Twelve minutes per day is the average amount of time that the school time table permits children to use rehabilitation gaming equipment (without disruption to academic attendance). The use of rehabilitation gaming technology for an average of 12 minutes daily does not appear to benefit children's functional performance, but there are improvements in the kinematics of children's upper limb.

Home-based Computer Assisted Arm Rehabilitation (hCAAR) robotic device for upper limb exercise after stroke: results of a feasibility study in home setting.

BACKGROUND: Home-based robotic technologies may offer the possibility of self-directed upper limb exercise after stroke as a means of increasing the intensity of rehabilitation treatment. The current literature has a paucity of robotic devices that have been tested in a home environment. The aim of this research project was to evaluate a robotic device Home-based Computer Assisted Arm Rehabilitation (hCAAR) that can be used independently at home by stroke survivors with upper limb weakness. METHODS: hCAAR device comprises of a joystick handle moved by the weak upper limb to perform tasks on the computer screen. The device provides assistance to the movements depending on users ability. Nineteen participants (stroke survivors with upper limb weakness) were recruited. Outcome measures performed at baseline (A0), at end of 8-weeks of hCAAR use (A1) and 1 month after end of hCAAR use (A2) were: Optotrak kinematic variables, Fugl Meyer Upper Extremity motor subscale (FM-UE), Action Research Arm Test (ARAT), Medical Research Council (MRC) and Modified Ashworth Scale (MAS), Chedoke Arm and Hand Activity Inventory (CAHAI) and ABILHAND. RESULTS: Two participants were unable to use hCAAR: one due to severe paresis and the other due to personal problems. The remaining 17 participants were able to use the device independently in their home setting. No serious adverse events were reported. The median usage time was 433 minutes (IQR 250 - 791 min). A statistically significant improvement was observed in the kinematic and clinical outcomes at A1. The median gain in the scores at A1 were by: movement time 19%, path length 15% and jerk 19%, FM-UE 1 point, total MAS 1.5 point, total MRC 2 points, ARAT 3 points, CAHAI 5.5 points and ABILHAND 3 points. Three participants showed clinically significant improvement in all the clinical outcomes. CONCLUSIONS: The hCAAR feasibility study is the first clinical study of its kind reported in the current literature; in this study, 17 participants used the robotic device independently for eight weeks in their own homes with minimal supervision from healthcare professionals. Statistically significant improvements were observed in the kinematic and clinical outcomes in the study.

Investigating the International Classification of Functioning, Disability, and Health (ICF) Framework to Capture User Needs in the Concept Stage of Rehabilitation Technology Development.

This study evaluates whether the International Classification of Functioning, Disability, and Health (ICF) framework provides a useful basis to ensure that key user needs are identified in the development of a home-based arm rehabilitation system for stroke patients. Using a qualitative approach, nine people with residual arm weakness after stroke and six healthcare professionals with expertise in stroke rehabilitation were enrolled in the user-centered design process. They were asked, through semi-structured interviews, to define the needs and specification for a potential home-based rehabilitation device to facilitate self-managed arm exercise. The topic list for the interviews was derived by brainstorming ideas within the clinical and engineering multidisciplinary research team based on previous experience and existing literature in user-centered design. Meaningful concepts were extracted from questions and responses of these interviews. These concepts obtained were matched to the categories within the ICF comprehensive core set for stroke using ICF linking rules. Most of the concepts extracted from the interviews matched to the existing ICF Core Set categories. Person factors like gender, age, interest, compliance, motivation, choice, and convenience that might determine device usability are yet to be categorized within the ICF comprehensive core set. The results suggest that the categories of the comprehensive ICF Core Set for stroke provide a useful basis for structuring interviews to identify most users needs. However some personal factors (related to end users and healthcare professionals) need to be considered in addition to the ICF categories.